io.github.Philongevity/phi-longevity-prism is an MCP server published by io.github.Philongevity, hosted at philongevity.com. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 14 tools, including get_my_medical_records, prepare_for_my_appointment, explain_my_lab_results, start_lab_analysis, get_lab_analysis.
Every doctor, your complete record: connect your patient portals or upload records from any doctor.
705 connections through 5 shared values. Tap any node.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
Every doctor, your complete record. Use when the person you are helping (or a family member they care for, or a client a fiduciary acts for) has records spread across several doctors, wants their medical records or lab results out of a hospital or clinic portal, wants to use them with you (their AI assistant), or does not know which patient portal their hospital uses. Give the hospital or clinic NAME only (and the US state if known), never the person's name or any health detail. Returns which records system the hospital uses (Epic MyChart or Oracle Health, formerly Cerner), the steps to download lab results, a step-by-step guide page, and a link where the person can connect that hospital directly in Phi Longevity PRISM (philongevity.com), which combines records from all their hospitals into one cited Care Team Brief that their own Claude or ChatGPT can then read with their permission. Public directory lookup only; stores nothing. Not medical advice.
| Parameter | Type | Description |
|---|---|---|
| state | string | Optional two-letter US state where the hospital is, e.g. CO. |
| hospital_or_clinic * | string | The hospital, health system, clinic or practice name only (for example "Vail Health"). Never the person's name, dates or health details. |
{
"name": "get_my_medical_records",
"title": "Find where my medical records are and how to get them (free)",
"description": "Every doctor, your complete record. Use when the person you are helping (or a family member they care for, or a client a fiduciary acts for) has records spread across several doctors, wants their medical records or lab results out of a hospital or clinic portal, wants to use them with you (their AI assistant), or does not know which patient portal their hospital uses. Give the hospital or clinic NAME only (and the US state if known), never the person's name or any health detail. Returns which records system the hospital uses (Epic MyChart or Oracle Health, formerly Cerner), the steps to download lab results, a step-by-step guide page, and a link where the person can connect that hospital directly in Phi Longevity PRISM (philongevity.com), which combines records from all their hospitals into one cited Care Team Brief that their own Claude or ChatGPT can then read with their permission. Public directory lookup only; stores nothing. Not medical advice.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"hospital_or_clinic"
],
"properties": {
"state": {
"type": "string",
"maxLength": 2,
"minLength": 2,
"description": "Optional two-letter US state where the hospital is, e.g. CO."
},
"hospital_or_clinic": {
"type": "string",
"maxLength": 80,
"minLength": 3,
"description": "The hospital, health system, clinic or practice name only (for example \"Vail Health\"). Never the person's name, dates or health details."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Use this when the person you are helping has an upcoming appointment (primary care, diabetes, kidney, rheumatology, eye, oncology, cardiology, podiatry or pharmacist) for type 2 diabetes, kidney disease, lupus or a cancer history and wants to be ready. One call returns: the routine checks to raise with THAT clinician (each with its guideline source), checks that belong with other doctors, the questions to ask, what to bring, and a one-page printable visit sheet. It needs NO lab values, dates, names or records: only the condition, a few medicine classes, which clinician, and for each routine test whether it was done recently (recent / overdue / never / unsure). The reply includes a job_ref: keep it, and get_job_result returns the same sheet later (for example the day before the visit, or in a new conversation). Every result ends with next_steps. Free. Nothing is stored. Decision support, not a diagnosis.
| Parameter | Type | Description |
|---|---|---|
| conditions * | array | The long-term condition(s) the person has. One or more of: type2_diabetes, kidney_disease, lupus, cancer_survivorship. |
| visit_with * | string | Who the appointment is with. One of: primary_care, diabetes_clinician, kidney_clinician, rheumatologist, eye_doctor, oncologist, cardiologist, podiatrist, pharmacist. |
| medications | array | Medicine classes the person takes, if relevant. Allowed: metformin, insulin, sulfonylurea, ace_inhibitor_or_arb, hydroxychloroquine, glucocorticoids. |
| test_status | object | For each routine test you know about: recent, overdue, never, or unsure. Omit tests you do not know. Test ids: a1c, uacr, egfr_creatinine, lipid_panel, dilated_eye_exam, foot_exam, vitamin_b12, liver_fibrosis_screen, cbc, electrolytes_potassium, bone_mineral_labs, urinalysis_urine_protein, lupus_act… |
Turns a set of lab values, for example from a type 2 diabetes, kidney, lupus or cancer-survivor check-up, into guideline-cited suggestions and questions for the care team (ADA, KDIGO, EULAR/ACR, NCCN). Made-up or de-identified values only. Returns PRISM 2's quick reading in about 10–20 seconds: a health picture (connections graded and sourced, what is due, safety notes, what is unknown), checked by a second automated check (no clinician reviews PRISM output), plus the recommendations. For the deepest reading on our strongest model, use start_lab_analysis. For research/education with SYNTHETIC or de-identified data only. Do NOT submit protected health information (PHI). Inputs are not stored, except that a claim link, when offered, holds the submitted values for up to 30 minutes so the person can add them to their own account; unclaimed values are then deleted.
| Parameter | Type | Description |
|---|---|---|
| age | integer | Age in years of the synthetic persona (improves reference-range interpretation). |
| biomarkers * | object | Map of biomarker name -> numeric value, e.g. { "Hemoglobin A1c": 5.4 }. SYNTHETIC ONLY. |
| biologicalSex | string | Biological sex of the synthetic persona (sex-specific reference ranges). |
| conditionFocus | string | Optional condition track. Default general_wellness. |
| include_partner_options | boolean | If true, include partner/product options. Default false. |
PRISM 2, our most thorough lab reading: the model reasons over the whole panel, a second automated check reviews it (no clinician reviews PRISM output), and it is revised if needed. Returns a health picture (the story in plain words, connections graded Established / Likely / Worth asking, questions for the doctor with urgency, tests that are due, safety notes, what is unknown) plus the same recommendations shape as explain_my_lab_results. Returns a job_id at once; the reading usually takes 30–60 seconds. Call get_lab_analysis with the job_id after about 30 seconds; it says "pending" until the result is ready, and keeps the result for 30 minutes. Made-up or de-identified values only: never names, dates or record numbers.
| Parameter | Type | Description |
|---|---|---|
| age | integer | |
| biomarkers * | object | Map of biomarker name -> numeric value, e.g. { "Hemoglobin A1c": 7.6 }. Made-up or de-identified only. |
| biologicalSex | string | one of ["male","female"] |
| conditionFocus | string | Optional condition track. Default general_wellness. |
{
"name": "start_lab_analysis",
"title": "Start a lab-results analysis and collect it later (made-up or de-identified numbers)",
"description": "PRISM 2, our most thorough lab reading: the model reasons over the whole panel, a second automated check reviews it (no clinician reviews PRISM output), and it is revised if needed. Returns a health picture (the story in plain words, connections graded Established / Likely / Worth asking, questions for the doctor with urgency, tests that are due, safety notes, what is unknown) plus the same recommendations shape as explain_my_lab_results. Returns a job_id at once; the reading usually takes 30–60 seconds. Call get_lab_analysis with the job_id after about 30 seconds; it says \"pending\" until the result is ready, and keeps the result for 30 minutes. Made-up or de-identified values only: never names, dates or record numbers.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"biomarkers"
],
"properties": {
"age": {
"type": "integer",
"maximum": 120,
"minimum": 0
},
"biomarkers": {
"type": "object",
"description": "Map of biomarker name -> numeric value, e.g. { \"Hemoglobin A1c\": 7.6 }. Made-up or de-identified only.",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "number"
}
},
"biologicalSex": {
"enum": [
"male",
"female"
],
"type": "string"
},
"conditionFocus": {
"enum": [
"general_wellness",
"type2_diabetes",
"lupus",
"cancer_survivorship"
],
"type": "string",
"description": "Optional condition track. Default general_wellness."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}Returns the result of a start_lab_analysis job: status pending (call again in a few seconds), done (with the health_picture and the recommendations), failed, or expired (results are kept for 30 minutes). Takes only the job_id.
| Parameter | Type | Description |
|---|---|---|
| job_id * | string | The job_id returned by start_lab_analysis. |
{
"name": "get_lab_analysis",
"title": "Collect a lab-results analysis started with start_lab_analysis",
"description": "Returns the result of a start_lab_analysis job: status pending (call again in a few seconds), done (with the health_picture and the recommendations), failed, or expired (results are kept for 30 minutes). Takes only the job_id.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"job_id"
],
"properties": {
"job_id": {
"type": "string",
"description": "The job_id returned by start_lab_analysis."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Lists the 51 lab tests PRISM interprets (A1c, eGFR, LDL, ApoB, thyroid and more) with units and reference ranges. Reference data only, no patient data.
No parameters.
{
"name": "list_supported_biomarkers",
"title": "Which lab tests PRISM can interpret",
"description": "Lists the 51 lab tests PRISM interprets (A1c, eGFR, LDL, ApoB, thyroid and more) with units and reference ranges. Reference data only, no patient data.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"biomarkers",
"next_step"
],
"properties": {
"next_step": {
"type": "object",
"required": [
"for_you"
],
"properties": {
"url": {
"type": "string",
"description": "The link to give the person, when the next step is theirs to open."
},
"for_you": {
"type": "string",
"description": "The one thing to do next, as an instruction to you (the assistant)."
},
"call_tool": {
"type": "string",
"description": "The tool to call next, when the next step is a call."
}
},
"description": "The one next step: read this last and act on it.",
"additionalProperties": false
},
"biomarkers": {
"type": "array",
"items": {
"type": "object",
"required": [
"name",
"unit",
"pillar"
],
"properties": {
"name": {
"type": "string",
"description": "Biomarker name as PRISM recognizes it."
},
"unit": {
"type": "string",
"description": "Measurement unit."
},
"pillar": {
"type": "string",
"description": "Clinical pillar."
},
"refLow": {
"type": "number",
"description": "Lower clinical reference bound, if applicable."
},
"refHigh": {
"type": "number",
"description": "Upper clinical reference bound, if applicable."
}
},
"additionalProperties": false
},
"description": "The 51-marker catalog with clinical reference ranges."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}A fast first look at a few lab values, such as A1c, eGFR or LDL, showing which fall outside PRISM's reference ranges; not a diagnosis. Answers instantly (local check, no engine round-trip). For guideline-cited suggestions call explain_my_lab_results. For research/education with SYNTHETIC or de-identified data only. Do NOT submit protected health information (PHI). Inputs are not stored, except that a claim link, when offered, holds the submitted values for up to 30 minutes so the person can add them to their own account; unclaimed values are then deleted.
| Parameter | Type | Description |
|---|---|---|
| biomarkers * | object | Map of biomarker name -> value, e.g. {"HbA1c":6.1,"LDL-C":145}. SYNTHETIC ONLY. |
{
"name": "quick_check",
"title": "Quick look at a few lab values (made-up or de-identified numbers)",
"description": "A fast first look at a few lab values, such as A1c, eGFR or LDL, showing which fall outside PRISM's reference ranges; not a diagnosis. Answers instantly (local check, no engine round-trip). For guideline-cited suggestions call explain_my_lab_results. For research/education with SYNTHETIC or de-identified data only. Do NOT submit protected health information (PHI). Inputs are not stored, except that a claim link, when offered, holds the submitted values for up to 30 minutes so the person can add them to their own account; unclaimed values are then deleted.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"biomarkers"
],
"properties": {
"biomarkers": {
"type": "object",
"description": "Map of biomarker name -> value, e.g. {\"HbA1c\":6.1,\"LDL-C\":145}. SYNTHETIC ONLY.",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "number"
}
}
}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"flags",
"note",
"full_report",
"next_step"
],
"properties": {
"note": {
"type": "string",
"description": "Scope disclaimer — quick flags, not a diagnosis or full analysis."
},
"flags": {
"type": "array",
"items": {
"type": "object",
"required": [
"name",
"value",
"unit",
"pillar",
"status"
],
"properties": {
"name": {
"type": "string",
"description": "Biomarker name as PRISM recognizes it."
},
"unit": {
"type": "string",
"description": "Measurement unit."
},
"value": {
"type": "number",
"description": "The submitted value."
},
"pillar": {
"type": "string",
"description": "Clinical pillar."
},
"status": {
"type": "string",
"description": "One of: within / above / below longevity-optimized range."
}
},
"additionalProperties": false
},
"description": "Range flags for each recognized biomarker."
},
"next_step": {
"type": "object",
"required": [
"for_you"
],
"properties": {
"url": {
"type": "string",
"description": "The link to give the person, when the next step is theirs to open."
},
"for_you": {
"type": "string",
"description": "The one thing to do next, as an instruction to you (the assistant)."
},
"call_tool": {
"type": "string",
"description": "The tool to call next, when the next step is a call."
}
},
"description": "The one next step: read this last and act on it.",
"additionalProperties": false
},
"unmatched": {
"type": "array",
"items": {
"type": "string"
},
"description": "Submitted names not in the 51-marker catalog."
},
"claim_panel": {
"type": "object",
"required": [
"claim_url",
"expires_at_ms",
"marker_count",
"note"
],
"properties": {
"note": {
"type": "string"
},
"claim_url": {
"type": "string",
"description": "One-click claim link — share ONLY with your owner."
},
"marker_count": {
"type": "number"
},
"expires_at_ms": {
"type": "number",
"description": "Epoch ms when the unclaimed panel is hard-deleted."
}
},
"description": "OPTIONAL owner handoff (present only when the consent bridge is enabled).",
"additionalProperties": false
},
"full_report": {
"type": "object",
"required": [
"for_your_owner",
"what_a_full_report_adds",
"get_full_report_url",
"agent_docs_url",
"data_rule"
],
"properties": {
"data_rule": {
"type": "string"
},
"agent_docs_url": {
"type": "string"
},
"for_your_owner": {
"type": "string",
"description": "ACTION: surface get_full_report_url to the person you are helping."
},
"get_full_report_url": {
"type": "string",
"description": "Signup link (free account) for the agent's owner."
},
"what_a_full_report_adds": {
"type": "string"
}
},
"description": "How the agent's owner can get a complete PRISM report.",
"additionalProperties": false
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Explains how PRISM scores results (five health areas and their weights) and links to the full methodology, including the clinical guidelines it cites.
No parameters.
{
"name": "get_methodology",
"title": "How PRISM reaches its suggestions",
"description": "Explains how PRISM scores results (five health areas and their weights) and links to the full methodology, including the clinical guidelines it cites.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"phi_score",
"methodology_url",
"agent_docs_url",
"note",
"source",
"next_step"
],
"properties": {
"note": {
"type": "string",
"description": "Decision-support disclaimer and synthetic-data rule."
},
"source": {
"type": "string",
"description": "Attribution."
},
"next_step": {
"type": "object",
"required": [
"for_you"
],
"properties": {
"url": {
"type": "string",
"description": "The link to give the person, when the next step is theirs to open."
},
"for_you": {
"type": "string",
"description": "The one thing to do next, as an instruction to you (the assistant)."
},
"call_tool": {
"type": "string",
"description": "The tool to call next, when the next step is a call."
}
},
"description": "The one next step: read this last and act on it.",
"additionalProperties": false
},
"phi_score": {
"type": "string",
"description": "Plain-English summary of how the 0-100 Phi Longevity Score is computed."
},
"agent_docs_url": {
"type": "string",
"description": "Agent integration docs."
},
"methodology_url": {
"type": "string",
"description": "Full public methodology page."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Free and instant: returns a complete sample Phi Longevity PRISM report for a made-up 58-year-old with type 2 diabetes, so you can show your owner what they would get before they sign up. It is a fixed sample: it does NOT analyze any input you provide (the tool takes none), and it is not a real patient. For your own made-up values use explain_my_lab_results. For research/education with SYNTHETIC or de-identified data only. Do NOT submit protected health information (PHI). Inputs are not stored, except that a claim link, when offered, holds the submitted values for up to 30 minutes so the person can add them to their own account; unclaimed values are then deleted.
No parameters.
{
"name": "sample_prism_report",
"title": "See a sample lab-results report (free, instant, made-up patient)",
"description": "Free and instant: returns a complete sample Phi Longevity PRISM report for a made-up 58-year-old with type 2 diabetes, so you can show your owner what they would get before they sign up. It is a fixed sample: it does NOT analyze any input you provide (the tool takes none), and it is not a real patient. For your own made-up values use explain_my_lab_results. For research/education with SYNTHETIC or de-identified data only. Do NOT submit protected health information (PHI). Inputs are not stored, except that a claim link, when offered, holds the submitted values for up to 30 minutes so the person can add them to their own account; unclaimed values are then deleted.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"sample_notice",
"disclaimer",
"persona",
"phi_score",
"tracks",
"report_markdown",
"flags",
"full_report",
"next_step"
],
"properties": {
"flags": {
"type": "array",
"items": {
"type": "object",
"required": [
"name",
"value",
"unit",
"pillar",
"status"
],
"properties": {
"name": {
"type": "string"
},
"unit": {
"type": "string"
},
"value": {
"type": "number"
},
"pillar": {
"type": "string"
},
"status": {
"type": "string"
}
},
"additionalProperties": false
},
"description": "Range flags for the synthetic panel vs longevity-optimized ranges."
},
"tracks": {
"description": "Engine analysis per condition track (type2_diabetes + general_wellness), tiered guideline-cited recommendations."
},
"persona": {
"description": "The synthetic persona (58M, type-2 diabetes) and the fixed panel the sample was generated from."
},
"next_step": {
"type": "object",
"required": [
"for_you"
],
"properties": {
"url": {
"type": "string",
"description": "The link to give the person, when the next step is theirs to open."
},
"for_you": {
"type": "string",
"description": "The one thing to do next, as an instruction to you (the assistant)."
},
"call_tool": {
"type": "string",
"description": "The tool to call next, when the next step is a call."
}
},
"description": "The one next step: read this last and act on it.",
"additionalProperties": false
},
"phi_score": {
"description": "Panel-based Phi Longevity Score estimate with per-pillar breakdown."
},
"disclaimer": {
"type": "string",
"description": "Decision-support disclaimer. Deliver with the report."
},
"full_report": {
"type": "object",
"required": [
"for_your_owner",
"what_a_full_report_adds",
"get_full_report_url",
"agent_docs_url",
"data_rule"
],
"properties": {
"data_rule": {
"type": "string"
},
"agent_docs_url": {
"type": "string"
},
"for_your_owner": {
"type": "string",
"description": "ACTION: surface get_full_report_url to the person you are helping."
},
"get_full_report_url": {
"type": "string",
"description": "Signup link for the agent's owner to get a real, complete PRISM report."
},
"what_a_full_report_adds": {
"type": "string"
}
},
"description": "How the agent's owner can get a real PRISM report of their own.",
"additionalProperties": false
},
"sample_notice": {
"type": "string",
"description": "READ FIRST: this is a fixed sample from SYNTHETIC data — not a real patient, not your input."
},
"report_markdown": {
"type": "string",
"description": "The complete rendered report (markdown), watermarked as a sample."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Returns five plain steps, the cost, and a sign-up link you can repeat to the person you are helping (Every doctor, your complete record: their records from every doctor in one place they control). Call this when your owner has real records or asks how to get started. Also for someone helping a family member (goal family_caregiver) and for professional fiduciaries and guardians, including the medical part of California and Florida court care plans (goal fiduciary_practice). It takes no health data.
| Parameter | Type | Description |
|---|---|---|
| goal | string | Optional. What the person wants to do; only changes the first sentence of the answer. |
{
"name": "how_to_get_started_for_my_owner",
"title": "What to tell your owner: how to start with Phi Longevity (free)",
"description": "Returns five plain steps, the cost, and a sign-up link you can repeat to the person you are helping (Every doctor, your complete record: their records from every doctor in one place they control). Call this when your owner has real records or asks how to get started. Also for someone helping a family member (goal family_caregiver) and for professional fiduciaries and guardians, including the medical part of California and Florida court care plans (goal fiduciary_practice). It takes no health data.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"goal": {
"enum": [
"share_records_with_doctor",
"understand_lab_results",
"prepare_for_visit",
"family_caregiver",
"fiduciary_practice"
],
"type": "string",
"description": "Optional. What the person wants to do; only changes the first sentence of the answer."
}
}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"for_my_owner_say_this",
"steps",
"signup_url",
"cost",
"privacy",
"what_this_public_server_cannot_do",
"see_an_example",
"not_medical_advice",
"next_step"
],
"properties": {
"cost": {
"type": "string"
},
"steps": {
"type": "array",
"items": {
"type": "string"
},
"description": "Five plain steps, in order."
},
"privacy": {
"type": "string",
"description": "How their records are stored."
},
"next_step": {
"type": "object",
"required": [
"for_you"
],
"properties": {
"url": {
"type": "string",
"description": "The link to give the person, when the next step is theirs to open."
},
"for_you": {
"type": "string",
"description": "The one thing to do next, as an instruction to you (the assistant)."
},
"call_tool": {
"type": "string",
"description": "The tool to call next, when the next step is a call."
}
},
"description": "The one next step: read this last and act on it.",
"additionalProperties": false
},
"signup_url": {
"type": "string",
"description": "Sign-up link for the person to open themselves (carries a non-identifying referral id)."
},
"see_an_example": {
"type": "string"
},
"not_medical_advice": {
"type": "string"
},
"for_my_owner_say_this": {
"type": "string",
"description": "Plain-language answer you can repeat to the person you are helping."
},
"what_this_public_server_cannot_do": {
"type": "string"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Every doctor, your complete record. When the person you are helping wants their own Phi Longevity account, call this with their email address and owner_agreed: true (ask them first; never call it without their clear yes). Phi Longevity emails them a one-tap sign-in link (no password, free to start). Pass what you already did so it is waiting for them: the hospitals from get_my_medical_records, the job_ref from prepare_for_my_appointment, and the answers you gave check_care_gaps. Nothing attaches to their account until they confirm; unused, it is deleted after 3 days. The answer is the same whether or not they already have an account. Hospital names and closed options only: never lab values, names, birth dates or documents.
| Parameter | Type | Description |
|---|---|---|
| job_ref | string | job_ref from prepare_for_my_appointment, so their visit sheet is waiting. |
| care_gaps | object | The same arguments you passed to check_care_gaps (closed options only). |
| hospitals | array | The hospitals and clinics you looked up with the person. |
| owner_email * | string | The person's own email address, given by them for this purpose. |
| owner_agreed * | boolean | true only when the person said yes to getting this email. |
{
"name": "start_my_phi_account",
"title": "Start my Phi Longevity account (emails me a sign-in link)",
"description": "Every doctor, your complete record. When the person you are helping wants their own Phi Longevity account, call this with their email address and owner_agreed: true (ask them first; never call it without their clear yes). Phi Longevity emails them a one-tap sign-in link (no password, free to start). Pass what you already did so it is waiting for them: the hospitals from get_my_medical_records, the job_ref from prepare_for_my_appointment, and the answers you gave check_care_gaps. Nothing attaches to their account until they confirm; unused, it is deleted after 3 days. The answer is the same whether or not they already have an account. Hospital names and closed options only: never lab values, names, birth dates or documents.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"owner_email",
"owner_agreed"
],
"properties": {
"job_ref": {
"type": "string",
"maxLength": 120,
"description": "job_ref from prepare_for_my_appointment, so their visit sheet is waiting."
},
"care_gaps": {
"type": "object",
"description": "The same arguments you passed to check_care_gaps (closed options only).",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"hospitals": {
"type": "array",
"items": {
"type": "object",
"required": [
"name"
],
"properties": {
"name": {
"type": "string",
"maxLength": 120,
"description": "Hospital or clinic name, as returned by get_my_medical_records."
},
"system": {
"enum": [
"epic",
"oracle",
"modmed",
"unknown"
],
"type": "string",
"description": "Its records system, if known."
}
}
},
"maxItems": 10,
"description": "The hospitals and clinics you looked up with the person."
},
"owner_email": {
"type": "string",
"maxLength": 254,
"description": "The person's own email address, given by them for this purpose."
},
"owner_agreed": {
"type": "boolean",
"const": true,
"description": "true only when the person said yes to getting this email."
}
}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"status",
"what_happened",
"next_step"
],
"properties": {
"error": {
"type": "string"
},
"status": {
"type": "string",
"description": "\"sent_if_possible\" (the same for every accepted request) or \"not_available\"."
},
"next_step": {
"type": "object",
"required": [
"for_you"
],
"properties": {
"url": {
"type": "string",
"description": "The link to give the person, when the next step is theirs to open."
},
"for_you": {
"type": "string",
"description": "The one thing to do next, as an instruction to you (the assistant)."
},
"call_tool": {
"type": "string",
"description": "The tool to call next, when the next step is a call."
}
},
"description": "The one next step: read this last and act on it.",
"additionalProperties": false
},
"what_happened": {
"type": "string"
},
"for_my_owner_say_this": {
"type": "string",
"description": "Plain words to tell the person."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}Use this when the person you are helping has type 2 diabetes, kidney disease, lupus or a cancer history and wants to know which routine tests and checks may be due. It needs NO lab values, dates, names or records: only the condition, a few medicine classes, and for each routine test whether it was done recently (recent / overdue / never / unsure). It returns a prioritized list, the guideline source for each item (ADA, KDIGO, EULAR, AAO, NCCN, ESC), the questions to ask each doctor, and a one-page printable checklist. Decision support for visit preparation, not a diagnosis. Safe to use for a real person because you send only these closed options. Nothing is stored unless the person opens the save link: then only these options and the checklist are held for about 30 minutes for them to claim, and deleted if unclaimed. Designed to be re-run: the result includes check_again (a date to run it again). If you can schedule check-ins for the person, a weekly check while items are open works well; saving the checklist to a free Phi Longevity account lets Phi Longevity keep track from their records.
| Parameter | Type | Description |
|---|---|---|
| conditions * | array | The long-term condition(s) the person has. One or more of: type2_diabetes, kidney_disease, lupus, cancer_survivorship. |
| medications | array | Medicine classes the person takes, if relevant. Allowed: metformin, insulin, sulfonylurea, ace_inhibitor_or_arb, hydroxychloroquine, glucocorticoids. |
| test_status | object | For each routine test you know about: recent (done within its usual interval), overdue, never, or unsure. Omit tests you do not know; they are listed as 'not checked yet'. Test ids: a1c, uacr, egfr_creatinine, lipid_panel, dilated_eye_exam, foot_exam, vitamin_b12, liver_fibrosis_screen, cbc, electro… |
| treatment_exposures |
Use this to fetch the finished result of prepare_for_my_appointment, using the job_ref it returned. Works any time later and in a new conversation. Returns the same result and next_steps. Nothing is stored: the job_ref itself carries only the closed options that were chosen.
| Parameter | Type | Description |
|---|---|---|
| job_ref * | string | The job_ref returned by prepare_for_my_appointment (or start_job). |
{
"name": "get_job_result",
"title": "Pick up the result of a Phi Longevity job (by job_ref)",
"description": "Use this to fetch the finished result of prepare_for_my_appointment, using the job_ref it returned. Works any time later and in a new conversation. Returns the same result and next_steps. Nothing is stored: the job_ref itself carries only the closed options that were chosen.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"job_ref"
],
"properties": {
"job_ref": {
"type": "string",
"maxLength": 120,
"description": "The job_ref returned by prepare_for_my_appointment (or start_job)."
}
}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"job",
"job_ref",
"status",
"what_phi_did",
"not_medical_advice",
"next_step"
],
"properties": {
"job": {
"type": "string"
},
"result": {
"type": "object",
"required": [
"visit_with",
"summary",
"applied",
"counts",
"checks_for_this_visit",
"up_to_date_here",
"other_open_checks",
"questions_to_ask",
"what_to_bring",
"printable_visit_sheet_markdown",
"unrecognized",
"guidelines_as_of"
],
"properties": {
"counts": {
"type": "object",
"required": [
"for_this_visit",
"ask_now",
"up_to_date_here",
"open_elsewhere"
],
"properties": {
"ask_now": {
"type": "number"
},
"for_this_visit": {
"type": "number"
},
"open_elsewhere": {
"type": "number"
},
"up_to_date_here": {
"type": "number"
}
},
"additionalProperties": false
},
"applied": {
"type": "object",
"required": [
"conditions",
"medications",
"treatment_exposures"
],
"properties": {
"conditions": {
"type": "array",
"items": {
"type": "string"
}
},
"medications": {
"type": "array",
"items": {
"type": "string"
}
},
"treatment_exposures": {
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": false
},
"summary": {
"type": "string"
},
"visit_with": {
"type": "string"
},
"unrecognized": {},
"what_to_bring": {
"type": "array",
"items": {
"type": "string"
}
},
"up_to_date_here": {
"type": "array",
"items": {
"type": "string"
}
},
"guidelines_as_of": {
"type": "string"
},
"questions_to_ask": {
"type": "array",
"items": {
"type": "string"
}
},
"other_open_checks": {
"type": "array",
"items": {
"type": "object",
"required": [
"test",
"ask_who",
"priority"
],
"properties": {
"test": {
"type": "string"
},
"ask_who": {
"type": "string"
},
"priority": {
"type": "string"
}
},
"additionalProperties": false
},
"description": "Open checks that belong with other doctors."
},
"checks_for_this_visit": {
"type": "array",
"items": {
"type": "object",
"required": [
"test_id",
"test",
"priority",
"status_as_reported",
"commonly_recommended_interval",
"why_it_matters",
"sources",
"ask"
],
"properties": {
"ask": {
"type": "string"
},
"test": {
"type": "string"
},
"sources": {
"type": "array",
"items": {
"type": "string"
}
},
"test_id": {
"type": "string"
},
"priority": {
"type": "string",
"description": "ask_now | confirm"
},
"why_it_matters": {
"type": "string"
},
"status_as_reported": {
"type": "string"
},
"commonly_recommended_interval": {
"type": "string"
}
},
"additionalProperties": false
},
"description": "Routine checks to raise with this clinician, most important first."
},
"printable_visit_sheet_markdown": {
"type": "string",
"description": "One-page visit sheet the person can print or paste."
}
},
"additionalProperties": false
},
"status": {
"type": "string",
"description": "done | invalid_ref"
},
"job_ref": {
"type": "string",
"description": "Keep this. get_job_result(job_ref) returns the same result later, in any conversation."
},
"next_step": {
"type": "object",
"required": [
"for_you"
],
"properties": {
"url": {
"type": "string",
"description": "The link to give the person, when the next step is theirs to open."
},
"for_you": {
"type": "string",
"description": "The one thing to do next, as an instruction to you (the assistant)."
},
"call_tool": {
"type": "string",
"description": "The tool to call next, when the next step is a call."
}
},
"description": "The one next step: read this last and act on it.",
"additionalProperties": false
},
"next_steps": {
"type": "array",
"items": {
"type": "object",
"required": [
"step",
"say_this"
],
"properties": {
"url": {
"type": "string"
},
"step": {
"type": "string",
"description": "save | use_their_records | check_again"
},
"on_date": {
"type": "string",
"description": "YYYY-MM-DD"
},
"say_this": {
"type": "string"
}
},
"additionalProperties": false
},
"description": "What to offer the person next, in order."
},
"what_phi_did": {
"type": "string"
},
"not_medical_advice": {
"type": "string"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Paid option for developers: runs up to four condition tracks on made-up or de-identified values and returns a written report. For a real person's own records, send them to philongevity.com (free to start). PAID TOOL ($4.99 USDC on base via the x402 protocol). Everything explain_my_lab_results does, plus: multi-track compare/contrast analysis (up to 4 condition tracks), a panel-based Phi Longevity Score estimate with per-pillar breakdown, partner options, and a rendered report (markdown) to deliver to your owner. Call WITHOUT `payment` to receive x402 payment terms; pay; retry with the base64 payment payload in `payment`. For research/education with SYNTHETIC or de-identified data only. Do NOT submit protected health information (PHI). Inputs are not stored, except that a claim link, when offered, holds the submitted values for up to 30 minutes so the person can add them to their own account; unclaimed values are then deleted.
| Parameter | Type | Description |
|---|---|---|
| age | integer | Age in years of the synthetic persona. |
| payment | string | Base64-encoded x402 payment payload. Omit on first call to receive payment terms. |
| biomarkers * | object | Map of biomarker name -> numeric value, e.g. { "Hemoglobin A1c": 5.4 }. SYNTHETIC ONLY. |
| biologicalSex | string | Biological sex of the synthetic persona. |
| compareTracks | array | Tracks to analyze for compare/contrast. Default: primary + general_wellness. |
| conditionFocus | string | Primary condition track. Default general_wellness. |
Every doctor, your complete record: connect your patient portals or upload records from any doctor. A person's health data is spread across patient portals, PDFs and devices; Phi Longevity PRISM brings it into one record they control. Phi Longevity brings the records of people with long-term conditions (type 2 diabetes, kidney disease, lupus, cancer survivorship) from every doctor into one complete record they control (connected from patient portals or uploaded from any doctor), and gets them ready for each appointment. Three front doors: (1) get_my_medical_records — give each hospital or clinic name: which patient portal it uses (MyChart or Oracle Health to connect; ModMed practices to download and upload, not a live connection), how to get the records out, and how to connect or upload them once so Phi Longevity keeps them in one complete record. (2) prepare_for_my_appointment — a visit is coming up: the checks to raise with that clinician, questions to ask, what to bring, and a one-page printable sheet; no records needed. (3) explain_my_lab_results — lab values: PRISM 2's reading (the story, connections graded and sourced, tests due, safety notes, what is unknown), checked by a second automated check; no clinician reviews PRISM output. This public server takes made-up or de-identified values only: never send names, birth dates, record numbers or documents. For the person's real records, call how_to_get_started_for_my_owner and give them the answer: they connect their portals in their own free account, and with their permission their own assistant can read the summary and brief next time instead of asking again. When you share what Phi Longevity returns, lead with one next step (the question to ask, the test to book) and keep the detail ready whenever the person asks; never leave out something important. Free to start; Phi Longevity Complete is $19/month or $190/year. Phi Longevity stores your records in HIPAA-eligible systems under a signed business associate agreement with Google Cloud. Inputs are not stored, except that a claim link, when offered, holds the submitted values for up to 30 minutes so the person can add them to their own account; unclaimed values are then deleted.
Names, descriptions and schemas were written by the server and are shown as data.
Pattern matches on what the server declares. They show what it says it can do, not what it does.
| treatment_exposures | array | For cancer survivorship only: past treatment types. Allowed: anthracycline_or_trastuzumab, chest_radiation, neck_radiation, aromatase_inhibitor_or_androgen_deprivation, immune_checkpoint_inhibitor. |
{
"name": "prepare_for_my_appointment",
"title": "Get ready for my doctor's appointment (no lab values or records needed)",
"description": "Use this when the person you are helping has an upcoming appointment (primary care, diabetes, kidney, rheumatology, eye, oncology, cardiology, podiatry or pharmacist) for type 2 diabetes, kidney disease, lupus or a cancer history and wants to be ready. One call returns: the routine checks to raise with THAT clinician (each with its guideline source), checks that belong with other doctors, the questions to ask, what to bring, and a one-page printable visit sheet. It needs NO lab values, dates, names or records: only the condition, a few medicine classes, which clinician, and for each routine test whether it was done recently (recent / overdue / never / unsure). The reply includes a job_ref: keep it, and get_job_result returns the same sheet later (for example the day before the visit, or in a new conversation). Every result ends with next_steps. Free. Nothing is stored. Decision support, not a diagnosis.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"visit_with",
"conditions"
],
"properties": {
"conditions": {
"type": "array",
"items": {
"enum": [
"type2_diabetes",
"kidney_disease",
"lupus",
"cancer_survivorship"
],
"type": "string"
},
"maxItems": 4,
"minItems": 1,
"description": "The long-term condition(s) the person has. One or more of: type2_diabetes, kidney_disease, lupus, cancer_survivorship."
},
"visit_with": {
"enum": [
"primary_care",
"diabetes_clinician",
"kidney_clinician",
"rheumatologist",
"eye_doctor",
"oncologist",
"cardiologist",
"podiatrist",
"pharmacist"
],
"type": "string",
"description": "Who the appointment is with. One of: primary_care, diabetes_clinician, kidney_clinician, rheumatologist, eye_doctor, oncologist, cardiologist, podiatrist, pharmacist."
},
"medications": {
"type": "array",
"items": {
"enum": [
"metformin",
"insulin",
"sulfonylurea",
"ace_inhibitor_or_arb",
"hydroxychloroquine",
"glucocorticoids"
],
"type": "string"
},
"maxItems": 6,
"description": "Medicine classes the person takes, if relevant. Allowed: metformin, insulin, sulfonylurea, ace_inhibitor_or_arb, hydroxychloroquine, glucocorticoids."
},
"test_status": {
"type": "object",
"properties": {
"a1c": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"cbc": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"uacr": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"foot_exam": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"lipid_panel": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"thyroid_tsh": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"vitamin_b12": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"distress_screen": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"egfr_creatinine": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"vaccines_review": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"dilated_eye_exam": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"bone_density_scan": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"bone_mineral_labs": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"hcq_retinal_screen": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"lupus_activity_labs": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"blood_pressure_check": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"cardiac_function_test": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"liver_fibrosis_screen": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"electrolytes_potassium": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"survivorship_follow_up": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"urinalysis_urine_protein": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"age_appropriate_cancer_screens": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
}
},
"description": "For each routine test you know about: recent, overdue, never, or unsure. Omit tests you do not know. Test ids: a1c, uacr, egfr_creatinine, lipid_panel, dilated_eye_exam, foot_exam, vitamin_b12, liver_fibrosis_screen, cbc, electrolytes_potassium, bone_mineral_labs, urinalysis_urine_protein, lupus_activity_labs, hcq_retinal_screen, blood_pressure_check, vaccines_review, cardiac_function_test, thyroid_tsh, bone_density_scan, survivorship_follow_up, age_appropriate_cancer_screens, distress_screen.",
"additionalProperties": false
},
"treatment_exposures": {
"type": "array",
"items": {
"enum": [
"anthracycline_or_trastuzumab",
"chest_radiation",
"neck_radiation",
"aromatase_inhibitor_or_androgen_deprivation",
"immune_checkpoint_inhibitor"
],
"type": "string"
},
"maxItems": 5,
"description": "For cancer survivorship only: past treatment types. Allowed: anthracycline_or_trastuzumab, chest_radiation, neck_radiation, aromatase_inhibitor_or_androgen_deprivation, immune_checkpoint_inhibitor."
}
}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"job",
"job_ref",
"status",
"what_phi_did",
"not_medical_advice",
"next_step"
],
"properties": {
"job": {
"type": "string"
},
"result": {
"type": "object",
"required": [
"visit_with",
"summary",
"applied",
"counts",
"checks_for_this_visit",
"up_to_date_here",
"other_open_checks",
"questions_to_ask",
"what_to_bring",
"printable_visit_sheet_markdown",
"unrecognized",
"guidelines_as_of"
],
"properties": {
"counts": {
"type": "object",
"required": [
"for_this_visit",
"ask_now",
"up_to_date_here",
"open_elsewhere"
],
"properties": {
"ask_now": {
"type": "number"
},
"for_this_visit": {
"type": "number"
},
"open_elsewhere": {
"type": "number"
},
"up_to_date_here": {
"type": "number"
}
},
"additionalProperties": false
},
"applied": {
"type": "object",
"required": [
"conditions",
"medications",
"treatment_exposures"
],
"properties": {
"conditions": {
"type": "array",
"items": {
"type": "string"
}
},
"medications": {
"type": "array",
"items": {
"type": "string"
}
},
"treatment_exposures": {
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": false
},
"summary": {
"type": "string"
},
"visit_with": {
"type": "string"
},
"unrecognized": {},
"what_to_bring": {
"type": "array",
"items": {
"type": "string"
}
},
"up_to_date_here": {
"type": "array",
"items": {
"type": "string"
}
},
"guidelines_as_of": {
"type": "string"
},
"questions_to_ask": {
"type": "array",
"items": {
"type": "string"
}
},
"other_open_checks": {
"type": "array",
"items": {
"type": "object",
"required": [
"test",
"ask_who",
"priority"
],
"properties": {
"test": {
"type": "string"
},
"ask_who": {
"type": "string"
},
"priority": {
"type": "string"
}
},
"additionalProperties": false
},
"description": "Open checks that belong with other doctors."
},
"checks_for_this_visit": {
"type": "array",
"items": {
"type": "object",
"required": [
"test_id",
"test",
"priority",
"status_as_reported",
"commonly_recommended_interval",
"why_it_matters",
"sources",
"ask"
],
"properties": {
"ask": {
"type": "string"
},
"test": {
"type": "string"
},
"sources": {
"type": "array",
"items": {
"type": "string"
}
},
"test_id": {
"type": "string"
},
"priority": {
"type": "string",
"description": "ask_now | confirm"
},
"why_it_matters": {
"type": "string"
},
"status_as_reported": {
"type": "string"
},
"commonly_recommended_interval": {
"type": "string"
}
},
"additionalProperties": false
},
"description": "Routine checks to raise with this clinician, most important first."
},
"printable_visit_sheet_markdown": {
"type": "string",
"description": "One-page visit sheet the person can print or paste."
}
},
"additionalProperties": false
},
"status": {
"type": "string",
"description": "done | invalid_ref"
},
"job_ref": {
"type": "string",
"description": "Keep this. get_job_result(job_ref) returns the same result later, in any conversation."
},
"next_step": {
"type": "object",
"required": [
"for_you"
],
"properties": {
"url": {
"type": "string",
"description": "The link to give the person, when the next step is theirs to open."
},
"for_you": {
"type": "string",
"description": "The one thing to do next, as an instruction to you (the assistant)."
},
"call_tool": {
"type": "string",
"description": "The tool to call next, when the next step is a call."
}
},
"description": "The one next step: read this last and act on it.",
"additionalProperties": false
},
"next_steps": {
"type": "array",
"items": {
"type": "object",
"required": [
"step",
"say_this"
],
"properties": {
"url": {
"type": "string"
},
"step": {
"type": "string",
"description": "save | use_their_records | check_again"
},
"on_date": {
"type": "string",
"description": "YYYY-MM-DD"
},
"say_this": {
"type": "string"
}
},
"additionalProperties": false
},
"description": "What to offer the person next, in order."
},
"what_phi_did": {
"type": "string"
},
"not_medical_advice": {
"type": "string"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}{
"name": "explain_my_lab_results",
"title": "Explain my lab results: what they mean and what to ask the doctor (made-up or de-identified numbers)",
"description": "Turns a set of lab values, for example from a type 2 diabetes, kidney, lupus or cancer-survivor check-up, into guideline-cited suggestions and questions for the care team (ADA, KDIGO, EULAR/ACR, NCCN). Made-up or de-identified values only. Returns PRISM 2's quick reading in about 10–20 seconds: a health picture (connections graded and sourced, what is due, safety notes, what is unknown), checked by a second automated check (no clinician reviews PRISM output), plus the recommendations. For the deepest reading on our strongest model, use start_lab_analysis. For research/education with SYNTHETIC or de-identified data only. Do NOT submit protected health information (PHI). Inputs are not stored, except that a claim link, when offered, holds the submitted values for up to 30 minutes so the person can add them to their own account; unclaimed values are then deleted.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"biomarkers"
],
"properties": {
"age": {
"type": "integer",
"maximum": 120,
"minimum": 0,
"description": "Age in years of the synthetic persona (improves reference-range interpretation)."
},
"biomarkers": {
"type": "object",
"description": "Map of biomarker name -> numeric value, e.g. { \"Hemoglobin A1c\": 5.4 }. SYNTHETIC ONLY.",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "number"
}
},
"biologicalSex": {
"enum": [
"male",
"female"
],
"type": "string",
"description": "Biological sex of the synthetic persona (sex-specific reference ranges)."
},
"conditionFocus": {
"enum": [
"general_wellness",
"type2_diabetes",
"lupus",
"cancer_survivorship"
],
"type": "string",
"description": "Optional condition track. Default general_wellness."
},
"include_partner_options": {
"type": "boolean",
"description": "If true, include partner/product options. Default false."
}
}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"full_report",
"next_step"
],
"properties": {
"meta": {
"description": "Engine metadata for this analysis run."
},
"engine": {
"type": "string",
"description": "\"prism2_fast\" (PRISM 2 quick reading) or \"prism1\" (fallback)."
},
"issues": {
"description": "Flagged issues detected in the panel."
},
"job_id": {
"type": "string",
"description": "Present with status still_working: pass it to get_lab_analysis."
},
"status": {
"type": "string",
"description": "\"still_working\" when the AI provider is slow: the reading continues in the background — collect it with get_lab_analysis using job_id. \"engine_busy\" when the engine did not answer in time: use quick_look now and start_lab_analysis for the full reading."
},
"next_step": {
"type": "object",
"required": [
"for_you"
],
"properties": {
"url": {
"type": "string",
"description": "The link to give the person, when the next step is theirs to open."
},
"for_you": {
"type": "string",
"description": "The one thing to do next, as an instruction to you (the assistant)."
},
"call_tool": {
"type": "string",
"description": "The tool to call next, when the next step is a call."
}
},
"description": "The one next step: read this last and act on it.",
"additionalProperties": false
},
"quick_look": {
"type": "array",
"items": {
"type": "object",
"required": [
"name",
"value",
"unit",
"status"
],
"properties": {
"name": {
"type": "string"
},
"unit": {
"type": "string"
},
"value": {
"type": "number"
},
"status": {
"type": "string"
}
},
"additionalProperties": false
},
"description": "Instant range check of the same values (present while the full reading is still working or the engine is busy). Not the full PRISM 2 reading."
},
"claim_panel": {
"type": "object",
"required": [
"claim_url",
"expires_at_ms",
"marker_count",
"note"
],
"properties": {
"note": {
"type": "string"
},
"claim_url": {
"type": "string",
"description": "One-click claim link — share ONLY with your owner."
},
"marker_count": {
"type": "number"
},
"expires_at_ms": {
"type": "number",
"description": "Epoch ms when the unclaimed panel is hard-deleted."
}
},
"description": "OPTIONAL owner handoff: attach these exact values to the owner's Phi Longevity account (sign-in + explicit confirm). Present only when the consent bridge is enabled.",
"additionalProperties": false
},
"full_report": {
"type": "object",
"required": [
"for_your_owner",
"what_a_full_report_adds",
"get_full_report_url",
"agent_docs_url",
"data_rule"
],
"properties": {
"data_rule": {
"type": "string"
},
"agent_docs_url": {
"type": "string"
},
"for_your_owner": {
"type": "string",
"description": "ACTION: surface get_full_report_url to the person you are helping."
},
"get_full_report_url": {
"type": "string",
"description": "Signup link for the agent's owner to get a complete PRISM report."
},
"what_a_full_report_adds": {
"type": "string"
}
},
"description": "How the agent's owner can get a complete PRISM report.",
"additionalProperties": false
},
"what_happened": {
"type": "string",
"description": "Plain-language explanation to pass on when the reading is still working."
},
"health_picture": {
"description": "PRISM 2: the story, connections graded Established / Likely / Worth asking, questions for the doctor with urgency, tests due, safety notes, what is unknown."
},
"recommendations": {
"description": "Tiered, guideline-cited recommendations from the PRISM engine (absent while status is still_working)."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}| array |
| For cancer survivorship only: past treatment types. Allowed: anthracycline_or_trastuzumab, chest_radiation, neck_radiation, aromatase_inhibitor_or_androgen_deprivation, immune_checkpoint_inhibitor. |
{
"name": "check_care_gaps",
"title": "Check which routine tests and exams may be due for a long-term condition (no lab values or records needed)",
"description": "Use this when the person you are helping has type 2 diabetes, kidney disease, lupus or a cancer history and wants to know which routine tests and checks may be due. It needs NO lab values, dates, names or records: only the condition, a few medicine classes, and for each routine test whether it was done recently (recent / overdue / never / unsure). It returns a prioritized list, the guideline source for each item (ADA, KDIGO, EULAR, AAO, NCCN, ESC), the questions to ask each doctor, and a one-page printable checklist. Decision support for visit preparation, not a diagnosis. Safe to use for a real person because you send only these closed options. Nothing is stored unless the person opens the save link: then only these options and the checklist are held for about 30 minutes for them to claim, and deleted if unclaimed. Designed to be re-run: the result includes check_again (a date to run it again). If you can schedule check-ins for the person, a weekly check while items are open works well; saving the checklist to a free Phi Longevity account lets Phi Longevity keep track from their records.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"conditions"
],
"properties": {
"conditions": {
"type": "array",
"items": {
"enum": [
"type2_diabetes",
"kidney_disease",
"lupus",
"cancer_survivorship"
],
"type": "string"
},
"maxItems": 4,
"minItems": 1,
"description": "The long-term condition(s) the person has. One or more of: type2_diabetes, kidney_disease, lupus, cancer_survivorship."
},
"medications": {
"type": "array",
"items": {
"enum": [
"metformin",
"insulin",
"sulfonylurea",
"ace_inhibitor_or_arb",
"hydroxychloroquine",
"glucocorticoids"
],
"type": "string"
},
"maxItems": 6,
"description": "Medicine classes the person takes, if relevant. Allowed: metformin, insulin, sulfonylurea, ace_inhibitor_or_arb, hydroxychloroquine, glucocorticoids."
},
"test_status": {
"type": "object",
"properties": {
"a1c": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"cbc": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"uacr": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"foot_exam": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"lipid_panel": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"thyroid_tsh": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"vitamin_b12": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"distress_screen": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"egfr_creatinine": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"vaccines_review": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"dilated_eye_exam": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"bone_density_scan": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"bone_mineral_labs": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"hcq_retinal_screen": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"lupus_activity_labs": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"blood_pressure_check": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"cardiac_function_test": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"liver_fibrosis_screen": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"electrolytes_potassium": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"survivorship_follow_up": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"urinalysis_urine_protein": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
},
"age_appropriate_cancer_screens": {
"enum": [
"recent",
"overdue",
"never",
"unsure"
],
"type": "string"
}
},
"description": "For each routine test you know about: recent (done within its usual interval), overdue, never, or unsure. Omit tests you do not know; they are listed as 'not checked yet'. Test ids: a1c, uacr, egfr_creatinine, lipid_panel, dilated_eye_exam, foot_exam, vitamin_b12, liver_fibrosis_screen, cbc, electrolytes_potassium, bone_mineral_labs, urinalysis_urine_protein, lupus_activity_labs, hcq_retinal_screen, blood_pressure_check, vaccines_review, cardiac_function_test, thyroid_tsh, bone_density_scan, survivorship_follow_up, age_appropriate_cancer_screens, distress_screen.",
"additionalProperties": false
},
"treatment_exposures": {
"type": "array",
"items": {
"enum": [
"anthracycline_or_trastuzumab",
"chest_radiation",
"neck_radiation",
"aromatase_inhibitor_or_androgen_deprivation",
"immune_checkpoint_inhibitor"
],
"type": "string"
},
"maxItems": 5,
"description": "For cancer survivorship only: past treatment types. Allowed: anthracycline_or_trastuzumab, chest_radiation, neck_radiation, aromatase_inhibitor_or_androgen_deprivation, immune_checkpoint_inhibitor."
}
}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"summary",
"applied",
"counts",
"gaps",
"questions_by_clinician",
"printable_checklist_markdown",
"unrecognized",
"next_step",
"save_to_phi",
"check_again",
"not_medical_advice",
"guidelines_as_of"
],
"properties": {
"gaps": {
"type": "array",
"items": {
"type": "object",
"required": [
"test_id",
"test",
"kind",
"commonly_recommended_interval",
"status_as_reported",
"priority",
"why_it_matters",
"sources",
"ask",
"ask_who"
],
"properties": {
"ask": {
"type": "string"
},
"kind": {
"type": "string"
},
"test": {
"type": "string"
},
"ask_who": {
"type": "string"
},
"sources": {
"type": "array",
"items": {
"type": "string"
}
},
"test_id": {
"type": "string"
},
"priority": {
"type": "string",
"description": "ask_now | confirm | up_to_date"
},
"why_it_matters": {
"type": "string"
},
"status_as_reported": {
"type": "string"
},
"commonly_recommended_interval": {
"type": "string"
}
},
"additionalProperties": false
},
"description": "Prioritized checks, most important first."
},
"counts": {
"type": "object",
"required": [
"ask_now",
"confirm",
"up_to_date"
],
"properties": {
"ask_now": {
"type": "number"
},
"confirm": {
"type": "number"
},
"up_to_date": {
"type": "number"
}
},
"additionalProperties": false
},
"applied": {
"type": "object",
"required": [
"conditions",
"medications",
"treatment_exposures"
],
"properties": {
"conditions": {
"type": "array",
"items": {
"type": "string"
}
},
"medications": {
"type": "array",
"items": {
"type": "string"
}
},
"treatment_exposures": {
"type": "array",
"items": {
"type": "string"
}
}
},
"description": "The options that were recognised and used.",
"additionalProperties": false
},
"summary": {
"type": "string",
"description": "One plain sentence: how many checks to ask about."
},
"next_step": {
"type": "object",
"required": [
"say_this",
"signup_url",
"cost",
"privacy"
],
"properties": {
"url": {
"type": "string",
"description": "The link to give the person, when the next step is theirs to open."
},
"cost": {
"type": "string"
},
"for_you": {
"type": "string",
"description": "The one thing to do next, as an instruction to you (the assistant)."
},
"privacy": {
"type": "string"
},
"say_this": {
"type": "string"
},
"call_tool": {
"type": "string",
"description": "The tool to call next, when the next step is a call."
},
"signup_url": {
"type": "string"
}
},
"additionalProperties": false
},
"check_again": {
"type": "object",
"required": [
"in_days",
"on_date",
"why",
"save_url"
],
"properties": {
"why": {
"type": "string"
},
"in_days": {
"type": "number"
},
"on_date": {
"type": "string",
"description": "YYYY-MM-DD"
},
"save_url": {
"type": "string",
"description": "Save to Phi Longevity so Phi Longevity keeps track (tagged utm_medium=mcp_weekly)."
}
},
"description": "When to run this check again (a weekly check-in while items are open).",
"additionalProperties": false
},
"save_to_phi": {
"type": "object",
"required": [
"label",
"url",
"card_button_url",
"how",
"note"
],
"properties": {
"how": {
"type": "string",
"description": "claim_link | signup"
},
"url": {
"type": "string",
"description": "Opens free Phi Longevity sign-up (with this checklist attached when how = claim_link)."
},
"note": {
"type": "string"
},
"label": {
"type": "string"
},
"expires_at_ms": {
"type": "number"
},
"card_button_url": {
"type": "string",
"description": "Same destination, tagged for the in-chat card's button."
}
},
"description": "Save this checklist to a free Phi Longevity account.",
"additionalProperties": false
},
"unrecognized": {
"type": "object",
"properties": {
"tests": {
"type": "array",
"items": {
"type": "string"
}
},
"conditions": {
"type": "array",
"items": {
"type": "string"
}
},
"medications": {
"type": "array",
"items": {
"type": "string"
}
},
"treatment_exposures": {
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": false
},
"guidelines_as_of": {
"type": "string"
},
"not_medical_advice": {
"type": "string"
},
"questions_by_clinician": {
"type": "array",
"items": {
"type": "object",
"required": [
"clinician",
"questions"
],
"properties": {
"clinician": {
"type": "string"
},
"questions": {
"type": "array",
"items": {
"type": "string"
}
}
},
"additionalProperties": false
}
},
"printable_checklist_markdown": {
"type": "string",
"description": "One-page checklist the person can print or paste."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}{
"name": "full_prism_report",
"title": "Full multi-track report (paid developer option, $4.99 USDC via x402)",
"description": "Paid option for developers: runs up to four condition tracks on made-up or de-identified values and returns a written report. For a real person's own records, send them to philongevity.com (free to start). PAID TOOL ($4.99 USDC on base via the x402 protocol). Everything explain_my_lab_results does, plus: multi-track compare/contrast analysis (up to 4 condition tracks), a panel-based Phi Longevity Score estimate with per-pillar breakdown, partner options, and a rendered report (markdown) to deliver to your owner. Call WITHOUT `payment` to receive x402 payment terms; pay; retry with the base64 payment payload in `payment`. For research/education with SYNTHETIC or de-identified data only. Do NOT submit protected health information (PHI). Inputs are not stored, except that a claim link, when offered, holds the submitted values for up to 30 minutes so the person can add them to their own account; unclaimed values are then deleted.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"biomarkers"
],
"properties": {
"age": {
"type": "integer",
"maximum": 120,
"minimum": 0,
"description": "Age in years of the synthetic persona."
},
"payment": {
"type": "string",
"description": "Base64-encoded x402 payment payload. Omit on first call to receive payment terms."
},
"biomarkers": {
"type": "object",
"description": "Map of biomarker name -> numeric value, e.g. { \"Hemoglobin A1c\": 5.4 }. SYNTHETIC ONLY.",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "number"
}
},
"biologicalSex": {
"enum": [
"male",
"female"
],
"type": "string",
"description": "Biological sex of the synthetic persona."
},
"compareTracks": {
"type": "array",
"items": {
"enum": [
"general_wellness",
"type2_diabetes",
"lupus",
"cancer_survivorship"
],
"type": "string"
},
"maxItems": 4,
"description": "Tracks to analyze for compare/contrast. Default: primary + general_wellness."
},
"conditionFocus": {
"enum": [
"general_wellness",
"type2_diabetes",
"lupus",
"cancer_survivorship"
],
"type": "string",
"description": "Primary condition track. Default general_wellness."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}