NOMOS is an MCP server published by com.nomosprotocol, hosted at www.nomosprotocol.com. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 7 tools, including verify_decision, generate_governance, detect_contradictions, ask_authority, ask_by_context.
Ask a sealed authority whether an action may proceed. Answers are deterministic and citable.
775 connections through 4 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
Check whether an AI decision is allowed, denied, or needs escalation according to a sealed NOMOS governance artifact. Always returns `allowed` (boolean) — that field is safe to read regardless of which artifact type answered. The rest of the shape genuinely differs by artifact type, because it proxies two different underlying endpoints: pub_ demo artifacts return a flat shape (`outcome`: auto_approved/auto_rejected/escalated, `rule_applied`, `rule_reference`, flat `confidence` and `audit_hash`); your own sealed artifacts from Studio return a nested shape (`verdict`: approved/rejected/escalated, a nested `rule` object, and nested `confidence`/`audit`/`performance` objects). See outputSchema for both exact shapes — do not assume one without checking which kind of artifact_id was passed. Use artifact IDs starting with pub_ for public demo artifacts that require no API key: pub_lending_v1 (loan approval), pub_refund_v1 (refund policy), pub_fraud_v1 (fraud detection), pub_hr_leave_v1 (HR leave approval), pub_kyc_v1 (KYC/identity).
| Parameter | Type | Description |
|---|---|---|
| inputs * | object | Key/value input fields for rule evaluation (e.g. {"amount": 5000, "credit_score": 720}). Fields must match the artifact's declared data contract. |
| api_key |
None yet. Changes appear after a server's second daily check.
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.
| string |
| NOMOS API key (nmk_live_...). Not required for pub_ artifacts. |
| decision * | string | The action or decision being checked, as a verb phrase (e.g. "approve_loan", "process_refund", "approve_leave"). Should match an action defined in the artifact. |
| domain_id | number | Your NOMOS domain ID. Required for custom artifacts created in Studio. Not needed for pub_ artifacts. |
| artifact_id * | string | Sealed artifact ID to evaluate against. Use pub_lending_v1, pub_refund_v1, pub_fraud_v1, pub_hr_leave_v1, or pub_kyc_v1 for public demos. Use your own artifact ID from Studio for custom governance. |
{
"name": "verify_decision",
"description": "Check whether an AI decision is allowed, denied, or needs escalation according to a sealed NOMOS governance artifact. Always returns `allowed` (boolean) — that field is safe to read regardless of which artifact type answered. The rest of the shape genuinely differs by artifact type, because it proxies two different underlying endpoints: pub_ demo artifacts return a flat shape (`outcome`: auto_approved/auto_rejected/escalated, `rule_applied`, `rule_reference`, flat `confidence` and `audit_hash`); your own sealed artifacts from Studio return a nested shape (`verdict`: approved/rejected/escalated, a nested `rule` object, and nested `confidence`/`audit`/`performance` objects). See outputSchema for both exact shapes — do not assume one without checking which kind of artifact_id was passed. Use artifact IDs starting with pub_ for public demo artifacts that require no API key: pub_lending_v1 (loan approval), pub_refund_v1 (refund policy), pub_fraud_v1 (fraud detection), pub_hr_leave_v1 (HR leave approval), pub_kyc_v1 (KYC/identity).",
"inputSchema": {
"type": "object",
"required": [
"artifact_id",
"decision",
"inputs"
],
"properties": {
"inputs": {
"type": "object",
"description": "Key/value input fields for rule evaluation (e.g. {\"amount\": 5000, \"credit_score\": 720}). Fields must match the artifact's declared data contract."
},
"api_key": {
"type": "string",
"description": "NOMOS API key (nmk_live_...). Not required for pub_ artifacts."
},
"decision": {
"type": "string",
"description": "The action or decision being checked, as a verb phrase (e.g. \"approve_loan\", \"process_refund\", \"approve_leave\"). Should match an action defined in the artifact."
},
"domain_id": {
"type": "number",
"description": "Your NOMOS domain ID. Required for custom artifacts created in Studio. Not needed for pub_ artifacts."
},
"artifact_id": {
"type": "string",
"description": "Sealed artifact ID to evaluate against. Use pub_lending_v1, pub_refund_v1, pub_fraud_v1, pub_hr_leave_v1, or pub_kyc_v1 for public demos. Use your own artifact ID from Studio for custom governance."
}
}
},
"outputSchema": {
"type": "object",
"anyOf": [
{
"type": "object",
"properties": {
"allowed": {
"type": "boolean"
},
"outcome": {
"enum": [
"auto_approved",
"auto_rejected",
"escalated"
],
"type": "string"
},
"rule_id": {
"type": "string"
},
"audit_hash": {
"type": "string"
},
"confidence": {
"type": "number",
"description": "Flat 0–1 score for this shape"
},
"latency_ms": {
"type": "number"
},
"artifact_id": {
"type": "string"
},
"audit_record": {
"type": "string"
},
"rule_applied": {
"type": "string"
},
"artifact_name": {
"type": "string"
},
"rule_reference": {
"type": "string"
},
"rule_description": {
"type": [
"string",
"null"
]
},
"verdict_description": {
"type": "string"
}
},
"description": "Shape returned for pub_ demo artifacts (via /api/v1/verify)."
},
{
"type": "object",
"properties": {
"rule": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"action": {
"type": "string"
},
"description": {
"type": [
"string",
"null"
]
}
},
"description": "Present only when a rule matched."
},
"audit": {
"type": "object",
"properties": {
"hash": {
"type": "string"
},
"timestamp": {
"type": "string"
}
}
},
"allowed": {
"type": "boolean"
},
"verdict": {
"enum": [
"approved",
"rejected",
"escalated"
],
"type": "string"
},
"confidence": {
"type": "object",
"properties": {
"tier": {
"type": "string"
},
"score": {
"type": "number"
},
"description": {
"type": "string"
}
},
"description": "Nested for this shape, not a flat number."
},
"artifact_id": {
"type": "string"
},
"performance": {
"type": "object",
"properties": {
"latency_ms": {
"type": "number"
}
}
},
"artifact_name": {
"type": "string"
},
"verdict_description": {
"type": "string"
}
},
"description": "Shape returned for your own sealed artifacts from Studio (via /api/v1/verify-decision)."
}
]
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true
}
}Convert one or more policy documents into a sealed NOMOS governance artifact (.nomos). Extracts executable rules using Claude, detects contradictions between rules, computes an Autonomy Readiness Index (ARI) score (0–1), and cryptographically seals the result. Returns an artifact_id you can use with verify_decision immediately. Optionally accepts historical behavioral decision logs to add a behavioral evidence layer and reach CERTIFIED confidence tier.
| Parameter | Type | Description |
|---|---|---|
| name * | string | Human-readable name for the governance artifact (e.g. "Loan Approval Policy v2", "HR Leave Rules"). |
| domain | string | Industry or domain hint (e.g. "lending", "hr", "e-commerce", "healthcare", "insurance"). Improves extraction accuracy. |
| api_key | string | NOMOS API key (nmk_live_...). |
| documents * | array | Policy documents to extract rules from. Each item must have filename and content (plain text). |
| organization * | string | Name of the organization this artifact governs (e.g. "Acme Bank", "HealthCorp"). |
| behavioral_logs | array | Optional historical decision records (CSV rows as objects) for behavioral triangulation. Minimum 10 rows recommended. |
{
"name": "generate_governance",
"description": "Convert one or more policy documents into a sealed NOMOS governance artifact (.nomos). Extracts executable rules using Claude, detects contradictions between rules, computes an Autonomy Readiness Index (ARI) score (0–1), and cryptographically seals the result. Returns an artifact_id you can use with verify_decision immediately. Optionally accepts historical behavioral decision logs to add a behavioral evidence layer and reach CERTIFIED confidence tier.",
"inputSchema": {
"type": "object",
"required": [
"name",
"organization",
"documents"
],
"properties": {
"name": {
"type": "string",
"description": "Human-readable name for the governance artifact (e.g. \"Loan Approval Policy v2\", \"HR Leave Rules\")."
},
"domain": {
"type": "string",
"description": "Industry or domain hint (e.g. \"lending\", \"hr\", \"e-commerce\", \"healthcare\", \"insurance\"). Improves extraction accuracy."
},
"api_key": {
"type": "string",
"description": "NOMOS API key (nmk_live_...)."
},
"documents": {
"type": "array",
"items": {
"type": "object",
"required": [
"filename",
"content"
],
"properties": {
"content": {
"type": "string",
"description": "Plain text content of the document."
},
"filename": {
"type": "string",
"description": "Original filename including extension (e.g. \"credit-policy.pdf\"). Used for provenance tracking."
},
"source_type": {
"enum": [
"policy",
"email",
"spreadsheet",
"transcript"
],
"type": "string",
"description": "Document type hint for extraction heuristics. Defaults to \"policy\"."
}
}
},
"description": "Policy documents to extract rules from. Each item must have filename and content (plain text)."
},
"organization": {
"type": "string",
"description": "Name of the organization this artifact governs (e.g. \"Acme Bank\", \"HealthCorp\")."
},
"behavioral_logs": {
"type": "array",
"items": {
"type": "object",
"description": "One row of historical decision data as a key/value object."
},
"description": "Optional historical decision records (CSV rows as objects) for behavioral triangulation. Minimum 10 rows recommended."
}
}
},
"outputSchema": {
"type": "object",
"properties": {
"ari_score": {
"type": "number",
"description": "Autonomy Readiness Index 0–1 (≥0.60 autonomous, ≥0.30 bounded, <0.30 human-governed)"
},
"seal_hash": {
"type": "string",
"description": "SHA-256 cryptographic seal of the artifact"
},
"artifact_id": {
"type": "string",
"description": "Unique ID for the sealed artifact — use this with verify_decision"
},
"autonomy_band": {
"enum": [
"autonomous",
"bounded",
"human_governed"
],
"type": "string",
"description": "Recommended deployment mode"
},
"contradictions": {
"type": "number",
"description": "Number of contradictions detected"
},
"confidence_tier": {
"enum": [
"DECLARED",
"VALIDATED",
"CERTIFIED"
],
"type": "string",
"description": "Artifact confidence tier"
},
"rules_extracted": {
"type": "number",
"description": "Number of executable rules extracted"
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false
}
}Analyze policy documents (and optional behavioral decision logs) to detect contradictions, hidden rules, and gaps between declared policy and observed behavior. Stateless — no artifact is created and nothing is persisted. Returns contradictions of three types: rule_collision (two rules that apply to the same case with different decisions where the policy does not settle it soundly, each with that case and what the policy would do), ghost_term (an undefined standard such as "reasonable" in a rule's own text), and layer_divergence (a policy rule and a rule of practice that one case meets with different decisions); with behavioral logs, policy_gaps measured from the decisions.
| Parameter | Type | Description |
|---|---|---|
| api_key | string | NOMOS API key (nmk_live_...). |
| documents * | array | Policy documents to analyze for contradictions. |
| behavioral_logs | array | Optional historical decision records. Enables layer_divergence detection — surfaces behavioral patterns that deviate from written policy. |
{
"name": "detect_contradictions",
"description": "Analyze policy documents (and optional behavioral decision logs) to detect contradictions, hidden rules, and gaps between declared policy and observed behavior. Stateless — no artifact is created and nothing is persisted. Returns contradictions of three types: rule_collision (two rules that apply to the same case with different decisions where the policy does not settle it soundly, each with that case and what the policy would do), ghost_term (an undefined standard such as \"reasonable\" in a rule's own text), and layer_divergence (a policy rule and a rule of practice that one case meets with different decisions); with behavioral logs, policy_gaps measured from the decisions.",
"inputSchema": {
"type": "object",
"required": [
"documents"
],
"properties": {
"api_key": {
"type": "string",
"description": "NOMOS API key (nmk_live_...)."
},
"documents": {
"type": "array",
"items": {
"type": "object",
"required": [
"filename",
"content"
],
"properties": {
"content": {
"type": "string",
"description": "Plain text content of the document."
},
"filename": {
"type": "string",
"description": "Original filename (e.g. credit-policy.txt)."
},
"source_type": {
"enum": [
"policy",
"email",
"spreadsheet",
"transcript"
],
"type": "string",
"description": "Document type hint."
}
}
},
"description": "Policy documents to analyze for contradictions."
},
"behavioral_logs": {
"type": "array",
"items": {
"type": "object",
"description": "One row of historical decision data."
},
"description": "Optional historical decision records. Enables layer_divergence detection — surfaces behavioral patterns that deviate from written policy."
}
}
},
"outputSchema": {
"type": "object",
"properties": {
"summary": {
"type": "string",
"description": "Plain-language summary of findings"
},
"hidden_rules": {
"type": "array",
"items": {
"type": "string"
},
"description": "Rules inferred from behavior not in written policy"
},
"contradictions": {
"type": "array",
"items": {
"type": "object",
"properties": {
"type": {
"type": "string",
"description": "Contradiction type"
},
"rules": {
"type": "array",
"items": {
"type": "string"
},
"description": "Conflicting rule texts"
},
"severity": {
"enum": [
"high",
"medium",
"low"
],
"type": "string"
},
"description": {
"type": "string",
"description": "Human-readable description of the conflict"
}
}
},
"description": "List of detected contradictions"
},
"total_contradictions": {
"type": "number",
"description": "Total contradictions found"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true
}
}Query a published authority on the NOMOS Exchange marketplace — a different system from verify_decision's own sealed policies. Every public authority (e.g. eu-ai-act.nomos) is queryable with no key. Returns the authority's own verdict (AUTHORIZED/DENIED/ESCALATED), the exact rule and reason, and a permanent, cryptographically-bound transcript (query_id + url) — replayable evidence, not just a reply. Nothing is invented or paraphrased: the verdict is the authority's sealed rules evaluated against your inputs. The default response is a short, curated summary (verdict, matched rule, source citation when the artifact has one, transparency/completeness disclosures, transcript link) — not the full rule-by-rule evaluation trace. Set include_evaluation_trace: true to get that complete diagnostic record when you or the user actually need it.
| Parameter | Type | Description |
|---|---|---|
| action | string | Optional label for what this query represents, for the caller's own transcript record (e.g. "pre-deployment check"). Purely descriptive — does not affect the verdict. |
| inputs * | object | Key/value facts to evaluate against the authority's rules (e.g. {"untargeted_facial_image_scraping": true}). Fields must match the authority's vocabulary — see the atlas endpoint or the artifact's catalog page. |
| purpose | string | Set "test" for test or evaluation queries: they are answered and sealed, but kept out of the authority's public history and counts. Defaults to production. |
| acts_for | string | Optional organisation the agent acts for. Recorded as declared; when an Exchange key is used, the key's account is recorded instead. |
| agent_id | string | Optional stable name for the agent asking (e.g. "acme-credit-agent"). Recorded on the transcript and shown in the authority's public history as who relies on it. |
| authority * | string | The Exchange artifact's standard name — its short slug, optionally ".nomos"-suffixed (e.g. "eu-ai-act" or "eu-ai-act.nomos"), or its raw artifact ID. Browse the catalog at https://www.nomosprotocol.com/exchange. |
| exchange_api_key | string | Exchange API key (nxk_...). Optional for free/public queries. Required only for metered access to licensed (paid) authorities beyond their free allotment. |
| include_evaluation_trace | boolean | Set true to receive the full rule-by-rule evaluation trace (every rule checked, every missing field) instead of the default curated summary. Most callers never need this. |
{
"name": "ask_authority",
"description": "Query a published authority on the NOMOS Exchange marketplace — a different system from verify_decision's own sealed policies. Every public authority (e.g. eu-ai-act.nomos) is queryable with no key. Returns the authority's own verdict (AUTHORIZED/DENIED/ESCALATED), the exact rule and reason, and a permanent, cryptographically-bound transcript (query_id + url) — replayable evidence, not just a reply. Nothing is invented or paraphrased: the verdict is the authority's sealed rules evaluated against your inputs. The default response is a short, curated summary (verdict, matched rule, source citation when the artifact has one, transparency/completeness disclosures, transcript link) — not the full rule-by-rule evaluation trace. Set include_evaluation_trace: true to get that complete diagnostic record when you or the user actually need it.",
"inputSchema": {
"type": "object",
"required": [
"authority",
"inputs"
],
"properties": {
"action": {
"type": "string",
"description": "Optional label for what this query represents, for the caller's own transcript record (e.g. \"pre-deployment check\"). Purely descriptive — does not affect the verdict."
},
"inputs": {
"type": "object",
"description": "Key/value facts to evaluate against the authority's rules (e.g. {\"untargeted_facial_image_scraping\": true}). Fields must match the authority's vocabulary — see the atlas endpoint or the artifact's catalog page."
},
"purpose": {
"enum": [
"production",
"test"
],
"type": "string",
"description": "Set \"test\" for test or evaluation queries: they are answered and sealed, but kept out of the authority's public history and counts. Defaults to production."
},
"acts_for": {
"type": "string",
"description": "Optional organisation the agent acts for. Recorded as declared; when an Exchange key is used, the key's account is recorded instead."
},
"agent_id": {
"type": "string",
"description": "Optional stable name for the agent asking (e.g. \"acme-credit-agent\"). Recorded on the transcript and shown in the authority's public history as who relies on it."
},
"authority": {
"type": "string",
"description": "The Exchange artifact's standard name — its short slug, optionally \".nomos\"-suffixed (e.g. \"eu-ai-act\" or \"eu-ai-act.nomos\"), or its raw artifact ID. Browse the catalog at https://www.nomosprotocol.com/exchange."
},
"exchange_api_key": {
"type": "string",
"description": "Exchange API key (nxk_...). Optional for free/public queries. Required only for metered access to licensed (paid) authorities beyond their free allotment."
},
"include_evaluation_trace": {
"type": "boolean",
"description": "Set true to receive the full rule-by-rule evaluation trace (every rule checked, every missing field) instead of the default curated summary. Most callers never need this."
}
}
},
"outputSchema": {
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Path to the permanent, shareable transcript for this query"
},
"verdict": {
"enum": [
"AUTHORIZED",
"DENIED",
"ESCALATED"
],
"type": "string",
"description": "The authority's own verdict"
},
"query_id": {
"type": "string",
"description": "Permanent transcript ID — reopen any time at the returned url"
},
"expected_fields": {
"type": "array",
"items": {
"type": "string"
},
"description": "Present only when ESCALATED for lack of data — the fields this authority still needs"
},
"matched_rule_id": {
"type": [
"string",
"null"
],
"description": "ID of the rule that determined the verdict — null when AUTHORIZED with no matching rule"
},
"response_source": {
"type": "string",
"description": "Provenance label — this is a sealed NOMOS verdict, not Claude's own reasoning. Preserve or restate this distinction when relaying the answer."
},
"rules_evaluated": {
"type": "array",
"items": {
"type": "object"
},
"description": "Only present when include_evaluation_trace was true"
},
"source_reference": {
"type": [
"object",
"null"
],
"properties": {
"section": {
"type": "string"
},
"document": {
"type": "string"
}
},
"description": "Citation for the matched rule, when the source document's structure was captured at extraction time. Names where the rule TEXT was extracted from (e.g. \"Article 5\"), not a legal claim about what it covers. Null if unavailable."
},
"matched_rule_name": {
"type": [
"string",
"null"
],
"description": "Human-readable name/description of the matched rule — use this for display, not matched_rule_id"
},
"verdict_description": {
"type": "string",
"description": "Human-readable reason — the exact rule and its consequence"
},
"rules_evaluated_count": {
"type": "number",
"description": "Total rules checked during evaluation — the size of the full trace, whether or not it was returned"
},
"open_higher_priority_count": {
"type": "number",
"description": "0 means every relevant fact was known when this was sealed; >0 means facts were still missing above the matched rule"
},
"open_higher_priority_rules": {
"type": "array",
"items": {
"type": "object",
"properties": {
"rule_id": {
"type": "string"
},
"consequence": {
"enum": [
"blocks",
"requires_review",
"permits"
],
"type": "string"
},
"description": {
"type": "string"
},
"missing_fields": {
"type": "array",
"items": {
"type": "string"
}
}
}
},
"description": "The actual rules behind open_higher_priority_count (capped to 20) — use this to answer \"which ones?\" instead of guessing. Each has the rule name, what it would do if it matched, and exactly which input fields are missing."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false
}
}Ask whether an action is allowed WITHOUT choosing the law yourself (NOMOS-SPEC-014). Describe where the act happens and who it involves; NOMOS works out from its signed registrar log which laws govern it, asks every one, and combines strictly: any deny denies, a yes needs every law. Prefer this over ask_authority whenever you do not already know which law applies: naming one law leaves out the others. Each law's own answer is a permanent, signed transcript (members[].query_id). If a fact that decides which law applies is missing, the answer is INSUFFICIENT_DATA with open_facts naming it: ask the user, never guess. A place the registrar does not cover is answered INSUFFICIENT_DATA, never as permission; say so plainly. Relay `coverage`: the registrar lists only its own laws, so other law may also apply.
| Parameter | Type | Description |
|---|---|---|
| action | string | Optional label for what is being done (e.g. "share_customer_data_with_analytics_vendor"), recorded on each transcript. |
| inputs | object | Facts about the action itself, evaluated by every law that applies (e.g. {"processing_fair_and_transparent": true}). A law that needs a fact you did not give holds the answer open and names it. |
| context * | object | The facts that decide which law applies. Codes: EU (an EU member state), QA (Qatar), AE (the UAE outside free zones with their own data law), DIFC, ADGM, QFC, US, SA, and so on. |
| purpose | string | Set "test" for test or evaluation queries: answered and sealed, but kept out of public history and counts. |
| acts_for | string | Optional organisation the agent acts for. |
| agent_id | string | Optional stable name for the agent asking, recorded on each transcript. |
| exchange_api_key | string | Exchange API key (nxk_...). Optional; needed only for licensed (paid) authorities. |
{
"name": "ask_by_context",
"description": "Ask whether an action is allowed WITHOUT choosing the law yourself (NOMOS-SPEC-014). Describe where the act happens and who it involves; NOMOS works out from its signed registrar log which laws govern it, asks every one, and combines strictly: any deny denies, a yes needs every law. Prefer this over ask_authority whenever you do not already know which law applies: naming one law leaves out the others. Each law's own answer is a permanent, signed transcript (members[].query_id). If a fact that decides which law applies is missing, the answer is INSUFFICIENT_DATA with open_facts naming it: ask the user, never guess. A place the registrar does not cover is answered INSUFFICIENT_DATA, never as permission; say so plainly. Relay `coverage`: the registrar lists only its own laws, so other law may also apply.",
"inputSchema": {
"type": "object",
"required": [
"context"
],
"properties": {
"action": {
"type": "string",
"description": "Optional label for what is being done (e.g. \"share_customer_data_with_analytics_vendor\"), recorded on each transcript."
},
"inputs": {
"type": "object",
"description": "Facts about the action itself, evaluated by every law that applies (e.g. {\"processing_fair_and_transparent\": true}). A law that needs a fact you did not give holds the answer open and names it."
},
"context": {
"type": "object",
"properties": {
"subjects_in": {
"type": "string",
"description": "Where the people the act concerns are located or resident"
},
"jurisdiction": {
"type": "string",
"description": "Where the act takes effect"
},
"established_in": {
"type": "string",
"description": "Where the acting organisation is incorporated or established"
},
"output_used_in": {
"type": "string",
"description": "Where any AI system output is used (the same as jurisdiction if no AI is involved)"
}
},
"description": "The facts that decide which law applies. Codes: EU (an EU member state), QA (Qatar), AE (the UAE outside free zones with their own data law), DIFC, ADGM, QFC, US, SA, and so on."
},
"purpose": {
"enum": [
"production",
"test"
],
"type": "string",
"description": "Set \"test\" for test or evaluation queries: answered and sealed, but kept out of public history and counts."
},
"acts_for": {
"type": "string",
"description": "Optional organisation the agent acts for."
},
"agent_id": {
"type": "string",
"description": "Optional stable name for the agent asking, recorded on each transcript."
},
"exchange_api_key": {
"type": "string",
"description": "Exchange API key (nxk_...). Optional; needed only for licensed (paid) authorities."
}
}
},
"outputSchema": {
"type": "object",
"properties": {
"mode": {
"type": "string",
"description": "\"resolution\": the laws were worked out from the context, not chosen by the caller"
},
"reason": {
"type": "string",
"description": "Why, in words"
},
"members": {
"type": "array",
"items": {
"type": "object"
},
"description": "Each law's own answer, with its permanent transcript (query_id)"
},
"verdict": {
"enum": [
"AUTHORIZED",
"DENIED",
"ESCALATED",
"INSUFFICIENT_DATA",
"CONFLICT"
],
"type": "string",
"description": "The strict combination of every applicable law's verdict"
},
"coverage": {
"type": "string",
"description": "What the answer covers; relay it to the user"
},
"authorized": {
"type": "boolean",
"description": "True only when every applicable law authorizes; never true over an empty set of laws"
},
"open_facts": {
"type": "array",
"items": {
"type": "string"
},
"description": "Facts to supply when the answer is held open"
},
"resolution": {
"type": "object",
"description": "How the laws were resolved (status, applicable, missing, proof with the log head consulted)"
},
"escalations": {
"type": "array",
"items": {
"type": "object"
},
"description": "Each law that requires approval, with its escalation"
},
"answered_under": {
"type": "array",
"items": {
"type": "string"
},
"description": "The laws the answer was computed under"
},
"deciding_authorities": {
"type": "array",
"items": {
"type": "string"
},
"description": "The laws that decided the verdict"
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false
}
}Find which published authorities on the NOMOS Exchange govern something you are about to do, from a plain description (e.g. "deploy a recruitment model in the EU"). No name needed. Returns the matching authorities ranked, and for each the facts it reads that match your description (what to pass to ask_authority as inputs) and its most relevant rules with where they come from in the source. Also returns authorities others have requested that are not listed yet. Matches by words and by meaning (a small multilingual model on the server, so questions in Arabic and other languages work); it only chooses what to ask, never a verdict. Call this before ask_authority when you do not know the authority's name.
| Parameter | Type | Description |
|---|---|---|
| limit | number | Maximum authorities to return (default 10). |
| description * | string | What you are about to do, in plain words. |
| jurisdiction | string | Optional jurisdiction tag to restrict to, e.g. "EU" or "AE". |
{
"name": "find_authority",
"description": "Find which published authorities on the NOMOS Exchange govern something you are about to do, from a plain description (e.g. \"deploy a recruitment model in the EU\"). No name needed. Returns the matching authorities ranked, and for each the facts it reads that match your description (what to pass to ask_authority as inputs) and its most relevant rules with where they come from in the source. Also returns authorities others have requested that are not listed yet. Matches by words and by meaning (a small multilingual model on the server, so questions in Arabic and other languages work); it only chooses what to ask, never a verdict. Call this before ask_authority when you do not know the authority's name.",
"inputSchema": {
"type": "object",
"required": [
"description"
],
"properties": {
"limit": {
"type": "number",
"description": "Maximum authorities to return (default 10)."
},
"description": {
"type": "string",
"description": "What you are about to do, in plain words."
},
"jurisdiction": {
"type": "string",
"description": "Optional jurisdiction tag to restrict to, e.g. \"EU\" or \"AE\"."
}
}
},
"outputSchema": {
"type": "object",
"properties": {
"next": {
"type": "string"
},
"places": {
"type": "array",
"items": {
"type": "string"
},
"description": "Jurisdictions the description names (e.g. AE for Dubai). An authority that covers none of them is not returned."
},
"search": {
"type": "object",
"description": "How the search ran: method \"hybrid\" (meaning and words) or \"keyword\", and the model used for meaning."
},
"matches": {
"type": "array",
"items": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "Pass this as `authority` to ask_authority."
},
"facts": {
"type": "array",
"items": {
"type": "string"
},
"description": "Input fields this authority reads that match the description."
},
"rules": {
"type": "array",
"items": {
"type": "object"
}
},
"score": {
"type": "number"
},
"title": {
"type": "string"
},
"matched_by": {
"enum": [
"words",
"meaning",
"both"
],
"type": "string"
},
"matched_terms": {
"type": "array",
"items": {
"type": "string"
},
"description": "Words of the description that matched. Empty when it matched by meaning alone (e.g. a question in Arabic)."
}
}
}
},
"requested": {
"type": "array",
"items": {
"type": "object"
},
"description": "Requested, not yet listed."
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true
}
}Ask for an authority (a law, regulation, standard or policy) to be added to the NOMOS Exchange when find_authority finds nothing. Requests are public and ranked by how many asked; they decide what is compiled next. Repeated requests from one caller count once. This never creates an authority: only its issuer, or NOMOS compiling the public text, can.
| Parameter | Type | Description |
|---|---|---|
| title * | string | The authority by its usual name, e.g. "UAE Personal Data Protection Law (Federal Decree-Law 45/2021)". |
| source_url | string | Optional link to the official text. |
| jurisdiction | string | Optional jurisdiction, e.g. "AE". |
{
"name": "request_authority",
"description": "Ask for an authority (a law, regulation, standard or policy) to be added to the NOMOS Exchange when find_authority finds nothing. Requests are public and ranked by how many asked; they decide what is compiled next. Repeated requests from one caller count once. This never creates an authority: only its issuer, or NOMOS compiling the public text, can.",
"inputSchema": {
"type": "object",
"required": [
"title"
],
"properties": {
"title": {
"type": "string",
"description": "The authority by its usual name, e.g. \"UAE Personal Data Protection Law (Federal Decree-Law 45/2021)\"."
},
"source_url": {
"type": "string",
"description": "Optional link to the official text."
},
"jurisdiction": {
"type": "string",
"description": "Optional jurisdiction, e.g. \"AE\"."
}
}
},
"outputSchema": {
"type": "object",
"properties": {
"id": {
"type": "number"
},
"note": {
"type": "string"
},
"title": {
"type": "string"
},
"status": {
"type": "string"
},
"counted": {
"type": "boolean"
},
"requests": {
"type": "number"
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true
}
}Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.