Agent Help Network is an MCP server published by com.agenthelpnetwork, hosted at agenthelpnetwork.com. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 5 tools, including check_incident, rate_last_lookup, report_observation, find_task_route, report_task_route.
Web step blocked? Host's declared agent policy, official path and status, plus one next action.
589 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
Call this when a web step is blocked or failing for no clear reason (a 403 or access denied, a 429, a 5xx or a timeout, a login wall, a "verify you are human" or CAPTCHA page), when sign-in failed or an extra verification step appeared (a code, app approval, new-device check; error_class=login_auth), or when asked "is this site down?" or whether its robots rules block agents. Skip it when the page opened normally or your own tool or platform already said why it refused (e.g. robots.txt or platform policy). Look the host up once per blocked step, before deciding whether to retry. Send the public hostname, never a URL path, query or credentials; add codes only when you observed them: error_class (site_access, login_auth, human_verification, service_error), failure_stage (before_target_response, response_observed, access_denial_observed, unknown), http_status, challenge, retry_after, via. Send agent_vendor only when you know which vendor's documented robots.txt token your requests send: openai, anthropic (Claude-User), google, perplexity, meta, mistral, amazon, microsoft, apple, duckduckgo, diffbot, exa, or other if none. Browser automation usually sends a normal browser user agent, so robots.txt agent tokens may not apply; leave agent_vendor out then. The answer: summary_line, next_action (do, url, retry_after_seconds), recommendation.action, access_profile, official_paths, provider_status and observations. no_reports is not a healthy site. Then follow next_action (continue, wait, use a listed official path, hand the step to the user, stop retrying, or look up once more). On 'pending', look up once more after retry_after_seconds; do not poll. Read-only: it may fetch the host's public robots.txt, llms.txt and status feed, and the home page unless robots.txt bars it (ahn_check), never changes the target site or your data; lookups and the codes you send are counted anonymously per host and hour. The first text block is a one-line summary; next_action gives the step to take, and recommendation stays the verdict.
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.
| Parameter | Type | Description |
|---|---|---|
| via | string | What made the failed request: http_fetch (a plain HTTP fetch), browser (browser automation) or unknown. Leave it out if unsure. |
| test | boolean | Set true to mark this lookup as a test (like the header X-AHN-Test: 1): it is kept out of the anonymous counts and the answer is the same. Leave it out for a real lookup; any other value is ignored. |
| challenge | string | header if the site's response carried a bot-challenge header, none if you saw the response and it did not. Never guess from the page body; leave it out if unknown. |
| failed_at | string | When the step failed, as an ISO 8601 time such as 2026-11-01T07:10:00Z (UTC if no offset). Leave it out for a failure that just happened. Only used to choose the cause shown in the answer; not stored. |
| site_host * | string | The public hostname that is blocked or failing, lowercase, for example example.com. Only the host: no scheme, URL path, query, port or credentials. |
| task_step | string | What you were doing, as a short lowercase code of letters, digits and underscores starting with a letter. Use status_check when you only check whether the site is up (not blocked). Leave it out otherwise. |
| error_class | string | What stopped you, only if you observed it: site_access (page or API refused or unreachable), login_auth (sign-in failed or an extra verification step appeared), human_verification (CAPTCHA or verify-you-are-human check), service_error (error response or timeout). Leave it out if unsure. |
| http_status | integer | HTTP status the site returned: 401, 402, 403, 407, 408, 429, 451 or 500-599. Leave out if unknown. |
| retry_after | string | Size of the Retry-After value the site sent, in seconds: none (no header, or an HTTP-date), lt_60 (under 60), 60_3600 (60 to 3600), gt_3600 (over 3600). Leave it out if you saw no response. |
| agent_vendor | string | The vendor whose documented robots.txt token your requests send (not the model vendor): openai, anthropic (Claude-User), google, perplexity, meta, mistral, amazon, microsoft, apple, duckduckgo, diffbot, exa, or other if none of them. Leave it out if you do not know, and for browser automation that s… |
| failure_stage | string | How far the request got, only if you observed it: before_target_response (no answer from the site, for example a timeout or connection failure), response_observed (the site answered with an error or unexpected page), access_denial_observed (the site explicitly refused access), unknown. Leave it out … |
{
"name": "check_incident",
"description": "Call this when a web step is blocked or failing for no clear reason (a 403 or access denied, a 429, a 5xx or a timeout, a login wall, a \"verify you are human\" or CAPTCHA page), when sign-in failed or an extra verification step appeared (a code, app approval, new-device check; error_class=login_auth), or when asked \"is this site down?\" or whether its robots rules block agents. Skip it when the page opened normally or your own tool or platform already said why it refused (e.g. robots.txt or platform policy). Look the host up once per blocked step, before deciding whether to retry. Send the public hostname, never a URL path, query or credentials; add codes only when you observed them: error_class (site_access, login_auth, human_verification, service_error), failure_stage (before_target_response, response_observed, access_denial_observed, unknown), http_status, challenge, retry_after, via. Send agent_vendor only when you know which vendor's documented robots.txt token your requests send: openai, anthropic (Claude-User), google, perplexity, meta, mistral, amazon, microsoft, apple, duckduckgo, diffbot, exa, or other if none. Browser automation usually sends a normal browser user agent, so robots.txt agent tokens may not apply; leave agent_vendor out then. The answer: summary_line, next_action (do, url, retry_after_seconds), recommendation.action, access_profile, official_paths, provider_status and observations. no_reports is not a healthy site. Then follow next_action (continue, wait, use a listed official path, hand the step to the user, stop retrying, or look up once more). On 'pending', look up once more after retry_after_seconds; do not poll. Read-only: it may fetch the host's public robots.txt, llms.txt and status feed, and the home page unless robots.txt bars it (ahn_check), never changes the target site or your data; lookups and the codes you send are counted anonymously per host and hour. The first text block is a one-line summary; next_action gives the step to take, and recommendation stays the verdict.",
"inputSchema": {
"type": "object",
"title": "check_incidentArguments",
"required": [
"site_host"
],
"properties": {
"via": {
"enum": [
"http_fetch",
"browser",
"unknown"
],
"type": "string",
"title": "Via",
"default": null,
"description": "What made the failed request: http_fetch (a plain HTTP fetch), browser (browser automation) or unknown. Leave it out if unsure."
},
"test": {
"type": "boolean",
"title": "Test",
"default": null,
"description": "Set true to mark this lookup as a test (like the header X-AHN-Test: 1): it is kept out of the anonymous counts and the answer is the same. Leave it out for a real lookup; any other value is ignored."
},
"challenge": {
"enum": [
"header",
"none"
],
"type": "string",
"title": "Challenge",
"default": null,
"description": "header if the site's response carried a bot-challenge header, none if you saw the response and it did not. Never guess from the page body; leave it out if unknown."
},
"failed_at": {
"type": "string",
"title": "Failed At",
"default": null,
"maxLength": 40,
"description": "When the step failed, as an ISO 8601 time such as 2026-11-01T07:10:00Z (UTC if no offset). Leave it out for a failure that just happened. Only used to choose the cause shown in the answer; not stored."
},
"site_host": {
"type": "string",
"title": "Site Host",
"description": "The public hostname that is blocked or failing, lowercase, for example example.com. Only the host: no scheme, URL path, query, port or credentials."
},
"task_step": {
"type": "string",
"title": "Task Step",
"default": "",
"description": "What you were doing, as a short lowercase code of letters, digits and underscores starting with a letter. Use status_check when you only check whether the site is up (not blocked). Leave it out otherwise."
},
"error_class": {
"type": "string",
"title": "Error Class",
"default": "",
"description": "What stopped you, only if you observed it: site_access (page or API refused or unreachable), login_auth (sign-in failed or an extra verification step appeared), human_verification (CAPTCHA or verify-you-are-human check), service_error (error response or timeout). Leave it out if unsure."
},
"http_status": {
"type": "integer",
"title": "Http Status",
"default": null,
"description": "HTTP status the site returned: 401, 402, 403, 407, 408, 429, 451 or 500-599. Leave out if unknown."
},
"retry_after": {
"enum": [
"none",
"lt_60",
"60_3600",
"gt_3600"
],
"type": "string",
"title": "Retry After",
"default": null,
"description": "Size of the Retry-After value the site sent, in seconds: none (no header, or an HTTP-date), lt_60 (under 60), 60_3600 (60 to 3600), gt_3600 (over 3600). Leave it out if you saw no response."
},
"agent_vendor": {
"enum": [
"openai",
"anthropic",
"google",
"perplexity",
"meta",
"mistral",
"amazon",
"microsoft",
"apple",
"duckduckgo",
"diffbot",
"exa",
"other"
],
"type": "string",
"title": "Agent Vendor",
"default": null,
"description": "The vendor whose documented robots.txt token your requests send (not the model vendor): openai, anthropic (Claude-User), google, perplexity, meta, mistral, amazon, microsoft, apple, duckduckgo, diffbot, exa, or other if none of them. Leave it out if you do not know, and for browser automation that sends a normal browser user agent."
},
"failure_stage": {
"type": "string",
"title": "Failure Stage",
"default": "",
"description": "How far the request got, only if you observed it: before_target_response (no answer from the site, for example a timeout or connection failure), response_observed (the site answered with an error or unexpected page), access_denial_observed (the site explicitly refused access), unknown. Leave it out if unsure."
}
}
},
"outputSchema": {
"truncated": true,
"chars": 40394
},
"annotations": {
"title": "Check host access profile",
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}If an earlier check_incident answer gave you a feedback token and you then tried again, say whether it worked. Sends only the token and the outcome code, no hostname. outcome: succeeded (the next attempt worked), still_blocked, handed_off (you handed the step to the user) or gave_up. path: official_path (you used the official path the answer pointed to), same_site (you retried the same site) or unknown. A token works once and expires one hour after the lookup; do not send one for an attempt you did not make. The outcome is counted anonymously per host and hour and does not change any answer.
| Parameter | Type | Description |
|---|---|---|
| path | string | Which way that attempt went: official_path (you used the official path the answer pointed to), same_site (you retried the same site) or unknown (the default). |
| token * | string | The feedback_token.token value from the check_incident answer, unchanged. |
| outcome * | string | What happened on your next attempt: succeeded (it worked), still_blocked, handed_off (you handed the step to the user) or gave_up. |
{
"name": "rate_last_lookup",
"description": "If an earlier check_incident answer gave you a feedback token and you then tried again, say whether it worked. Sends only the token and the outcome code, no hostname. outcome: succeeded (the next attempt worked), still_blocked, handed_off (you handed the step to the user) or gave_up. path: official_path (you used the official path the answer pointed to), same_site (you retried the same site) or unknown. A token works once and expires one hour after the lookup; do not send one for an attempt you did not make. The outcome is counted anonymously per host and hour and does not change any answer.",
"inputSchema": {
"type": "object",
"title": "rate_last_lookupArguments",
"required": [
"token",
"outcome"
],
"properties": {
"path": {
"enum": [
"official_path",
"same_site",
"unknown"
],
"type": "string",
"title": "Path",
"default": "unknown",
"description": "Which way that attempt went: official_path (you used the official path the answer pointed to), same_site (you retried the same site) or unknown (the default)."
},
"token": {
"type": "string",
"title": "Token",
"pattern": "^[A-Za-z0-9_-]{16,480}\\.[A-Za-z0-9_-]{43}$",
"maxLength": 530,
"description": "The feedback_token.token value from the check_incident answer, unchanged."
},
"outcome": {
"enum": [
"succeeded",
"still_blocked",
"handed_off",
"gave_up"
],
"type": "string",
"title": "Outcome",
"description": "What happened on your next attempt: succeeded (it worked), still_blocked, handed_off (you handed the step to the user) or gave_up."
}
}
},
"outputSchema": {
"type": "object",
"title": "FeedbackReceipt",
"required": [
"accepted"
],
"properties": {
"accepted": {
"type": "boolean",
"const": true,
"title": "Accepted"
}
},
"additionalProperties": true
},
"annotations": {
"title": "Rate the last lookup",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Submit one de-identified firsthand observation under your own operating authority and platform rules. Public reports enter private review and are not site-status claims. Never include names, account details, URLs, cookies, tokens, or conversation text. Add cause with cause_basis only when you established the cause from one of the four listed bases, never as a guess; otherwise leave both out.
| Parameter | Type | Description |
|---|---|---|
| observation * | ref | The observation to submit: site_host, error_class and outcome are required; the other fields are optional and described one by one. Only coded values and the public hostname; no names, account details, URLs, cookies, tokens or conversation text. |
{
"name": "report_observation",
"description": "Submit one de-identified firsthand observation under your own operating authority and platform rules. Public reports enter private review and are not site-status claims. Never include names, account details, URLs, cookies, tokens, or conversation text. Add cause with cause_basis only when you established the cause from one of the four listed bases, never as a guess; otherwise leave both out.",
"inputSchema": {
"type": "object",
"$defs": {
"Outcome": {
"enum": [
"passed",
"blocked",
"error",
"abandoned"
],
"type": "string",
"title": "Outcome"
},
"AttemptEnv": {
"enum": [
"agent_cloud_browser",
"human_in_agent_browser",
"human_own_browser",
"unknown"
],
"type": "string",
"title": "AttemptEnv"
},
"CauseBasis": {
"enum": [
"own_platform_message",
"site_message",
"person_confirmed",
"compared_with_own_browser"
],
"type": "string",
"title": "CauseBasis",
"description": "D109: what the reporting agent established the cause from."
},
"ErrorClass": {
"enum": [
"site_access",
"login_auth",
"human_verification",
"service_error"
],
"type": "string",
"title": "ErrorClass"
},
"AgentFamily": {
"enum": [
"dots",
"muse",
"other"
],
"type": "string",
"title": "AgentFamily"
},
"AttemptActor": {
"enum": [
"agent",
"human"
],
"type": "string",
"title": "AttemptActor"
},
"ChallengeKind": {
"enum": [
"interactive_check",
"loop",
"block_page",
"unknown",
"none"
],
"type": "string",
"title": "ChallengeKind"
},
"ObservationIn": {
"type": "object",
"title": "ObservationIn",
"required": [
"outcome",
"site_host",
"error_class"
],
"properties": {
"cause": {
"anyOf": [
{
"$ref": "#/$defs/ObservationCause"
},
{
"type": "null"
}
],
"default": null,
"description": "Optional, with cause_basis, for outcome blocked or error: the cause you established. Leave out if not established."
},
"outcome": {
"$ref": "#/$defs/Outcome",
"description": "How the attempt ended: passed (it worked), blocked (the site or a check stopped it), error (it failed with an error), or abandoned (you or the person stopped before the end)."
},
"site_host": {
"type": "string",
"title": "Site Host",
"description": "The public hostname the attempt was about, for example example.com. Only the host: no scheme, path, query, port or credentials."
},
"synthetic": {
"type": "boolean",
"title": "Synthetic",
"default": false,
"description": "true only for a made-up test report. Leave it out (false) for a real attempt."
},
"task_step": {
"type": "string",
"title": "Task Step",
"default": "other",
"description": "What you were trying to do, as a short lowercase code of letters, digits and underscores that starts with a letter, for example login, checkout or status_check. Default other."
},
"attempt_env": {
"$ref": "#/$defs/AttemptEnv",
"default": "unknown",
"description": "Where the attempt ran: agent_cloud_browser (a browser run by an agent in the cloud; needs attempt_actor agent), human_in_agent_browser or human_own_browser (a person at a browser; needs attempt_actor human), or unknown (the default)."
},
"cause_basis": {
"anyOf": [
{
"$ref": "#/$defs/CauseBasis"
},
{
"type": "null"
}
],
"default": null,
"description": "Required with cause: what you established it from."
},
"error_class": {
"$ref": "#/$defs/ErrorClass",
"description": "What kind of stop it was: site_access (page or API refused or unreachable), login_auth (sign-in failed or an extra verification step appeared), human_verification (a CAPTCHA or a verify-you-are-human check), or service_error (the site returned an error or timed out)."
},
"observed_at": {
"type": "string",
"title": "Observed At",
"format": "date-time",
"description": "When the attempt happened, as an ISO 8601 time with a timezone offset, for example 2026-11-01T07:10:00Z. Leave it out for an attempt that just happened. Must be within the last 7 days and not in the future."
},
"agent_family": {
"$ref": "#/$defs/AgentFamily",
"default": "other",
"description": "Which agent family you are: dots, muse, or other (the default; use it if neither fits)."
},
"attempt_actor": {
"$ref": "#/$defs/AttemptActor",
"default": "agent",
"description": "Who made the attempt: agent (you, the default) or human (the person did it themselves)."
},
"challenge_kind": {
"$ref": "#/$defs/ChallengeKind",
"default": "none",
"description": "What the challenge looked like: interactive_check (a box or puzzle to complete), loop (the check kept repeating), block_page (a page that only says access is denied), unknown, or none (the default; no challenge)."
},
"schema_version": {
"type": "integer",
"title": "Schema Version",
"default": 1,
"description": "Report format version. Always 1; leave it out."
},
"idempotency_key": {
"type": "string",
"title": "Idempotency Key",
"format": "uuid",
"description": "A UUID that makes a resend safe: sending the same key with the same body again does not create a second record. Leave it out to get a new one."
},
"challenge_vendor": {
"$ref": "#/$defs/ChallengeVendor",
"default": "none",
"description": "Which bot-check provider showed a challenge: cloudflare, recaptcha, hcaptcha, unknown (a challenge from another or unclear provider), or none (the default; no challenge)."
},
"consent_confirmed": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"title": "Consent Confirmed",
"default": null,
"description": "Legacy field kept for older clients. It is not used to decide anything; leave it out."
}
},
"additionalProperties": false
},
"ChallengeVendor": {
"enum": [
"cloudflare",
"recaptcha",
"hcaptcha",
"unknown",
"none"
],
"type": "string",
"title": "ChallengeVendor"
},
"ObservationCause": {
"enum": [
"site_said_no_agents",
"site_bot_check",
"site_unavailable",
"platform_refused",
"platform_needs_person",
"verification_on_person_device",
"verification_not_received",
"signed_out",
"agent_browser_differs"
],
"type": "string",
"title": "ObservationCause",
"description": "D109: the cause the reporting agent says it established, by the layer it points at. There is no \"unknown\" value: a\nreport that did not establish a cause leaves the field out."
}
},
"title": "report_observationArguments",
"required": [
"observation"
],
"properties": {
"observation": {
"$ref": "#/$defs/ObservationIn",
"description": "The observation to submit: site_host, error_class and outcome are required; the other fields are optional and described one by one. Only coded values and the public hostname; no names, account details, URLs, cookies, tokens or conversation text."
}
}
},
"outputSchema": {
"type": "object",
"title": "Receipt",
"required": [
"observation_id",
"incident_id",
"review_state",
"synthetic"
],
"properties": {
"synthetic": {
"type": "boolean",
"title": "Synthetic"
},
"incident_id": {
"type": "string",
"title": "Incident Id",
"format": "uuid"
},
"review_state": {
"type": "string",
"title": "Review State"
},
"observation_id": {
"type": "string",
"title": "Observation Id",
"format": "uuid"
},
"withdrawal_token": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Withdrawal Token",
"default": null
}
},
"additionalProperties": true
},
"annotations": {
"title": "Report an authorized observation",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}Call this once per task when you start a customer task on a site (a return or exchange, a refund, a cancellation, a warranty claim, an account recovery, a document submission), before you open its help pages, even when nothing is blocked. Look up recorded task routes for a public hostname: for a kind of customer task (a refund, a cancellation, a booking and so on), an obstacle and the routes the site's own documents name. A record may carry condition_text, a condition the site's page states, quoted as written: it is not our judgement, so decide yourself whether it applies to your task, with the page at source_url. The answer is a list of records, not a guarantee and not advice; an empty list does not mean there is no route. Sends only the hostname and an optional task kind, and changes nothing. Read summary_line first. field_notes explains outcome, period and routes_tried.
| Parameter | Type | Description |
|---|---|---|
| site_host * | string | The public hostname of the site whose task routes you want, lowercase, for example example.com. Only the host: no scheme, URL path, query, port or credentials. |
| task_kind | string | Optional: one kind of customer task to look up, from the list. Leave it out to get the records for every task kind of the site. |
{
"name": "find_task_route",
"description": "Call this once per task when you start a customer task on a site (a return or exchange, a refund, a cancellation, a warranty claim, an account recovery, a document submission), before you open its help pages, even when nothing is blocked. Look up recorded task routes for a public hostname: for a kind of customer task (a refund, a cancellation, a booking and so on), an obstacle and the routes the site's own documents name. A record may carry condition_text, a condition the site's page states, quoted as written: it is not our judgement, so decide yourself whether it applies to your task, with the page at source_url. The answer is a list of records, not a guarantee and not advice; an empty list does not mean there is no route. Sends only the hostname and an optional task kind, and changes nothing. Read summary_line first. field_notes explains outcome, period and routes_tried.",
"inputSchema": {
"type": "object",
"title": "find_task_routeArguments",
"required": [
"site_host"
],
"properties": {
"site_host": {
"type": "string",
"title": "Site Host",
"description": "The public hostname of the site whose task routes you want, lowercase, for example example.com. Only the host: no scheme, URL path, query, port or credentials."
},
"task_kind": {
"enum": [
"claim_unclaimed_property",
"warranty_claim",
"warranty_dispute",
"refund_request",
"return_or_exchange",
"cancel_subscription",
"account_closure",
"account_recovery",
"portal_login",
"address_or_profile_change",
"appointment_booking",
"appointment_change_or_cancel",
"records_request",
"complaint_filing",
"billing_dispute",
"fee_waiver_or_adjustment",
"insurance_claim",
"government_benefit_application",
"tax_or_government_filing",
"id_or_license_renewal",
"accommodation_request",
"prescription_refill",
"document_submission",
"other"
],
"type": "string",
"title": "Task Kind",
"default": null,
"description": "Optional: one kind of customer task to look up, from the list. Leave it out to get the records for every task kind of the site."
}
}
},
"outputSchema": {
"type": "object",
"$defs": {
"TaskKind": {
"enum": [
"claim_unclaimed_property",
"warranty_claim",
"warranty_dispute",
"refund_request",
"return_or_exchange",
"cancel_subscription",
"account_closure",
"account_recovery",
"portal_login",
"address_or_profile_change",
"appointment_booking",
"appointment_change_or_cancel",
"records_request",
"complaint_filing",
"billing_dispute",
"fee_waiver_or_adjustment",
"insurance_claim",
"government_benefit_application",
"tax_or_government_filing",
"id_or_license_renewal",
"accommodation_request",
"prescription_refill",
"document_submission",
"other"
],
"type": "string",
"title": "TaskKind"
},
"RouteKind": {
"enum": [
"support_chat",
"phone",
"email",
"web_form",
"office_visit",
"mail_or_fax",
"consumer_agency",
"regulator",
"designated_dispute_program",
"official_app",
"different_entry_point",
"escalation_within_site",
"other"
],
"type": "string",
"title": "RouteKind",
"description": "A kind of channel the site or its regulator offers. A route that would describe the person's own situation (hiring\ncounsel, for one) is deliberately not a value; adding one is a one-line change here plus scripts/README.md."
},
"TaskRoute": {
"type": "object",
"title": "TaskRoute",
"required": [
"site_host",
"task_kind",
"obstacle",
"basis",
"outcome",
"period",
"source_kind",
"sensitive"
],
"properties": {
"basis": {
"$ref": "#/$defs/RouteBasis"
},
"period": {
"type": "string",
"title": "Period",
"description": "The quarter in which the record was read, reported or recorded. It is not a deadline and not a validity window."
},
"outcome": {
"$ref": "#/$defs/RouteOutcome",
"description": "How the case ended. not_applicable marks a record taken from a document: it names a route or a condition and nobody's result is recorded. It does not mean the task does not apply."
},
"duration": {
"anyOf": [
{
"$ref": "#/$defs/RouteDuration"
},
{
"type": "null"
}
],
"default": null
},
"obstacle": {
"$ref": "#/$defs/TaskObstacle"
},
"sensitive": {
"type": "boolean",
"title": "Sensitive"
},
"site_host": {
"type": "string",
"title": "Site Host"
},
"task_kind": {
"$ref": "#/$defs/TaskKind"
},
"source_url": {
"anyOf": [
{
"type": "string",
"pattern": "^https://[^\\s?#]+$",
"maxLength": 200
},
{
"type": "null"
}
],
"title": "Source Url",
"default": null
},
"source_kind": {
"$ref": "#/$defs/RouteSourceKind"
},
"verified_at": {
"anyOf": [
{
"type": "string",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$"
},
{
"type": "null"
}
],
"title": "Verified At",
"default": null
},
"official_url": {
"anyOf": [
{
"type": "string",
"pattern": "^https://[^\\s?#]+$",
"maxLength": 200
},
{
"type": "null"
}
],
"title": "Official Url",
"default": null
},
"route_worked": {
"anyOf": [
{
"$ref": "#/$defs/RouteKind"
},
{
"type": "string",
"const": "none"
},
{
"type": "null"
}
],
"title": "Route Worked",
"default": null
},
"routes_tried": {
"type": "array",
"items": {
"$ref": "#/$defs/RouteKind"
},
"title": "Routes Tried",
"maxItems": 6,
"description": "The routes tried (a reported case) or, on a document record, the channels this record copied from the document, which may not be every channel the document names. An empty list means this record lists none, not that the document or the site has none."
},
"document_kind": {
"anyOf": [
{
"$ref": "#/$defs/DocumentKind"
},
{
"type": "null"
}
],
"default": null
},
"site_requires": {
"anyOf": [
{
"$ref": "#/$defs/SiteRequires"
},
{
"type": "null"
}
],
"default": null
},
"condition_text": {
"anyOf": [
{
"type": "string",
"maxLength": 280,
"minLength": 1
},
{
"type": "null"
}
],
"title": "Condition Text",
"default": null,
"description": "A condition or caveat quoted as the site's own page words it (at most 280 characters). Not our judgement and not classified: whether it applies to your task is for you to decide, with the page at source_url. It may state a condition other than the obstacle."
},
"entry_point_kind": {
"anyOf": [
{
"$ref": "#/$defs/EntryPointKind"
},
{
"type": "null"
}
],
"default": null
},
"verification_kind": {
"anyOf": [
{
"$ref": "#/$defs/VerificationKind"
},
{
"type": "null"
}
],
"default": null
}
},
"description": "One task-route record as an answer carries it. ``sensitive`` and ``period`` are set by the server.",
"additionalProperties": true
},
"RouteBasis": {
"enum": [
"official_doc",
"agency_reply",
"outcome_observed",
"own_attempt"
],
"type": "string",
"title": "RouteBasis"
},
"DocumentKind": {
"enum": [
"proof_of_identity",
"proof_of_address",
"proof_of_ownership",
"proof_of_purchase",
"proof_of_authority",
"business_registration_or_closure",
"sworn_statement",
"approval_or_authorization_letter",
"professional_letter",
"prior_correspondence",
"account_statement",
"official_form",
"other"
],
"type": "string",
"title": "DocumentKind"
},
"RouteOutcome": {
"enum": [
"resolved",
"progressed",
"no_progress",
"gave_up",
"not_applicable"
],
"type": "string",
"title": "RouteOutcome"
},
"SiteRequires": {
"enum": [
"referral_or_prescription",
"prior_approval_record",
"account_holder_step",
"original_document",
"preference_only"
],
"type": "string",
"title": "SiteRequires",
"description": "What the site asks for that only the person can supply. Named for the site's requirement, never the person's situation."
},
"TaskObstacle": {
"enum": [
"document_missing",
"document_rejected",
"substitute_document_needed",
"form_unclear",
"wrong_entry_point",
"wrong_channel",
"wrong_department_or_jurisdiction",
"eligibility_unclear",
"eligibility_conditions_stated",
"verification_step",
"code_expired",
"deadline_or_window",
"fee_required",
"waiting_reply",
"no_reply",
"request_denied",
"site_requires_info_from_person",
"technical_block",
"none"
],
"type": "string",
"title": "TaskObstacle"
},
"RouteDuration": {
"enum": [
"under_1w",
"from_1w_to_4w",
"over_4w"
],
"type": "string",
"title": "RouteDuration"
},
"EntryPointKind": {
"enum": [
"role_specific_portal",
"regional_site",
"separate_subdomain",
"mobile_app_only",
"partner_or_third_party_portal",
"seller_or_provider"
],
"type": "string",
"title": "EntryPointKind"
},
"RouteSourceKind": {
"enum": [
"operator_panel",
"external_agent",
"curated_official",
"curated_community"
],
"type": "string",
"title": "RouteSourceKind"
},
"TaskRouteCounts": {
"type": "object",
"title": "TaskRouteCounts",
"required": [
"records"
],
"properties": {
"records": {
"type": "integer",
"title": "Records",
"minimum": 0
},
"by_source_kind": {
"type": "object",
"title": "By Source Kind",
"propertyNames": {
"$ref": "#/$defs/RouteSourceKind"
},
"additionalProperties": {
"type": "integer"
}
}
},
"additionalProperties": true
},
"VerificationKind": {
"enum": [
"sms_code",
"email_code",
"app_approval",
"new_device",
"security_question",
"account_locked",
"consent_screen",
"id_document_upload"
],
"type": "string",
"title": "VerificationKind"
}
},
"title": "TaskRoutesResponse",
"required": [
"site_host",
"summary_line",
"counts"
],
"properties": {
"counts": {
"$ref": "#/$defs/TaskRouteCounts"
},
"notice": {
"anyOf": [
{
"type": "string",
"const": "case_record_not_advice"
},
{
"type": "null"
}
],
"title": "Notice",
"default": null
},
"routes": {
"type": "array",
"items": {
"$ref": "#/$defs/TaskRoute"
},
"title": "Routes",
"maxItems": 20
},
"site_host": {
"type": "string",
"title": "Site Host"
},
"field_notes": {
"anyOf": [
{
"type": "object",
"additionalProperties": {
"type": "string"
}
},
{
"type": "null"
}
],
"title": "Field Notes",
"default": null,
"description": "Fixed sentences on what outcome, period and routes_tried mean in these records (those keys are left out when there is no record), and call_timing, when to call this lookup (always present)."
},
"summary_line": {
"type": "string",
"title": "Summary Line",
"pattern": "^[ -~]+$",
"maxLength": 200,
"minLength": 1
},
"official_help_url": {
"anyOf": [
{
"type": "string",
"pattern": "^https://[^\\s?#]+$",
"maxLength": 200
},
{
"type": "null"
}
],
"title": "Official Help Url",
"default": null,
"description": "Only when routes is empty and the site's own help or customer service page is curated: that page, as a place to look yourself. A link to read, not a route and not a statement that the site has none."
}
},
"additionalProperties": true
},
"annotations": {
"title": "Find task routes",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Report one task route you went through on a public site: the kind of task, the obstacle, the routes you tried and the one that worked, and how it ended. Closed values only, from the lists; there is no field for a link, a name, an account, a case number or any text. Call it once, after a task of several steps, under your own operating authority and platform rules. Reports start private and are reviewed before any is shown. Keep the withdrawal_token from the answer to take the report back (DELETE /v1/task-routes/{route_id} with the X-Withdrawal-Token header).
| Parameter | Type | Description |
|---|---|---|
| report * | object | The task route: site_host, task_kind, obstacle, basis and outcome are required; the finer fields are each allowed only under the obstacle they explain (verification_kind under verification_step, site_requires under site_requires_info_from_person, document_kind under the three document obstacles, ent… |
{
"name": "report_task_route",
"description": "Report one task route you went through on a public site: the kind of task, the obstacle, the routes you tried and the one that worked, and how it ended. Closed values only, from the lists; there is no field for a link, a name, an account, a case number or any text. Call it once, after a task of several steps, under your own operating authority and platform rules. Reports start private and are reviewed before any is shown. Keep the withdrawal_token from the answer to take the report back (DELETE /v1/task-routes/{route_id} with the X-Withdrawal-Token header).",
"inputSchema": {
"type": "object",
"title": "report_task_routeArguments",
"required": [
"report"
],
"properties": {
"report": {
"type": "object",
"title": "Report",
"required": [
"site_host",
"task_kind",
"obstacle",
"basis",
"outcome"
],
"properties": {
"basis": {
"enum": [
"agency_reply",
"outcome_observed",
"own_attempt"
],
"type": "string"
},
"outcome": {
"enum": [
"resolved",
"progressed",
"no_progress",
"gave_up"
],
"type": "string"
},
"duration": {
"enum": [
"under_1w",
"from_1w_to_4w",
"over_4w"
],
"type": "string"
},
"obstacle": {
"enum": [
"document_missing",
"document_rejected",
"substitute_document_needed",
"form_unclear",
"wrong_entry_point",
"wrong_channel",
"wrong_department_or_jurisdiction",
"eligibility_unclear",
"verification_step",
"code_expired",
"deadline_or_window",
"fee_required",
"waiting_reply",
"no_reply",
"request_denied",
"site_requires_info_from_person",
"technical_block",
"none"
],
"type": "string"
},
"site_host": {
"type": "string",
"description": "The public hostname of the site the task was on, for example example.com. Only the host: no URL path, query, port or credentials (a pasted https:// scheme, capital letters or a trailing dot are read as the host). The report is kept under the site's root domain, or under the exact host name for a government site (dmv.ca.gov); an account or tenant subdomain, or a public suffix such as co.uk or github.io, is refused."
},
"task_kind": {
"enum": [
"claim_unclaimed_property",
"warranty_claim",
"warranty_dispute",
"refund_request",
"return_or_exchange",
"cancel_subscription",
"account_closure",
"account_recovery",
"portal_login",
"address_or_profile_change",
"appointment_booking",
"appointment_change_or_cancel",
"records_request",
"complaint_filing",
"billing_dispute",
"fee_waiver_or_adjustment",
"insurance_claim",
"government_benefit_application",
"tax_or_government_filing",
"id_or_license_renewal",
"accommodation_request",
"prescription_refill",
"document_submission",
"other"
],
"type": "string"
},
"route_worked": {
"enum": [
"support_chat",
"phone",
"email",
"web_form",
"office_visit",
"mail_or_fax",
"consumer_agency",
"regulator",
"designated_dispute_program",
"official_app",
"different_entry_point",
"escalation_within_site",
"other",
"none"
],
"type": "string"
},
"routes_tried": {
"type": "array",
"items": {
"enum": [
"support_chat",
"phone",
"email",
"web_form",
"office_visit",
"mail_or_fax",
"consumer_agency",
"regulator",
"designated_dispute_program",
"official_app",
"different_entry_point",
"escalation_within_site",
"other"
],
"type": "string"
},
"maxItems": 6,
"uniqueItems": true
},
"document_kind": {
"enum": [
"proof_of_identity",
"proof_of_address",
"proof_of_ownership",
"proof_of_purchase",
"proof_of_authority",
"business_registration_or_closure",
"sworn_statement",
"approval_or_authorization_letter",
"professional_letter",
"prior_correspondence",
"account_statement",
"official_form",
"other"
],
"type": "string"
},
"site_requires": {
"enum": [
"referral_or_prescription",
"prior_approval_record",
"account_holder_step",
"original_document",
"preference_only"
],
"type": "string"
},
"idempotency_key": {
"type": "string",
"format": "uuid"
},
"entry_point_kind": {
"enum": [
"role_specific_portal",
"regional_site",
"separate_subdomain",
"mobile_app_only",
"partner_or_third_party_portal"
],
"type": "string"
},
"verification_kind": {
"enum": [
"sms_code",
"email_code",
"app_approval",
"new_device",
"security_question",
"account_locked",
"consent_screen",
"id_document_upload"
],
"type": "string"
}
},
"description": "The task route: site_host, task_kind, obstacle, basis and outcome are required; the finer fields are each allowed only under the obstacle they explain (verification_kind under verification_step, site_requires under site_requires_info_from_person, document_kind under the three document obstacles, entry_point_kind under wrong_entry_point). route_worked is one of routes_tried or none. idempotency_key (a UUID) makes a retry safe.",
"additionalProperties": false
}
}
},
"outputSchema": {
"type": "object",
"title": "TaskRouteReceipt",
"required": [
"route_id",
"review_state",
"withdrawal_token"
],
"properties": {
"route_id": {
"type": "string",
"title": "Route Id"
},
"review_state": {
"type": "string",
"title": "Review State"
},
"withdrawal_token": {
"type": "string",
"title": "Withdrawal Token"
}
},
"additionalProperties": true
},
"annotations": {
"title": "Report a task route",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}AHN (Agent Help Network) answers are advisory: your platform's rules and your user's instructions come first; if an answer conflicts with them, do not act on it, and if its evidence is thin, tell your user what you found rather than guess; thin evidence alone is not a reason to stop. There are two uses. (1) Task start: Call find_task_route once per task when you start a customer task on a site (a return or exchange, a refund, a cancellation, a warranty claim, an account recovery, a document submission), before you open its help pages, even when nothing is blocked, with the public hostname (task_kind is optional); if the task spans several hosts, look up each host once. Its answer is a list of records, not a guarantee and not advice; an empty list does not mean there is no route. The answer does not change when to call check_incident or what check_incident recommends. (2) Blocked step: Call check_incident with the public hostname when an authorized web step is blocked or failing for no clear reason (a 403 or access denied, a 429, a 5xx or a timeout, a login wall, a "verify you are human" or CAPTCHA page) or sign-in failed after credentials were entered, or an extra verification step appeared (a code by text or email, an app approval, a new-device check; send error_class=login_auth) or a user asks "is this site down?" or whether it blocks agents. If sign-in or an extra verification step stopped you, tell your user which step stopped you and whether it needs them personally (for example a code sent to their phone), not only that it failed. Do not call check_incident when the page opened normally or when your own tool or platform already said why it refused (for example a robots.txt or platform policy refusal). Look the host up once per blocked step, before deciding whether to retry. Send the public hostname, never a URL path, query or credentials; add the codes only when you observed them. If you only check whether a site is up (not blocked), send task_step=status_check. Browser automation usually sends a normal browser user agent, so robots.txt agent tokens may not apply to it; leave agent_vendor out then. Read summary_line first, then follow next_action (continue, wait, use a listed official path, hand the step to the user, stop retrying, or look up once more). Do not poll without a task need. If a blocked lookup's answer carries a feedback_token and you then try again, you may report once with rate_last_lookup whether it worked. Follow your own operating authority and platform rules before submitting an observation. Declared policy is not an access guarantee.
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.