agentcheck is an MCP server published by io.github.agentwares, hosted at agentwares-agentcheck.vercel.app. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 11 tools, including agentcheck_get_status, agentcheck_get_pricing, agentcheck_model_retirements, agentcheck_api_sunsets, agentcheck_statuspage_preview.
Synthetic checks, nightly regression replay and model-drift alerts for AI agents
107 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
Current status of a public monitored target: overall state, uptime over 24h/7d/30d, last check time, last nightly scores, open incidents and the badge/status URLs. Use the owner (GitHub login) and target slug from the status page URL https://agentwares-agentcheck.vercel.app/<owner>/<slug>. No API key needed.
| Parameter | Type | Description |
|---|---|---|
| slug * | string | target slug, e.g. demo |
| owner * | string | GitHub login of the target's owner, e.g. demo |
{
"name": "agentcheck_get_status",
"description": "Current status of a public monitored target: overall state, uptime over 24h/7d/30d, last check time, last nightly scores, open incidents and the badge/status URLs. Use the owner (GitHub login) and target slug from the status page URL https://agentwares-agentcheck.vercel.app/<owner>/<slug>. No API key needed.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"owner",
"slug"
],
"properties": {
"slug": {
"type": "string",
"minLength": 1,
"description": "target slug, e.g. demo"
},
"owner": {
"type": "string",
"minLength": 1,
"description": "GitHub login of the target's owner, e.g. demo"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Machine-readable pricing for agentcheck: tiers with monthly USD price, target limits, check interval and features, plus per-run add-ons. Same data as /pricing.json. No API key needed.
No parameters.
{
"name": "agentcheck_get_pricing",
"description": "Machine-readable pricing for agentcheck: tiers with monthly USD price, target limits, check interval and features, plus per-run add-ons. Same data as /pricing.json. No API key needed.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Is this model retiring? Pass model IDs as your code or config names them (gpt-5-mini, claude-sonnet-4-5-20250929, gemini-2.5-flash, openai/o3-mini). For each, returns every announced shutdown on OpenAI's, Anthropic's and Google's own deprecation pages (OpenAI API, Claude API, Gemini API, Vertex AI): status, shutdown date, recommended replacement, the replacement's list-price ratio per token, the API changes the provider documents, the source URL with the date it was read, and a page with the details. retiring: false means no shutdown for that ID is on those pages. Language models only. No API key needed.
| Parameter | Type | Description |
|---|---|---|
| models * | array | model IDs exactly as your code or config names them, e.g. ["gpt-5-mini", "claude-sonnet-4-5"]; router prefixes such as openai/ or models/ are ignored, and fine-tuned IDs (ft:…) match their base model |
{
"name": "agentcheck_model_retirements",
"description": "Is this model retiring? Pass model IDs as your code or config names them (gpt-5-mini, claude-sonnet-4-5-20250929, gemini-2.5-flash, openai/o3-mini). For each, returns every announced shutdown on OpenAI's, Anthropic's and Google's own deprecation pages (OpenAI API, Claude API, Gemini API, Vertex AI): status, shutdown date, recommended replacement, the replacement's list-price ratio per token, the API changes the provider documents, the source URL with the date it was read, and a page with the details. retiring: false means no shutdown for that ID is on those pages. Language models only. No API key needed.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"models"
],
"properties": {
"models": {
"type": "array",
"items": {
"type": "string",
"maxLength": 200,
"minLength": 1
},
"maxItems": 50,
"minItems": 1,
"description": "model IDs exactly as your code or config names them, e.g. [\"gpt-5-mini\", \"claude-sonnet-4-5\"]; router prefixes such as openai/ or models/ are ignored, and fine-tuned IDs (ft:…) match their base model"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}When does the API version this code pins stop working, and what happens then? Pass provider and version pairs as your code pins them (shopify 2025-10, meta v21.0, google-ads v22, hubspot v1, twilio-flex 2.16.2, twilio-notify v1, keap xml-rpc, exchange-online ews, stripe 2024-06-20). For each, returns every dated end the provider's own versioning, changelog or retirement page lists: status, end date (and whether the provider gives only a month), what happens after it (error, silent fall-forward to another version, app delisting, or unsupported), whether the failure is silent, the replacement version, the source URL with the date it was read, and a page with the details. Where the provider's own pages give different dates for the same end, other_dates lists each one with its page and date_note says which the counts run to. A pair with no entry comes back with the reason: older than every listed version, no end date published yet, or a provider that publishes none (Stripe). Covers Shopify, HubSpot, Meta Graph and Marketing APIs, Google Ads and Content API for Shopping, Twilio Flex UI and Notify, Thryv's Keap XML-RPC, and Exchange Web Services (EWS) in Exchange Online. No API key needed.
| Parameter | Type | Description |
|---|---|---|
| pins * | array | provider and version pairs, e.g. [{"provider": "shopify", "version": "2025-10"}] |
{
"name": "agentcheck_api_sunsets",
"description": "When does the API version this code pins stop working, and what happens then? Pass provider and version pairs as your code pins them (shopify 2025-10, meta v21.0, google-ads v22, hubspot v1, twilio-flex 2.16.2, twilio-notify v1, keap xml-rpc, exchange-online ews, stripe 2024-06-20). For each, returns every dated end the provider's own versioning, changelog or retirement page lists: status, end date (and whether the provider gives only a month), what happens after it (error, silent fall-forward to another version, app delisting, or unsupported), whether the failure is silent, the replacement version, the source URL with the date it was read, and a page with the details. Where the provider's own pages give different dates for the same end, other_dates lists each one with its page and date_note says which the counts run to. A pair with no entry comes back with the reason: older than every listed version, no end date published yet, or a provider that publishes none (Stripe). Covers Shopify, HubSpot, Meta Graph and Marketing APIs, Google Ads and Content API for Shopping, Twilio Flex UI and Notify, Thryv's Keap XML-RPC, and Exchange Web Services (EWS) in Exchange Online. No API key needed.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"pins"
],
"properties": {
"pins": {
"type": "array",
"items": {
"type": "object",
"required": [
"provider",
"version"
],
"properties": {
"api": {
"type": "string",
"maxLength": 60,
"minLength": 1,
"description": "optional, to narrow one provider to one API: admin or storefront (Shopify), graph-api or marketing-api (Meta), ads-api or content-api (Google), pipelines, rest or developer-platform (HubSpot), flex-ui or notify (Twilio), exchange-online (Microsoft); omit it to get every API of that provider with this version"
},
"version": {
"type": "string",
"maxLength": 60,
"minLength": 1,
"description": "the version as the code pins it: 2025-10, v21.0, v22, v1, 2025.2, 2.16.2, xml-rpc, ews, 2024-06-20"
},
"provider": {
"type": "string",
"maxLength": 60,
"minLength": 1,
"description": "the provider as you would name it: shopify, hubspot, meta (or facebook), google-ads, content-api, twilio-flex, twilio-notify, keap (or thryv, infusionsoft), ews (or exchange-online, microsoft), stripe"
}
},
"additionalProperties": false
},
"maxItems": 50,
"minItems": 1,
"description": "provider and version pairs, e.g. [{\"provider\": \"shopify\", \"version\": \"2025-10\"}]"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Read a public Atlassian Statuspage page once: its name, overall status, components (id, name, status, group) and unresolved incidents, from the page's own /api/v2/summary.json. Pass any address on the page: status.example.com, https://status.example.com/history or the JSON URL. Use it before POST /api/v1/statuspage, which turns the components you give a URL into a live agentcheck status page checked by agentcheck itself, with no signup; the answer carries that request's body. Same read as /statuspage/preview: only public addresses, 5-second timeout, 512 KB cap. Private pages cannot be read. No API key needed.
| Parameter | Type | Description |
|---|---|---|
| url * | string | the status page's address, e.g. https://status.example.com or its summary.json |
{
"name": "agentcheck_statuspage_preview",
"description": "Read a public Atlassian Statuspage page once: its name, overall status, components (id, name, status, group) and unresolved incidents, from the page's own /api/v2/summary.json. Pass any address on the page: status.example.com, https://status.example.com/history or the JSON URL. Use it before POST /api/v1/statuspage, which turns the components you give a URL into a live agentcheck status page checked by agentcheck itself, with no signup; the answer carries that request's body. Same read as /statuspage/preview: only public addresses, 5-second timeout, 512 KB cap. Private pages cannot be read. No API key needed.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"maxLength": 2048,
"minLength": 1,
"description": "the status page's address, e.g. https://status.example.com or its summary.json"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Enroll something to monitor: an http endpoint (JSON or OpenAI-style chat), a remote MCP server (Streamable HTTP url) or an A2A agent (origin with /.well-known/agent-card.json). Pass `checks` to create checks in the same call (POST /api/v1/probe proposes three). Returns the target id, the public status page, the badge SVG URL and a README snippet. The first check runs on the next scheduled tick, within five minutes; call agentcheck_run_now to run immediately. Free tier: 1 target, hourly; Starter+: 5-minute checks. Requires an API key.
| Parameter | Type | Description |
|---|---|---|
| url | string | endpoint URL (http/mcp) or the agent's origin (a2a) |
| auth | any | credential the prober sends to your endpoint: {type:'bearer',token} or {type:'header',name,value}. Stored encrypted and never returned or logged. |
| kind * | string | http (JSON or chat endpoint), mcp (Streamable HTTP url, or npx/uvx package spec), a2a (agent card) |
| name | string | display name; defaults to the host |
| slug | string | URL slug for /<owner>/<slug>; defaults to a slug of the name |
| alerts | object | where to send an incident when a check starts failing. Any combination; omit it and incidents are visible only on the status page. |
| checks | array | checks to create right away (the probe proposes three) |
| format | string | http: openai_chat (POST /chat/completions body), json (raw POST), get (plain fetch) |
| headers | object | extra request headers |
| isPublic | boolean | public status page + badge (default true) |
| modelVar | string | the model your agent runs on (e.g. claude-sonnet-5); enables model-drift re-runs |
| corpusUrl | string | RAG targets: public corpus URL for the nightly groundedness scorer (Pro) |
| modelHeader | string | request header your endpoint accepts to override the model (drift re-runs try the new model) |
| packageSpec | string | mcp only: `npx @org/server` / `uvx server` — runs on the mcpcheck runner, not the scheduled checks |
| agentCardUrl | string | a2a: explicit agent card URL when it is not at /.well-known/agent-card.json |
{
"name": "agentcheck_create_target",
"description": "Enroll something to monitor: an http endpoint (JSON or OpenAI-style chat), a remote MCP server (Streamable HTTP url) or an A2A agent (origin with /.well-known/agent-card.json). Pass `checks` to create checks in the same call (POST /api/v1/probe proposes three). Returns the target id, the public status page, the badge SVG URL and a README snippet. The first check runs on the next scheduled tick, within five minutes; call agentcheck_run_now to run immediately. Free tier: 1 target, hourly; Starter+: 5-minute checks. Requires an API key.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"kind"
],
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "endpoint URL (http/mcp) or the agent's origin (a2a)"
},
"auth": {
"anyOf": [
{
"type": "object",
"required": [
"type",
"token"
],
"properties": {
"type": {
"type": "string",
"const": "bearer"
},
"token": {
"type": "string"
}
}
},
{
"type": "object",
"required": [
"type",
"name",
"value"
],
"properties": {
"name": {
"type": "string"
},
"type": {
"type": "string",
"const": "header"
},
"value": {
"type": "string"
}
}
}
],
"description": "credential the prober sends to your endpoint: {type:'bearer',token} or {type:'header',name,value}. Stored encrypted and never returned or logged."
},
"kind": {
"enum": [
"http",
"mcp",
"a2a"
],
"type": "string",
"description": "http (JSON or chat endpoint), mcp (Streamable HTTP url, or npx/uvx package spec), a2a (agent card)"
},
"name": {
"type": "string",
"maxLength": 80,
"minLength": 1,
"description": "display name; defaults to the host"
},
"slug": {
"type": "string",
"pattern": "^[a-z0-9][a-z0-9-]{0,62}$",
"description": "URL slug for /<owner>/<slug>; defaults to a slug of the name"
},
"alerts": {
"type": "object",
"properties": {
"emails": {
"type": "array",
"items": {
"type": "string",
"format": "email",
"pattern": "^(?!\\.)(?!.*\\.\\.)([A-Za-z0-9_'+\\-\\.]*)[A-Za-z0-9_+-]@([A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"
}
},
"slackWebhookUrl": {
"type": "string",
"format": "uri"
},
"discordWebhookUrl": {
"type": "string",
"format": "uri"
}
},
"description": "where to send an incident when a check starts failing. Any combination; omit it and incidents are visible only on the status page."
},
"checks": {
"type": "array",
"items": {
"type": "object",
"required": [
"name",
"kind",
"golden"
],
"properties": {
"kind": {
"enum": [
"http",
"mcp_tools_list",
"mcp_tool_call",
"a2a_task",
"custom"
],
"type": "string",
"description": "what to run: http (GET path or POST prompt), mcp_tools_list, mcp_tool_call (tool + args), a2a_task (message)"
},
"name": {
"type": "string",
"maxLength": 120,
"minLength": 1,
"description": "short name shown on the status page"
},
"input": {
"type": "object",
"default": {},
"description": "http: { path?, method?, body?, prompt? } · mcp_tool_call: { tool, args } · a2a_task: { message }",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"golden": {
"type": "object",
"required": [
"kind"
],
"properties": {
"kind": {
"enum": [
"exact",
"contains",
"regex",
"json_schema",
"rubric",
"baseline"
],
"type": "string",
"description": "how the answer is judged; exact/contains/regex/json_schema cost nothing, rubric/baseline use the LLM judge"
},
"tools": {
"type": "array",
"items": {
"type": "string"
},
"description": "expected tool-call sequence (replay checks)"
},
"value": {
"type": "string",
"description": "exact / contains: the expected text"
},
"rubric": {
"type": "string",
"description": "rubric: what a passing answer must do, in plain language"
},
"schema": {
"type": "object",
"description": "json_schema: JSON Schema (draft 2020-12 subset)",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"pattern": {
"type": "string",
"description": "regex: pattern source without slashes"
},
"expected": {
"type": "string",
"description": "rubric: a reference answer, when there is one"
},
"caseInsensitive": {
"type": "boolean"
}
},
"description": "how the answer is judged. exact / contains / regex / json_schema are free and deterministic; rubric and baseline call the LLM judge, and baseline compares against the last known-good answer."
},
"intervalSec": {
"type": "integer",
"default": 3600,
"maximum": 604800,
"minimum": 60,
"description": "seconds between runs; the tier's interval is the floor (Free hourly, Starter+ 5 min)"
}
}
},
"maxItems": 20,
"description": "checks to create right away (the probe proposes three)"
},
"format": {
"enum": [
"openai_chat",
"json",
"get"
],
"type": "string",
"description": "http: openai_chat (POST /chat/completions body), json (raw POST), get (plain fetch)"
},
"headers": {
"type": "object",
"description": "extra request headers",
"propertyNames": {
"type": "string"
},
"additionalProperties": {
"type": "string"
}
},
"isPublic": {
"type": "boolean",
"default": true,
"description": "public status page + badge (default true)"
},
"modelVar": {
"type": "string",
"description": "the model your agent runs on (e.g. claude-sonnet-5); enables model-drift re-runs"
},
"corpusUrl": {
"type": "string",
"format": "uri",
"description": "RAG targets: public corpus URL for the nightly groundedness scorer (Pro)"
},
"modelHeader": {
"type": "string",
"description": "request header your endpoint accepts to override the model (drift re-runs try the new model)"
},
"packageSpec": {
"type": "string",
"description": "mcp only: `npx @org/server` / `uvx server` — runs on the mcpcheck runner, not the scheduled checks"
},
"agentCardUrl": {
"type": "string",
"format": "uri",
"description": "a2a: explicit agent card URL when it is not at /.well-known/agent-card.json"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": true
}
}Add a check to one of your targets. A check runs an input (http path/prompt, mcp tool call, a2a message) on a schedule and judges the answer with a golden: exact, contains, regex and json_schema cost nothing; rubric and baseline use the LLM judge (baseline = same outcome as the last known-good answer). Returns the check id. Requires an API key.
| Parameter | Type | Description |
|---|---|---|
| kind * | string | what to run: http (GET path or POST prompt), mcp_tools_list, mcp_tool_call (tool + args), a2a_task (message) |
| name * | string | short name shown on the status page |
| input | object | http: { path?, method?, body?, prompt? } · mcp_tool_call: { tool, args } · a2a_task: { message } |
| golden * | object | how the answer is judged. exact / contains / regex / json_schema are free and deterministic; rubric and baseline call the LLM judge, and baseline compares against the last known-good answer. |
| targetId * | string | id from agentcheck_create_target or GET /api/v1/targets |
| intervalSec | integer | seconds between runs; the tier's interval is the floor (Free hourly, Starter+ 5 min) |
{
"name": "agentcheck_add_check",
"description": "Add a check to one of your targets. A check runs an input (http path/prompt, mcp tool call, a2a message) on a schedule and judges the answer with a golden: exact, contains, regex and json_schema cost nothing; rubric and baseline use the LLM judge (baseline = same outcome as the last known-good answer). Returns the check id. Requires an API key.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"name",
"kind",
"golden",
"targetId"
],
"properties": {
"kind": {
"enum": [
"http",
"mcp_tools_list",
"mcp_tool_call",
"a2a_task",
"custom"
],
"type": "string",
"description": "what to run: http (GET path or POST prompt), mcp_tools_list, mcp_tool_call (tool + args), a2a_task (message)"
},
"name": {
"type": "string",
"maxLength": 120,
"minLength": 1,
"description": "short name shown on the status page"
},
"input": {
"type": "object",
"default": {},
"description": "http: { path?, method?, body?, prompt? } · mcp_tool_call: { tool, args } · a2a_task: { message }",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"golden": {
"type": "object",
"required": [
"kind"
],
"properties": {
"kind": {
"enum": [
"exact",
"contains",
"regex",
"json_schema",
"rubric",
"baseline"
],
"type": "string",
"description": "how the answer is judged; exact/contains/regex/json_schema cost nothing, rubric/baseline use the LLM judge"
},
"tools": {
"type": "array",
"items": {
"type": "string"
},
"description": "expected tool-call sequence (replay checks)"
},
"value": {
"type": "string",
"description": "exact / contains: the expected text"
},
"rubric": {
"type": "string",
"description": "rubric: what a passing answer must do, in plain language"
},
"schema": {
"type": "object",
"description": "json_schema: JSON Schema (draft 2020-12 subset)",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
},
"pattern": {
"type": "string",
"description": "regex: pattern source without slashes"
},
"expected": {
"type": "string",
"description": "rubric: a reference answer, when there is one"
},
"caseInsensitive": {
"type": "boolean"
}
},
"description": "how the answer is judged. exact / contains / regex / json_schema are free and deterministic; rubric and baseline call the LLM judge, and baseline compares against the last known-good answer."
},
"targetId": {
"type": "string",
"minLength": 1,
"description": "id from agentcheck_create_target or GET /api/v1/targets"
},
"intervalSec": {
"type": "integer",
"default": 3600,
"maximum": 604800,
"minimum": 60,
"description": "seconds between runs; the tier's interval is the floor (Free hourly, Starter+ 5 min)"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Run every check of one of your targets immediately (outside the schedule) and return pass/fail per check with latency, judge cost and any incident opened or closed. Use it right after enrolling, or to confirm a fix. Requires an API key.
| Parameter | Type | Description |
|---|---|---|
| targetId * | string | target id |
{
"name": "agentcheck_run_now",
"description": "Run every check of one of your targets immediately (outside the schedule) and return pass/fail per check with latency, judge cost and any incident opened or closed. Use it right after enrolling, or to confirm a fix. Requires an API key.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"targetId"
],
"properties": {
"targetId": {
"type": "string",
"minLength": 1,
"description": "target id"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}Record one production interaction with your agent (the prompt or messages, the final answer, the tools it called, optionally the model) as a trace on a target. Call it from your agent or from a proxy in front of it after each task; promote a good trace with agentcheck_promote_trace to replay it nightly and catch regressions. Requires an API key.
| Parameter | Type | Description |
|---|---|---|
| name | string | short label, e.g. 'refund for order A-1029' |
| input * | any | the prompt, the messages array, or an object with prompt/messages |
| model | string | the model that produced this answer, so drift re-runs can compare across models |
| output * | string | the agent's final answer |
| targetId * | string | id from agentcheck_create_target or GET /api/v1/targets |
| toolCalls | array | tool calls in order |
{
"name": "agentcheck_record",
"description": "Record one production interaction with your agent (the prompt or messages, the final answer, the tools it called, optionally the model) as a trace on a target. Call it from your agent or from a proxy in front of it after each task; promote a good trace with agentcheck_promote_trace to replay it nightly and catch regressions. Requires an API key.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"targetId",
"input",
"output"
],
"properties": {
"name": {
"type": "string",
"maxLength": 120,
"description": "short label, e.g. 'refund for order A-1029'"
},
"input": {
"anyOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "object",
"required": [
"role",
"content"
],
"properties": {
"role": {
"type": "string"
},
"content": {
"type": "string"
}
}
}
},
{
"type": "object",
"propertyNames": {
"type": "string"
},
"additionalProperties": {}
}
],
"description": "the prompt, the messages array, or an object with prompt/messages"
},
"model": {
"type": "string",
"description": "the model that produced this answer, so drift re-runs can compare across models"
},
"output": {
"type": "string",
"minLength": 1,
"description": "the agent's final answer"
},
"targetId": {
"type": "string",
"minLength": 1,
"description": "id from agentcheck_create_target or GET /api/v1/targets"
},
"toolCalls": {
"type": "array",
"items": {
"type": "object",
"required": [
"name"
],
"properties": {
"args": {},
"name": {
"type": "string"
}
}
},
"description": "tool calls in order"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Turn an imported or recorded trace into a replayable check whose golden is the recorded outcome (tool sequence + final-answer rubric). The check runs daily and in the nightly replay (Pro). Returns the check. Requires an API key.
| Parameter | Type | Description |
|---|---|---|
| traceId * | string | trace id from agentcheck_record or POST /api/v1/targets/{id}/traces |
{
"name": "agentcheck_promote_trace",
"description": "Turn an imported or recorded trace into a replayable check whose golden is the recorded outcome (tool sequence + final-answer rubric). The check runs daily and in the nightly replay (Pro). Returns the check. Requires an API key.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"traceId"
],
"properties": {
"traceId": {
"type": "string",
"minLength": 1,
"description": "trace id from agentcheck_record or POST /api/v1/targets/{id}/traces"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Open and recent incidents across your targets (or one target): when they opened/closed, the failing check and the cause. Requires an API key.
| Parameter | Type | Description |
|---|---|---|
| targetId | string | narrow to one target; omit for incidents across every target on the account |
{
"name": "agentcheck_list_incidents",
"description": "Open and recent incidents across your targets (or one target): when they opened/closed, the failing check and the cause. Requires an API key.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"targetId": {
"type": "string",
"description": "narrow to one target; omit for incidents across every target on the account"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}agentcheck monitors production AI agents and MCP servers and re-runs your suite when a model changes. Public tools need no key: agentcheck_get_status(owner, slug), agentcheck_get_pricing(), agentcheck_model_retirements(models), agentcheck_api_sunsets(pins), agentcheck_statuspage_preview(url). With an API key (Authorization: Bearer ak_live_…, free at /dashboard/keys): agentcheck_create_target → agentcheck_add_check → agentcheck_run_now; agentcheck_record + agentcheck_promote_trace turn production traces into nightly regression checks; agentcheck_list_incidents. Public model-drift index: /drift.json.
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.