Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

agentcheck

REMOTE · AGENTWARES-AGENTCHECK.VERCEL.APP · SCANNED SEP 25

Synthetic checks, nightly regression replay and model-drift alerts for AI agents

+3 this week 73 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability66
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1489 tokens (~186/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management60
  • Stability observed for 18 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the agentcheck MCP server?

agentcheck is a hosted endpoint at https://agentwares-agentcheck.vercel.app/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · agentwares-agentcheck.vercel.app

# add to Claude Code
claude mcp add --transport http agentwares-agentcheck 'https://agentwares-agentcheck.vercel.app/api/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "agentwares-agentcheck": {
      "url": "https://agentwares-agentcheck.vercel.app/api/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "agentwares-agentcheck": {
      "type": "http",
      "url": "https://agentwares-agentcheck.vercel.app/api/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.agentwares-agentcheck]
url = "https://agentwares-agentcheck.vercel.app/api/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "agentwares-agentcheck": {
      "type": "remote",
      "url": "https://agentwares-agentcheck.vercel.app/api/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add agentwares-agentcheck --url 'https://agentwares-agentcheck.vercel.app/api/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  agentwares-agentcheck:
    url: "https://agentwares-agentcheck.vercel.app/api/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "agentwares-agentcheck": {
      "Transport": "http",
      "Url": "https://agentwares-agentcheck.vercel.app/api/mcp"
    }
  }
}
# add to Vellum
assistant mcp add agentwares-agentcheck -t streamable-http -u 'https://agentwares-agentcheck.vercel.app/api/mcp'
// mcp.json
{
  "mcpServers": {
    "agentwares-agentcheck": {
      "type": "http",
      "url": "https://agentwares-agentcheck.vercel.app/api/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 25 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 23 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

  • 21 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Sept 26 +1
    • Schema quality: 168 → 186 ▼ functional
    • Tool coverage: 81% → 100% ▲ functional
    • Schema quality: good → excellent functional
    • Server version: 0.1.0 → 0.1.1 functional
    • “agentcheck_add_check” reworded the description of “golden” cosmetic
    • “agentcheck_create_target” reworded the description of “alerts” cosmetic
    • “agentcheck_create_target” reworded the description of “auth” cosmetic
    • “agentcheck_list_incidents” reworded the description of “targetId” cosmetic
    • “agentcheck_record” reworded the description of “model” cosmetic
    • “agentcheck_record” reworded the description of “targetId” cosmetic
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 25 Sept 2026 · Probed https://agentwares-agentcheck.vercel.app/api/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=*.vercel.app CN=WR1,O=Google Trust Services,C=US 29 Aug 2026 27 Nov 2026 RSA 2048 SHA256-RSA f7911168ffa7d0f4135e24792e7a52a8
SANs: *.vercel.app
CN=WR1,O=Google Trust Services,C=US (CA) CN=GTS Root R1,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 RSA 2048 SHA256-RSA 7fd9e2c2d2048a0474b627a26d0868a7
CN=GTS Root R1,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 19 Jun 2020 28 Jan 2028 RSA 4096 SHA256-RSA 77bd0d6cdb36f91aea210fc4f058d30d

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of agentwares-agentcheck.vercel.app. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
app. present 23684 8 Verified
vercel.app. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=63072000; includeSubDomains; preload
x-content-type-options nosniff
referrer-policy strict-origin-when-cross-origin

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://agentwares-agentcheck.vercel.app/api/mcp Verified 200
http (plaintext) http://agentwares-agentcheck.vercel.app/api/mcp HTTPS enforced 308 https://agentwares-agentcheck.vercel.app/api/mcp
MCP tools · 8 exposed · ~1,377 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
agentcheck_add_check ~277

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.

NameTypeReqDescription
goldenobjectyeshow 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.
inputobject–http: { path?, method?, body?, prompt? } · mcp_tool_call: { tool, args } · a2a_task: { message }
intervalSecinteger–seconds between runs; the tier's interval is the floor (Free hourly, Starter+ 5 min)
kindstringyeswhat to run: http (GET path or POST prompt), mcp_tools_list, mcp_tool_call (tool + args), a2a_task (message)
namestringyesshort name shown on the status page
targetIdstringyesid from agentcheck_create_target or GET /api/v1/targets

No output schema declared.

No examples provided.

agentcheck_create_target ~524

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 minute tick; call agentcheck_run_now to run immediately. Free tier: 1 target, hourly; Starter+: 5-minute checks. Requires an API key.

NameTypeReqDescription
agentCardUrlstring–a2a: explicit agent card URL when it is not at /.well-known/agent-card.json
alertsobject–where to send an incident when a check starts failing. Any combination; omit it and incidents are visible only on the status page.
auth––credential the prober sends to your endpoint: {type:'bearer',token} or {type:'header',name,value}. Stored encrypted and never returned or logged.
checksarray–checks to create right away (the probe proposes three)
corpusUrlstring–RAG targets: public corpus URL for the nightly groundedness scorer (Pro)
formatstring–http: openai_chat (POST /chat/completions body), json (raw POST), get (plain fetch)
headersobject–extra request headers
isPublicboolean–public status page + badge (default true)
kindstringyeshttp (JSON or chat endpoint), mcp (Streamable HTTP url, or npx/uvx package spec), a2a (agent card)
modelHeaderstring–request header your endpoint accepts to override the model (drift re-runs try the new model)
modelVarstring–the model your agent runs on (e.g. claude-sonnet-5); enables model-drift re-runs
namestring–display name; defaults to the host
packageSpecstring–mcp only: `npx @org/server` / `uvx server` — runs on the mcpcheck runner, not the minute checks
slugstring–URL slug for /<owner>/<slug>; defaults to a slug of the name
urlstring–endpoint URL (http/mcp) or the agent's origin (a2a)

No output schema declared.

No examples provided.

agentcheck_get_pricing ~50

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.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

agentcheck_get_status ~118

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.

NameTypeReqDescription
ownerstringyesGitHub login of the target's owner, e.g. demo
slugstringyestarget slug, e.g. demo

No output schema declared.

No examples provided.

agentcheck_list_incidents ~63

Open and recent incidents across your targets (or one target): when they opened/closed, the failing check and the cause. Requires an API key.

NameTypeReqDescription
targetIdstring–narrow to one target; omit for incidents across every target on the account

No output schema declared.

No examples provided.

agentcheck_promote_trace ~84

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.

NameTypeReqDescription
traceIdstringyestrace id from agentcheck_record or POST /api/v1/targets/{id}/traces

No output schema declared.

No examples provided.

agentcheck_record ~191

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.

NameTypeReqDescription
input–yesthe prompt, the messages array, or an object with prompt/messages
modelstring–the model that produced this answer, so drift re-runs can compare across models
namestring–short label, e.g. 'refund for order A-1029'
outputstringyesthe agent's final answer
targetIdstringyesid from agentcheck_create_target or GET /api/v1/targets
toolCallsarray–tool calls in order

No output schema declared.

No examples provided.

agentcheck_run_now ~70

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.

NameTypeReqDescription
targetIdstringyestarget id

No output schema declared.

No examples provided.

Common questions

What is the agentcheck MCP server?

agentcheck is an MCP server listed in the public MCP registry as io.github.agentwares/agentcheck. Synthetic checks, nightly regression replay and model-drift alerts for AI agents. This page covers its hosted endpoint (https://agentwares-agentcheck.vercel.app/api/mcp).

Is the agentcheck MCP server safe to use?

agentcheck scores 73 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the agentcheck MCP server expose?

agentcheck exposes 8 tools: agentcheck_get_status, agentcheck_get_pricing, agentcheck_create_target, agentcheck_add_check, agentcheck_run_now, and 3 more. Their descriptions and schemas cost roughly 1,377 tokens of context every time the server is loaded.

Does the agentcheck MCP server require authentication?

No. We connected to agentcheck without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the agentcheck MCP server still maintained?

agentcheck is still listed as active in the MCP registry. We last reached this channel on 25 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.