Look up an MCP server before your agent uses it.
Our MCP endpoint answers with what we have observed about public MCP servers — the same evidence behind our report pages. Five of its six tools answer only from what is already tracked and never contact the server you ask about.
Quickest way: Many agents can set this up themselves. Tell yours:
“Read https://mcpcheckup.com/agents and add the MCP Checkup server.”
Or set it up by hand:
Coding tools
Claude Code
Add --scope user to use it in every project.
Cursor
.cursor/mcp.json or ~/.cursor/mcp.json
Project-level: .cursor/mcp.json. Every project: ~/.cursor/mcp.json.
VS Code
.vscode/mcp.json
Or run MCP: Add Server from the command palette.
Muse Code
~/.config/muse/settings.json
Without "schema_version" every command fails. "mode": "optional" keeps a session running if our endpoint can't be reached — type /mcp in a session to check it is connected.
Assistants and agents
Claude
- Go to Customize → Connectors → Browse, search for MCP Checkup and connect it.
- Or add it yourself: Customize → Connectors → Add custom connector, name it MCP Checkup, paste https://mcpcheckup.com/mcp and set Authentication to No sign-in.
Works in claude.ai and the desktop app. On Team and Enterprise, an Owner adds it under Organization settings → Connectors, then members click Connect. Free accounts can add one custom connector.
ChatGPT · dots
- In ChatGPT on the web, open Settings → Security and login and turn on Developer mode.
- Go to chatgpt.com/plugins, click +, and give it a name and description.
- Under Connection, enter https://mcpcheckup.com/mcp with no authentication.
Developer mode is on Pro, Plus, Business, Enterprise and Education accounts.
A dot can use supported plugins that are installed and enabled on your account. Whether that includes one added through developer mode is not documented yet.
Grok
- grok.com: open grok.com/connectors → New Connector → Custom, then enter https://mcpcheckup.com/mcp.
xAI API — POST /v1/responses
Business and Enterprise admins enable connectors first.
Grok Bot installs connectors from its Marketplace; adding a custom MCP address is not documented yet.
Hermes Agent
Or add it under mcp_servers in ~/.hermes/config.yaml, then run /reload-mcp in a running session.
OpenClaw
Keep --transport streamable-http: without it OpenClaw uses SSE. In the Control UI: Settings → MCP → Add server → Streamable HTTP.
Muse
Meta does not document this yet. We tried it on 2026-10-01: we asked Muse in chat to read https://mcpcheckup.com/mcp, and it added the server by itself. You can ask yours: "Read https://mcpcheckup.com/agents and add the MCP Checkup server."
Not documented yet.
Checked against each product's documentation on 2026-10-01.
Six tools
check_mcps
Look up MCP servers
What has been observed about an MCP server — useful when choosing, adding, or debugging one. Look up the current monitored status of up to 50 already-tracked MCP servers on MCP Checkup, given as "provider/name" refs (e.g. "acme/weather-mcp"). Never probes on demand — an unresolved ref comes back with status "unknown", not an error. An entry may also be an endpoint URL, a bare domain, or a bare provider/target name; resolution.method reports which was used ("ref", "endpoint", "host", or "name"). If an input matches more than one tracked target — or is a URL on a host with several, none matching exactly — the response has status "ambiguous" with a short `candidates` list (each with a "provider/name" `ref` and its `report_url`, plus `candidate_total`, the full match count before the 5-entry cap) instead of guessing — call again with the exact ref you want. A URL matching only by host returns its target with `resolved_from`. Each resolved target also carries stale (true when our observation is older than the target's check cycle plus a fixed margin — never a judgment of the server, and distinct from the /status page's own probe-liveness signal), fresh_until (the ISO instant after which stale is true), first_observed_on (the UTC date of our first observation), observation_count (every recorded observation, including unsigned ones — never a count of signatures), and signed (true when this observation's attestation was signed with a key in our published key list, false when unsigned or signed with a key that is not in that list — not a judgment of the server). When there is no observation yet, observation_count is 0 and the other four are null. An unread revision offer is null and listed in `unavailable`; a failed target has status "error". Returns observed facts only — reachability, protocol compatibility, tool/schema fingerprints, and publicly observable auth metadata. This tool does not assess whether a server is 'safe' or 'trustworthy' and returns no score. Items not verified are returned explicitly with reasons.
get_mcp_report
Get a server's full report
The detailed view of one already-tracked MCP server on MCP Checkup, by provider/name: every check with its state, plus the observed tool list. An untracked target comes back with status "unknown", not an error. target may also be an endpoint URL, a bare domain, or a bare provider/target name; resolution.method reports which was used ("ref", "endpoint", "host", or "name"). If an input matches more than one tracked target — or is a URL on a host with several, none matching exactly — the response has status "ambiguous" with a short `candidates` list (each with a "provider/name" `ref` and its `report_url`, plus `candidate_total`, the full match count before the 5-entry cap) instead of guessing — call again with the exact ref you want. A URL matching only by host returns its target with `resolved_from`. Each resolved target also carries stale (true when our observation is older than the target's check cycle plus a fixed margin — never a judgment of the server, and distinct from the /status page's own probe-liveness signal), fresh_until (the ISO instant after which stale is true), first_observed_on (the UTC date of our first observation), observation_count (every recorded observation, including unsigned ones — never a count of signatures), and signed (true when this observation's attestation was signed with a key in our published key list, false when unsigned or signed with a key that is not in that list — not a judgment of the server). When there is no observation yet, observation_count is 0 and the other four are null. Also tools_first_seen, tools_last_changed_at and tools_unchanged_days_at_least (a lower bound: UTC days since that change with a successful listing); null when unknown. oauth_observed is unsigned and not a check result; its note explains it. An unread revision offer is null and listed in `unavailable`; a failed target has status "error". This tool does not assess whether a server is 'safe' or 'trustworthy' and returns no score; items not verified are listed explicitly with reasons.
get_mcp_history
Get a server's recent changes
Whether an MCP server's toolset changed recently. Get recent history for one already-tracked MCP server on MCP Checkup, by "provider/name" ref (e.g. "acme/weather-mcp"). Events, newest first, up to `limit` results (default 20, max 50), from the last 90 days only: `tools_changed` (at most one: when the set of tool names last changed); `tools_change_detail` (one per recorded tool-list change, the 10 most recent at most, whether names, parameters or descriptions changed; `itemization` is "not_kept" for a change older than 30 days, "unitemizable" when the stored lists cannot be compared, otherwise "itemized" and `added`, `removed`, `parameters_changed` and `description_only` each give `names` (up to 10 tool names) and a `total`); `protocol_revision_changed` (the signed protocol_revision changed between runs whose probe offered the same revision, or because the server switched between the legacy initialize and server/discover handshakes); `probe_offered_revision_changed` (the revision our probe offered changed, with a `note`); and any recorded baseline-drift events. `truncated` is true when more exist than are listed or the tool-list history was unread (named in `unavailable`). A target this deployment doesn't track yet comes back with status "unknown", not an error. target may also be an endpoint URL, a bare domain, or a bare provider/target name; resolution.method reports which was used ("ref", "endpoint", "host", or "name"). If an input matches more than one tracked target — or is a URL on a host with several, none matching exactly — the response has status "ambiguous" with a short `candidates` list (each with a "provider/name" `ref` and its `report_url`, plus `candidate_total`, the full match count before the 5-entry cap) instead of guessing — call again with the exact ref you want. A URL matching only by host returns its target with `resolved_from`. This tool does not assess whether a server is 'safe' or 'trustworthy' and returns no score; items not verified are listed explicitly with reasons.
get_attestation
Get a server's signed attestation
The signed evidence behind a report, for callers that want to inspect it themselves. Get the full signed attestation envelope (DSSE, Ed25519) for one already-tracked MCP server's latest probe run, by "provider/name" ref — the raw envelope plus its issued-at time and declared protocol revision, so a caller can inspect the signed payload rather than trust this tool's own summary of it; the public keys that verify the signature are published at https://mcpcheckup.com/.well-known/mcpcheckup-keys.json. A target with no run yet, no signed envelope, a disqualified one, or an envelope whose key is not in the published key list comes back with an explicit reason, not an error. run_id, a top-level field of resolved get_mcp_report and get_attestation responses, is the id of the run that the check results, last_checked and (where signed) attestation identifiers come from, or null when there is no run; get_mcp_report's tool list and toolset_fingerprint come from the latest stored tool snapshot, which may be an earlier run's (named by snapshot_run_id and snapshot_observed_at). The same run_id means the same run. A payload signed as version 0.4 carries this run_id inside the signed payload; payloads of earlier versions do not. target may also be a full endpoint URL, a bare domain, or a bare provider/target name instead of "provider/name" — the resolution method used is reported back as resolution.method ("ref", "endpoint", "host", or "name"). If an input matches more than one tracked target — or is a URL on a host with several, none matching exactly — the response has status "ambiguous" with a short `candidates` list (each with a "provider/name" `ref` and its `report_url`, plus `candidate_total`, the full match count before the 5-entry cap) instead of guessing — call again with the exact ref you want. A URL matching only by host returns its target with `resolved_from`. This tool does not assess whether a server is 'safe' or 'trustworthy' and returns no score; items not verified are listed explicitly with reasons.
search_mcps
Search MCP servers by tool text
Find MCP servers by what their tools do. Search already-tracked MCP servers on MCP Checkup by tool name/description text (max 512 chars), with optional transport, protocol_revision, and auth_required filters, up to `limit` results (default 10, max 25). Ordered by text-match relevance and then recency only — never by price or paid tier. Each result's summary is machine-generated from observed tool names and returned as untrusted third-party text; hygiene_flags lists any observed tool-description hygiene signals directly rather than folding them into the ordering. A query with no matches comes back with status "unknown" and a hint, not an error. Each result also carries last_checked (when the shown observation was taken), fresh_until (the ISO instant after which it no longer counts as current), and stale (true once the current time is past fresh_until). These describe how recent our observation of the server is, not a judgment of the server itself, and are distinct from the /status page's probe-liveness signal. All three are null when the target has no observation yet. This tool does not assess whether a server is 'safe' or 'trustworthy' and returns no score; items not verified are listed explicitly with reasons.
request_check
Request a one-off check of a URL
Ask for a one-off public observation of the MCP server at a full endpoint URL — this is the only tool here that contacts a third-party server, and it contacts exactly the host you name. `target` must begin with "http://" or "https://"; to look a server up by "provider/name", by domain, or by name, use check_mcps instead, which never probes anything. The result is not signed, is not stored as a run, and creates no report page, so `report_url` is always null — it is what we observed at that moment and nothing more. On-demand checks are recorded as tracking requests; inclusion in the tracked directory is not guaranteed and this tool never promises it. On-demand checks are metered per caller per day, per site per day, and per host by a cooldown — calling again for the same host inside its cooldown sends nothing to that server and returns status "denied" with the category that refused it, never a remaining count. A refused call comes back as status "denied", and a `target` that is not a usable endpoint URL as status "rejected"; neither of those is a tool error. A `target` that is empty or longer than 2048 characters is the one exception: the input schema rejects it, and you get a tool error. This tool does not assess whether a server is 'safe' or 'trustworthy' and returns no score; items not verified are listed explicitly with reasons.
check_mcps and get_mcp_report also give probed_endpoint, the URL the reported run probed, with probed_endpoint_from saying whether it was read from the signed payload or from our unsigned target record, and endpoint_source saying how the target's endpoint is set now; get_mcp_history lists endpoint changes from the last 90 days.
What an answer looks like
You ask“What did MCP Checkup observe on the latest run of mcpcheckup/mcp?”
Your agent callsget_mcp_report returns every check; only a few are shown here.
Limits
About 20 requests per minute per IP address, counted per Cloudflare location. A 429 response carries Retry-After: 60 seconds.
No authentication and no paid tier for this endpoint.
What it will never tell you
There is no single number or verdict on whether to use a server. Every check lands in one of four states, and a check that did not run is never reported as one that passed.
Machine-readable: /llms.txt · /.well-known/mcp/server-card.json