# io.github.agentwares/mcp-liveness > Does an MCP server work for a stock client? By registry name or URL. Tool drift too. Free, no key. - name: io.github.agentwares/mcp-liveness - version: 0.3.0 - connection class: R0 (autonomous) - trust: 93/100 flags: duplicate-repo - quality: 81/100 (good) - owner: not claimed - descriptor: https://api.protogrid.dev/v1/servers/io.github.agentwares%2Fmcp-liveness - tools: https://api.protogrid.dev/v1/servers/io.github.agentwares%2Fmcp-liveness/tools **An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe. ## Connection (mcpServers) ```json { "mcpServers": { "mcp-liveness": { "type": "http", "url": "https://agentwares-mcp-liveness.vercel.app/mcp" } } } ``` ## Trust - hygiene: 80 - liveness: 100 - freshness: 100 - provenance: 90 - drivers: +repository +namespace-matches-repo +website +reachable +uptime-100% +updated-14d-ago -duplicate-repo(7 names) - Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. ## Quality 81/100 (good) ### protocol: 100 (weight 25) - pass `protocol.modern`: supports 2026-07-28 (server/discover) - pass `protocol.stateless`: answers without a session - pass `protocol.transport`: streamable HTTP - pass `protocol.list_ttl`: tool list is cacheable (ttlMs 300000) ### authorization: n/a (weight 15) - n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth - n/a `auth.secret_in_url`: no templated URL ### tool hygiene: 93 (weight 30) - pass `tools.descriptions`: every tool has a description - warn `tools.description_length`: 3 tools have descriptions over 1,024 characters, which crowds the context - pass `tools.schemas`: every tool has an object input schema - pass `tools.annotations`: 5 of 5 tools declare readOnlyHint or destructiveHint - pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint - pass `tools.token_cost`: about 2,150 tokens to load every tool - pass `tools.api_dump`: tools are not a one-to-one API dump ### stability: 25 (weight 15) - warn `stability.changes`: 10 tool changes in 30 days - fail `stability.rug_pull`: 1 tools kept their name but changed most of their description in 30 days; review before trusting them ### dependencies: n/a (weight 15) - n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package - tools: 5, about 2,150 tokens to load them all - tool set hash: c6425a805f3dd8d9036af965e861cbee - tools last changed: 2026-10-09T07:32:42.384Z - badge: [![protogrid quality](https://protogrid.dev/badge/io.github.agentwares/mcp-liveness.svg)](https://protogrid.dev/servers/io.github.agentwares/mcp-liveness) - Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. ### Tool changes - 2026-10-09 `mcp_liveness_check_apps` added - Checks a remote MCP server's MCP Apps UI (SEP-1865 `ui://` resources) from outside, with no credential and without calling any tool, and returns the first step that stops the view rendering, whose it is (`server`, or `host` for a known host bug with its issue URL), the fix, and the source (the spec, or the host's published page, with the date read). It opens the server as an MCP Apps host would, then reads tools/list, resources/list and resources/read: each tool's link to its view (_meta.ui.resourceUri, or ChatGPT's openai/outputTemplate alias), the view's MIME type (text/html;profile=mcp-app) and HTML, what the HTML loads against the CSP a host builds from _meta.ui.csp, whether it sends ui/initialize, ui.domain for Claude and for ChatGPT, and what OpenAI's directory review checks (explicit tool annotations, descriptions, a public https endpoint, the domain-verification file). Verdicts per host — `spec`, `claude`, `chatgpt`, `chatgpt-directory` — are judged from each host's published pages; no host is run. Use it when a user says an MCP App or ChatGPT app shows a blank or invisible frame, 'Resource not found: ui://', 'Invalid ui.domain format', or a submission error such as annotations_required. `verdict` is ok, at_risk, broken, no_ui, needs_sign_in or unreachable. The URL must be public https; checks are limited to 30 a minute per caller. - 2026-10-09 `mcp_liveness_check_auth` added - Walks a remote MCP server's OAuth sign-in chain from outside, with no credential and no client registration, and returns the first step that breaks, whose it is (`server`, `identity_provider`, or `client` for a known client bug, with its issue URL), the fix, and the spec section that requires it. Steps, in order: one unauthenticated request (it must answer 401 with a WWW-Authenticate challenge); RFC 9728 protected-resource metadata; RFC 8414 or OpenID Connect discovery at the locations the 2026-07-28 MCP spec lists, with the issuer and PKCE S256 checked; and how a client gets a client ID (client ID metadata documents, dynamic registration, or a pasted ID). Then a verdict per client — claude.ai, Claude Code, ChatGPT, VS Code, Cursor — emulated from each client's published requirements and known issues; no client is run. Use it when a user says a connector shows an error such as 'Authorization with the MCP server failed' or 'Dynamic Client Registration not supported', or before publishing a server that needs sign-in. `verdict` is ok, at_risk, broken, no_auth (it asked for no credential) or unreachable. The URL must be public https; checks are limited to 30 a minute per caller. - 2026-10-09 `mcp_liveness_drift` changed (annotations) - 2026-10-09 `mcp_liveness_explain_outcomes` changed (annotations) - 2026-10-09 `mcp_liveness_check` changed (annotations) - 2026-10-08 `mcp_liveness_check` changed (description) - before: Makes one `initialize` call to an MCP server's endpoint with no credential and reports what a stock client gets. The server is named either by its exact official-registry `name`, or by its endpoint `url` when it is not in the registry or is listed under another name; exactly one of the two is accepted. Outcomes: `usable` (it connected and negotiated a protocol version), `needs_credential` (401 or 403 — by name, the answer also says whether a credential can be obtained in-band or whether a person has to create one), `charged` (402, access is for sale), `unreachable` (not an MCP server there: wrong URL, dead host, or a 200 that is not JSON-RPC), and, for a name only, `local_only` (no remote endpoint; it must be spawned as a process) and `not_listed` (no server with that exact name; its endpoint can still be checked by `url`). A `url` must be public https: private, loopback, link-local, multicast and cloud-metadata addresses are refused, redirects are re-checked, and URL checks are limited to 30 a minute per caller. Useful before relying on a server: roughly two in five remote registry listings do not answer a stock client. - after: Makes one handshake with an MCP server's endpoint — `server/discover` at protocol revision 2026-07-28, then `initialize` for a server on the older revision — with no credential, and reports what a stock client gets. The server is named either by its exact official-registry `name`, or by its endpoint `url` when it is not in the registry or is listed under another name; exactly one of the two is accepted. Outcomes: `usable` (it connected and negotiated a protocol version), `needs_credential` (401 or 403 — by name, the answer also says whether a credential can be obtained in-band or whether a person has to create one), `charged` (402, access is for sale), `unreachable` (not an MCP server there: wrong URL, dead host, or a 200 that is not JSON-RPC), and, for a name only, `local_only` (no remote endpoint; it must be spawned as a process) and `not_listed` (no server with that exact name; its endpoint can still be checked by `url`). A `url` must be public https: private, loopback, link-local, multicast and cloud-metadata addresses are refused, redirects are re-checked, and URL checks are limited to 30 a minute per caller. Useful before relying on a server: roughly two in five remote registry listings do not answer a stock client. - 2026-10-07 `mcp_liveness_drift` changed (description, annotations) - before: Given a server's exact name in the official MCP registry, report which of its tools were added, removed, or had their description, input schema or output schema change between the month you name and the latest monthly snapshot. Call this when a server worked before and is behaving differently now, when a prompt or an integration written against its tools has started failing, or before trusting a tool description you cached. A liveness check says it answers today; this says whether it is still the same server your code was written against. The answer names the changed tools and the kind of change. It does not diff the schemas themselves: the snapshots keep content hashes, not bodies, so `detail` hands back the release-asset location of both full months for a caller that needs the exact diff. A month with no snapshot for that server gets an error naming the months that do have one, never an empty diff that would read as `nothing changed`. - after: Given a server's exact name in the official MCP registry, reports which of its tools were added, removed, or had their description, input schema or output schema change between a named month and the latest monthly snapshot. Useful when a server that worked before behaves differently now, when a prompt or an integration written against its tools has started failing, or before relying on a cached tool description. A liveness check says a server answers today; this says whether it is still the same server that code was written against. The answer names the changed tools and the kind of change. It does not diff the schemas themselves: the snapshots keep content hashes, not bodies, so `detail` hands back the release-asset location of both full months for a caller that needs the exact diff. A month with no snapshot for that server gets an error naming the months that do have one, never an empty diff that would read as `nothing changed`. - 2026-10-07 `mcp_liveness_explain_outcomes` changed (description, annotations) **meaning changed** - before: Return the six outcomes this server can report, what each means for an agent choosing a server from the registry, and what to do next for each. Makes no request and costs nothing; call it once to interpret mcp_liveness_check results. - after: Returns the six outcomes this server can report — usable, needs_credential, charged, unreachable, local_only and not_listed — what each means for an agent choosing a server from the registry, and the usual next move for each. A static reference: it makes no network request and its answer never changes between calls. - 2026-10-07 `mcp_liveness_check` changed (description, annotations) - before: Make one `initialize` call to an MCP server's endpoint with no credential and report what a stock client gets. Name the server by its exact official-registry `name`, or by its endpoint `url` when it is not in the registry or is listed under another name — pass exactly one of the two. Outcomes: `usable` (it connected and negotiated a protocol version), `needs_credential` (401 or 403 — by name, the answer then says whether a credential can be obtained in-band or whether a person has to create one), `charged` (402, access is for sale), `unreachable` (not an MCP server there: wrong URL, dead host, or a 200 that is not JSON-RPC), and, for a name only, `local_only` (no remote endpoint; it must be spawned as a process) and `not_listed` (no server with that exact name — pass `url` instead). A `url` must be public https: private, loopback, link-local, multicast and cloud-metadata addresses are refused, redirects are re-checked, and URL checks are limited to 30 a minute per caller. Call this before spending a call on a server; roughly two in five remote registry listings do not answer a stock client. - after: Makes one `initialize` call to an MCP server's endpoint with no credential and reports what a stock client gets. The server is named either by its exact official-registry `name`, or by its endpoint `url` when it is not in the registry or is listed under another name; exactly one of the two is accepted. Outcomes: `usable` (it connected and negotiated a protocol version), `needs_credential` (401 or 403 — by name, the answer also says whether a credential can be obtained in-band or whether a person has to create one), `charged` (402, access is for sale), `unreachable` (not an MCP server there: wrong URL, dead host, or a 200 that is not JSON-RPC), and, for a name only, `local_only` (no remote endpoint; it must be spawned as a process) and `not_listed` (no server with that exact name; its endpoint can still be checked by `url`). A `url` must be public https: private, loopback, link-local, multicast and cloud-metadata addresses are refused, redirects are re-checked, and URL checks are limited to 30 a minute per caller. Useful before relying on a server: roughly two in five remote registry listings do not answer a stock client. - 2026-10-07 `mcp_liveness_check` changed (description, inputSchema) - before: Given a server's exact name in the official MCP registry, make one `initialize` call to the endpoint its listing names and report what a client with no credential gets. Outcomes: `usable` (it connected and negotiated a protocol version), `needs_credential` (401 or 403 — the answer then says whether a credential can be obtained in-band or whether a person has to create one), `charged` (402, access is for sale), `unreachable` (the listed endpoint is not an MCP server: wrong URL, dead host, or a 200 that is not JSON-RPC), `local_only` (no remote endpoint; it must be spawned as a process), and `not_listed` (no server with that exact name). Call this before spending a call on a server you found in the catalogue. Roughly two in five remote listings do not answer a stock client. - after: Make one `initialize` call to an MCP server's endpoint with no credential and report what a stock client gets. Name the server by its exact official-registry `name`, or by its endpoint `url` when it is not in the registry or is listed under another name — pass exactly one of the two. Outcomes: `usable` (it connected and negotiated a protocol version), `needs_credential` (401 or 403 — by name, the answer then says whether a credential can be obtained in-band or whether a person has to create one), `charged` (402, access is for sale), `unreachable` (not an MCP server there: wrong URL, dead host, or a 200 that is not JSON-RPC), and, for a name only, `local_only` (no remote endpoint; it must be spawned as a process) and `not_listed` (no server with that exact name — pass `url` instead). A `url` must be public https: private, loopback, link-local, multicast and cloud-metadata addresses are refused, redirects are re-checked, and URL checks are limited to 30 a minute per caller. Call this before spending a call on a server; roughly two in five remote registry listings do not answer a stock client. Full history: https://api.protogrid.dev/v1/servers/io.github.agentwares%2Fmcp-liveness/changes ## Remotes - https://agentwares-mcp-liveness.vercel.app/mcp (streamable-http, auth none, reachable true, uptime30d 1) ## Packages _none_ ## Tools (5) - `mcp_liveness_check`: Makes one handshake with an MCP server's endpoint — `server/discover` at protocol revision 2026-07-28, then `initialize` for a server on the older revision — with no credential, and reports what a stock client gets. The server is named either by its exact official-registry `name`, or by its endpoint `url` when it is not in the registry or is listed under another name; exactly one of the two is accepted. Outcomes: `usable` (it connected and negotiated a protocol version), `needs_credential` (401 or 403 — by name, the answer also says whether a credential can be obtained in-band or whether a person has to create one), `charged` (402, access is for sale), `unreachable` (not an MCP server there: wrong URL, dead host, or a 200 that is not JSON-RPC), and, for a name only, `local_only` (no remote endpoint; it must be spawned as a process) and `not_listed` (no server with that exact name; its endpoint can still be checked by `url`). A `url` must be public https: private, loopback, link-local, multicast and cloud-metadata addresses are refused, redirects are re-checked, and URL checks are limited to 30 a minute per caller. Useful before relying on a server: roughly two in five remote registry listings do not answer a stock client. - `mcp_liveness_check_apps`: Checks a remote MCP server's MCP Apps UI (SEP-1865 `ui://` resources) from outside, with no credential and without calling any tool, and returns the first step that stops the view rendering, whose it is (`server`, or `host` for a known host bug with its issue URL), the fix, and the source (the spec, or the host's published page, with the date read). It opens the server as an MCP Apps host would, then reads tools/list, resources/list and resources/read: each tool's link to its view (_meta.ui.resourceUri, or ChatGPT's openai/outputTemplate alias), the view's MIME type (text/html;profile=mcp-app) and HTML, what the HTML loads against the CSP a host builds from _meta.ui.csp, whether it sends ui/initialize, ui.domain for Claude and for ChatGPT, and what OpenAI's directory review checks (explicit tool annotations, descriptions, a public https endpoint, the domain-verification file). Verdicts per host — `spec`, `claude`, `chatgpt`, `chatgpt-directory` — are judged from each host's published pages; no host is run. Use it when a user says an MCP App or ChatGPT app shows a blank or invisible frame, 'Resource not found: ui://', 'Invalid ui.domain format', or a submission error such as annotations_required. `verdict` is ok, at_risk, broken, no_ui, needs_sign_in or unreachable. The URL must be public https; checks are limited to 30 a minute per caller. - `mcp_liveness_check_auth`: Walks a remote MCP server's OAuth sign-in chain from outside, with no credential and no client registration, and returns the first step that breaks, whose it is (`server`, `identity_provider`, or `client` for a known client bug, with its issue URL), the fix, and the spec section that requires it. Steps, in order: one unauthenticated request (it must answer 401 with a WWW-Authenticate challenge); RFC 9728 protected-resource metadata; RFC 8414 or OpenID Connect discovery at the locations the 2026-07-28 MCP spec lists, with the issuer and PKCE S256 checked; and how a client gets a client ID (client ID metadata documents, dynamic registration, or a pasted ID). Then a verdict per client — claude.ai, Claude Code, ChatGPT, VS Code, Cursor — emulated from each client's published requirements and known issues; no client is run. Use it when a user says a connector shows an error such as 'Authorization with the MCP server failed' or 'Dynamic Client Registration not supported', or before publishing a server that needs sign-in. `verdict` is ok, at_risk, broken, no_auth (it asked for no credential) or unreachable. The URL must be public https; checks are limited to 30 a minute per caller. - `mcp_liveness_drift`: Given a server's exact name in the official MCP registry, reports which of its tools were added, removed, or had their description, input schema or output schema change between a named month and the latest monthly snapshot. Useful when a server that worked before behaves differently now, when a prompt or an integration written against its tools has started failing, or before relying on a cached tool description. A liveness check says a server answers today; this says whether it is still the same server that code was written against. The answer names the changed tools and the kind of change. It does not diff the schemas themselves: the snapshots keep content hashes, not bodies, so `detail` hands back the release-asset location of both full months for a caller that needs the exact diff. A month with no snapshot for that server gets an error naming the months that do have one, never an empty diff that would read as `nothing changed`. - `mcp_liveness_explain_outcomes`: Returns the six outcomes this server can report — usable, needs_credential, charged, unreachable, local_only and not_listed — what each means for an agent choosing a server from the registry, and the usual next move for each. A static reference: it makes no network request and its answer never changes between calls.