MCP HeartbeatTHE MCP OBSERVATORY
Public workspace

Explore

Evidence for your next connection.

Independent measurements of remote MCP servers. Every observation has a timestamp.

Read-only probes

MCP server · Code & DevOps

MCP Yellow Pages

Find and evaluate MCP servers: search the independent MCP Yellow Pages directory.

Checks passed
11 / 22

3 failed · 8 not measured

Median response
639 ms

Median of successful probes over 7 days

30-day uptime
Not measured

Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.

Discovered tools
6

Tool definitions returned by this server

Independent monitoring

Health & checks

Status history

Responded

The server completed its last measured handshake. This is an observation, not a guarantee.

Last checked
Check summary by test group
Test areaPassedFailedUnmeasured
ConnectionCan a client connect and discover tools?
410
Reliability & speedDoes it respond consistently and quickly?
004
Access & authenticationWhat is required to use this server?
102
Tool qualityAre the tool definitions usable by an agent?
400
Publisher identityCan the publisher be traced to its source?
222

Unmeasured means there is not enough evidence to decide. How these checks work

Inspect individual checks 22 recorded

Core

  • Pass
    Reachable

    Latest probe returned HTTP 200 in 639 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-03-26, serverInfo.name mcpyp.

  • Pass
    Lists tools

    tools/list returned 6 tools.

  • Fail
    Current protocol

    Negotiated 2025-03-26. The bar is 2025-06-18 or newer.

  • Pass
    HTTPS

    The endpoint URL is https.

Performance

  • Not measured
    Fast (p50)

    Median latency 639 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 639 ms over 1 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.

  • Not measured
    Reliable (uptime)

    1 of 1 attempts returned a tool list in 30 days (100%). The bar is 99%. Need at least 30 samples.

  • Not measured
    Stable tool list

    Fewer than two successful probes in 30 days, so tool-list stability is not measured.

Access

  • Pass
    Open access

    tools/list succeeded with no credential, and the record declares none.

  • Not measured
    Standard auth

    Auth is not required, so the OAuth metadata check does not apply.

  • Not measured
    Free tier cited

    No publisher quote has been checked.

Tools

  • Pass
    Tools described

    Every tool description is at least 20 characters.

  • Pass
    Valid input schemas

    Every inputSchema is a JSON Schema object.

  • Pass
    Parameters documented

    18 of 18 parameters have a description (100%). The bar is 80%.

  • Pass
    Safety hints

    Every tool sets readOnlyHint or destructiveHint.

Publisher

  • Pass
    Verified namespace

    Listed in the Official MCP Registry.

  • Not measured
    Website matches publisher

    This namespace is not a reverse domain, so the website comparison does not apply.

  • Fail
    Source repo linked

    No repository URL is on file.

  • Fail
    Repo owner matches

    The GitHub repository owner does not match the namespace login.

  • Pass
    Recently updated

    Updated 2026-11-04T22:14:57.57009Z, within 180 days.

  • Not measured
    Open-source licence

    No GitHub repository to ask about a licence.

Start using MCP Yellow Pages

Connect to this server

Choose your client, copy the configuration, then enable the server in your client’s MCP settings.

Run this command in your terminal, then restart Claude Code.

Claude Code

claude mcp add --transport http mcp-yellow-pages https://api.mcpyp.com/mcp

Capabilities

Tools 6

explore

Step 1 of the MCPYP selection funnel (broad search). Returns a broad pool of candidate servers for a task (default 20, paged with offset) plus the total match count. Use this first to see the shape of the pool, then narrow with refine. Pass the same journey_id across explore, refine, and pick so the journey is logged as one funnel. Optional no_key_required narrows the pool to servers usable without a publisher API key. Most callers can skip the funnel and use find_mcp + get_mcp instead.

Discovered
find_mcp

Search the MCP Yellow Pages measured catalog — the entry point for finding an MCP server. Give a plain task description ('send email', 'stock prices', 'github issues') and get servers ranked by content match, then by independently measured quality (liveness, deep-test results, tool counts). Every result was actually probed by MCPYP. Usual flow: find_mcp to discover candidates, then get_mcp to inspect one, then get_config to connect. requires_key tells you whether the server needs a publisher API key before use. Set no_key_required=true to return only servers verified usable without a publisher API key (a successful keyless call on record).

Discovered
get_config

Get a ready-to-paste client configuration for one MCP server: an mcpServers entry for your MCP client config, plus a docs link to the full 6-tool reference (https://mcpyp.com/#/find, For machines tab). If the server requires a publisher API key, the config contains a <YOUR_API_KEY> placeholder plus where to obtain the key; MCPYP never issues, stores, or brokers keys. Pass the same journey_id as the pick step so the funnel conversion is logged.

Discovered
get_mcp

Get the full measured profile of one MCP server: description, measured tool list with parameters, liveness and deep-test outcomes, key status, endpoint and region. Call after find_mcp, with the name or slug from a find_mcp result, to inspect a candidate before connecting. The profile also carries profile_url (the public evidence page). MCPYP never proxies calls — use get_config to connect to the server yourself.

Discovered
pick

Step 3 of the MCPYP selection funnel (final selection). Commits to exactly ONE server: either the top-ranked server for a further-improved query, or the named server from the refine step. Keep improving the query: each step's query should be sharper than the last, so the journey shows how the choice narrowed. After pick, call get_config to connect. This is the funnel's conversion point. Optional no_key_required constrains the query pick to servers usable without a publisher API key; it does not apply when a server is picked by name (an explicit choice is picked as-is).

Discovered
refine

Step 2 of the MCPYP selection funnel (refined search). Narrows a task to exactly 5 candidates. IMPORTANT: improve the query at each step - use what explore returned (candidate names, tool names, categories) to write a sharper, more specific query here than the explore query. Optionally constrain to servers that need no publisher key (no_key_required). Call after explore, then commit with pick.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected639 ms6