protogrid

Search / io.github.Carmel-Labs-Inc/mcp-index

AgentStatus MCP Index

R0· no sign-in

Live public MCP Index. Search, recommend, and call healthy MCP servers.

v1.0.0 · active · repository · descriptor JSON · versions

An agent can connect right now, no human step.Remote endpoint, no authentication, reachable on the last probe.
Quality79good
Trust94of 100
Uptime, 30 days100%
Latency p50479 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "mcp-index": {
      "type": "http",
      "url": "https://index.mcp.agentstatus.dev/mcp"
    }
  }
}
claude mcp add --transport http mcp-index https://index.mcp.agentstatus.dev/mcp
[mcp_servers.mcp-index]
url = "https://index.mcp.agentstatus.dev/mcp"
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mcp-index": {
      "type": "remote",
      "url": "https://index.mcp.agentstatus.dev/mcp",
      "enabled": true
    }
  }
}
{
  "mcpServers": {
    "mcp-index": {
      "type": "http",
      "url": "https://index.mcp.agentstatus.dev/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=mcp-index&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vaW5kZXgubWNwLmFnZW50c3RhdHVzLmRldi9tY3AifQ%3D%3D"
}
{
  "servers": {
    "mcp-index": {
      "type": "http",
      "url": "https://index.mcp.agentstatus.dev/mcp"
    }
  }
}
{
  "mcpServers": {
    "mcp-index": {
      "httpUrl": "https://index.mcp.agentstatus.dev/mcp"
    }
  }
}
extensions:
  "mcp-index":
    enabled: true
    name: "mcp-index"
    type: streamable_http
    uri: "https://index.mcp.agentstatus.dev/mcp"
    timeout: 300

Quality 79 / 100good

protocol88 · weight 25
  • pass
    protocol.modernsupports 2026-07-28 (server/discover)
  • pass
    protocol.statelessanswers without a session
  • pass
    protocol.transportstreamable HTTP
  • warn
    protocol.list_ttltools/list carries no ttlMs, so clients re-fetch it
authorizationn/a · weight 15
  • n/a
    auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
  • n/a
    auth.secret_in_urlno templated URL
tool hygiene88 · weight 30
  • pass
    tools.descriptionsevery tool has a description
  • pass
    tools.description_lengthdescriptions are concise
  • pass
    tools.schemasevery tool has an object input schema
  • pass
    tools.annotations8 of 9 tools declare readOnlyHint or destructiveHint
  • fail
    tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: search_records (idempotentHint); compare_records (idempotentHint); list_sections (idempotentHint); …
  • pass
    tools.token_costabout 1,601 tokens to load every tool
  • pass
    tools.api_dumptools are not a one-to-one API dump
  • pass
    tools.hidden_textno hidden text in tool names, descriptions, schemas or annotations
stability50 · weight 15
  • warn
    stability.changes17 tool changes in 30 days
  • fail
    stability.rug_pull1 tools kept their name but changed most of their description in 30 days; review before trusting them
  • pass
    stability.new_linksno tool change named a new site
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

9 tools, about 1,601 tokens to load them all · tool set 713232189195 · tools last changed 2026-11-11 · checked 2026-11-14 07:03 UTC

Tool changes

  • send_feedbackadded

    Tell the developer this result was wrong or confusing. Call this after a tool, not instead of the tool.

  • finish_workchangedinput schema
  • start_workchangedinput schema
  • call_indexed_toolchangedinput schema
  • list_sectionschangedinput schema
  • compare_recordschangedinput schema
  • recommend_recordschangedinput schema
  • get_recordchangedinput schema
  • search_recordschangedinput schema
  • finish_workadded

    Mark a started job finished or failed and post work.finished to subscribers. Call this when the work is actually done.

Showing the latest 10. Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 94 / 100

provenance80
liveness100
freshness100
hygiene100

+repository +namespace-matches-repo +reachable +uptime-100% +updated-14d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remoteauthreachableuptime 30dp50protocollast ok
https://index.mcp.agentstatus.dev/mcp streamable-httpnoneyes100%479 ms2026-07-28, 2025-11-25, 2025-06-18, 2025-03-26, 2024-11-052026-11-14

Tools (9)

call_indexed_toolRun a tool on a public MCP server from the full AgentStatus Index. This connection does not list those servers. Call search_records or recommend_records first, then pass that slug and tool. The call is sent to that server and its result is returned here.
compare_recordsread-onlyCompare two to five directory items by id, slug, or exact name. Returns stored details and the fields that differ.
finish_workMark a started job finished or failed and post work.finished to subscribers. Call this when the work is actually done.
get_recordread-onlyLook up one directory item by id, slug, or exact name.
list_sectionsread-onlyShow the sections in MCP for AgentStatus MCP Index.
recommend_recordsread-onlyReturn public MCP servers from the full Index for a need. Each match includes a slug and tool names. This tool only reads the Index.
search_recordsread-onlySearch the full public MCP Index. The tools on this connection are only the Index, not the catalog. Pass the job as query. Optional host is cursor, copilot, or vscode. Each match includes a slug and tool names. Run one with call_indexed_tool.
send_feedbackTell the developer this result was wrong or confusing. Call this after a tool, not instead of the tool.
start_workStart work that finishes later. This call returns immediately with a job id. Subscribers hear work.finished when finish_work runs.

Schemas: list_tools.

Similar MCP servers

Official server.json
{
  "name": "io.github.Carmel-Labs-Inc/mcp-index",
  "title": "AgentStatus MCP Index",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://index.mcp.agentstatus.dev/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.0.0",
  "repository": {
    "url": "https://github.com/Carmel-Labs-Inc/agentstatus-mcp-index",
    "source": "github"
  },
  "description": "Live public MCP Index. Search, recommend, and call healthy MCP servers."
}