protogrid

Search / work.agentexchange.tooldrift/monitor

monitor

R0· no sign-in

Check if an MCP server tool changed or hides injection patterns before you trust it.

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

An agent can connect right now, no human step.Remote endpoint, no authentication, reachable on the last probe.
Quality79good
Trust79of 100
Uptime, 30 days94%
Latency p50137 ms

Connect

8 clients · secrets stay placeholders
{
  "mcpServers": {
    "monitor": {
      "type": "http",
      "url": "https://tooldrift.agentexchange.work/mcp"
    }
  }
}
claude mcp add --transport http monitor https://tooldrift.agentexchange.work/mcp
[mcp_servers.monitor]
url = "https://tooldrift.agentexchange.work/mcp"
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "monitor": {
      "type": "remote",
      "url": "https://tooldrift.agentexchange.work/mcp",
      "enabled": true
    }
  }
}
{
  "mcpServers": {
    "monitor": {
      "type": "http",
      "url": "https://tooldrift.agentexchange.work/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=monitor&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vdG9vbGRyaWZ0LmFnZW50ZXhjaGFuZ2Uud29yay9tY3AifQ%3D%3D"
}
{
  "servers": {
    "monitor": {
      "type": "http",
      "url": "https://tooldrift.agentexchange.work/mcp"
    }
  }
}
{
  "mcpServers": {
    "monitor": {
      "httpUrl": "https://tooldrift.agentexchange.work/mcp"
    }
  }
}
extensions:
  "monitor":
    enabled: true
    name: "monitor"
    type: streamable_http
    uri: "https://tooldrift.agentexchange.work/mcp"
    timeout: 300

Quality 79 / 100good

protocol75 · weight 25
  • warn
    protocol.modernnewest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
  • n/a
    protocol.statelessonly applies to 2026-07-28 servers
  • pass
    protocol.transportstreamable HTTP
  • n/a
    protocol.list_ttlonly applies to 2026-07-28 servers
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 hygiene71 · weight 30
  • pass
    tools.descriptionsevery tool has a description
  • pass
    tools.description_lengthdescriptions are concise
  • pass
    tools.schemasevery tool has an object input schema
  • fail
    tools.annotationsno tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
  • fail
    tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: check_mcp_server (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_drift_feed (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_findings (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
  • pass
    tools.token_costabout 256 tokens to load every tool
  • pass
    tools.api_dumptools are not a one-to-one API dump
stability100 · weight 15
  • pass
    stability.changesno tool changes in 30 days
  • pass
    stability.rug_pullno tool changed its meaning under the same name
dependenciesn/a · weight 15
  • n/a
    deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

3 tools, about 256 tokens to load them all · tool set f5b15e8ed635 · checked 2026-10-20 11:08 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

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 79 / 100

no-repository
provenance55
liveness98
freshness85
hygiene80

+dns-namespace +website +reachable +uptime-94% ~updated-68d-ago -no-repository

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://tooldrift.agentexchange.work/mcp streamable-httpnoneyes94%137 ms2025-06-182026-10-20

Tools (3)

check_mcp_serverCheck whether an MCP server's tools have changed since they were first recorded, and whether any tool description contains prompt-injection or data-exfiltration patterns. Call this BEFORE trusting a newly added or recently updated MCP server. Returns a verdict of clean or REVIEW_BEFORE_USE.
get_drift_feedList MCP tools across the public ecosystem whose definitions recently changed, newest first. Use to see whether a dependency mutated.
get_findingsList tools whose descriptions contain detected injection, concealment, or exfiltration patterns. Filter by severity: critical, high, medium, low.

Schemas: list_tools.

Similar MCP servers

Official server.json
{
  "name": "work.agentexchange.tooldrift/monitor",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://tooldrift.agentexchange.work/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.0.0",
  "websiteUrl": "https://tooldrift.agentexchange.work",
  "description": "Check if an MCP server tool changed or hides injection patterns before you trust it."
}