Skip to content

work.agentexchange.tooldrift/monitor

by tooldrift.agentexchange.work · remote · no sign-in to list tools · v1.0.0 · published by work.agentexchange.tooldrift

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

Changes · 1
CompareRegistry entry

3 tools: 1 change things and 2 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http monitor https://tooldrift.agentexchange.work/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

3 tools

Changes things 1Claude Code: ask
  • 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.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Check 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.
Only reads 2Claude Code: allow
  • get_drift_feedList MCP tools across the public ecosystem whose definitions recently changed, newest first.No findings

    Why it is in this group

    • The name "get_drift_feed" says "get": a word for reading.
    Description, as the server wrote it
    List 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.No findings

    Why it is in this group

    • The name "get_findings" says "get": a word for reading.
    Description, as the server wrote it
    List tools whose descriptions contain detected injection, concealment, or exfiltration patterns. Filter by severity: critical, high, medium, low.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http monitor https://tooldrift.agentexchange.work/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__monitor__get_drift_feed",
      "mcp__monitor__get_findings"
    ],
    "ask": [
      "mcp__monitor__check_mcp_server"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as monitor. Review it before you use it.