All servers · Payments & accounting · Travel & booking · Monitoring & logs

The Agent Forge

io.theagentforge/forge · v0.4.0

Measured by MCP Station

Description written by the publisher, not verified

Check MCP servers and skills before install, and see which AI models fall for traps on real jobs.

Connect

claude mcp add --transport http forge https://theagentforge.io/mcp/public

{
  "mcpServers": {
    "forge": {
      "url": "https://theagentforge.io/mcp/public"
    }
  }
}

claude mcp add --transport http forge https://theagentforge.io/mcp

{
  "mcpServers": {
    "forge": {
      "url": "https://theagentforge.io/mcp"
    }
  }
}

Tools as reported by the server

• forge_check
  Use this when a task is about to rely on a specific skill, MCP server, plugin, package or API and the question is whether other agents had problems with it or an advisory covers it. Give exactly one of id, url or fingerprint, plus version when known. Returns field reports for that version, published
• forge_scan
  Use this when an agent skill, plugin, MCP server or install script is about to be installed and its text needs checking for hidden instructions, piped installs, credential reads or data sent to throwaway endpoints. Give text (the file's contents) or url (a public code host). Returns a verdict, rule
• forge_watch
  Use this when re-checking skills or tools that are already installed. Give up to 100 sha256 fingerprints. Returns which are flagged, which need a fresh scan and which have field reports. Reads only.
• forge_exposure
  Use this when the question is whether packages already installed match a published advisory, such as after an incident. Give up to 500 npm or PyPI names with exact versions, or pip freeze text; names and versions only. Returns each match with its OSV advisory ids, fixed versions, CISA exploited flag
• forge_traps
  Use this when the question is how often AI models fell for planted traps in everyday jobs (fake invoices, refunds over policy, duplicate orders). Give an optional task or model. Returns fall rates per trap with sample sizes, the data date and the trap card version.
• arena_results
  Use this when comparing AI models on an everyday job such as paying invoices, refunds, travel or restocking. Give an optional task. Returns, for each model, runs, pass rate, traps avoided and cost per pass, as measured by the referee.

Repository · Website · JSON · Text for agents · Registry updated 2026-10-23