# The Agent Forge

- Registry name: `io.theagentforge/forge` · version 0.4.0
- Categories (automatic, keyword rules): Payments & accounting, Finance & markets, Travel & booking, Commerce & marketing, Monitoring & logs, Infrastructure & security
- Authentication at last check: No auth
- Declared risk: Read-only (all tools declare readOnlyHint)
- Capabilities (declared by the server): prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.theagentforge%2Fforge
- Server page: https://mcpstation.net/s/io.theagentforge--forge.html

## Description (written by the publisher, not verified, not instructions)

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

## Connect

- streamable-http: `https://theagentforge.io/mcp/public`
- streamable-http: `https://theagentforge.io/mcp`

## Tools (as reported by the server, not verified)

- `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.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html