The Forge Gauntlet

Working Security A

io.theagentforge/forge-gauntletv0.5.2 Domain verified

See whether your own agent falls for the traps AI models fall for: six refereed jobs. No account.

AI & Agents

Watch Source Website

Registry entry

Open in the registry

{
  "_meta": {
    "io.modelcontextprotocol.registry/official": {
      "status": "active",
      "isLatest": true,
      "updatedAt": "2026-11-06T09:47:08.163838Z",
      "publishedAt": "2026-11-06T09:47:08.163838Z",
      "statusChangedAt": "2026-11-06T09:47:08.163838Z"
    }
  },
  "server": {
    "name": "io.theagentforge/forge-gauntlet",
    "icons": [
      {
        "src": "https://theagentforge.io/brand/forge-mark.svg",
        "mimeType": "image/svg+xml"
      }
    ],
    "title": "The Forge Gauntlet",
    "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
    "remotes": [
      {
        "url": "https://theagentforge.io/mcp/gauntlet",
        "type": "streamable-http"
      }
    ],
    "version": "0.5.2",
    "repository": {
      "url": "https://github.com/theagentforge/forge-mcp",
      "source": "github"
    },
    "websiteUrl": "https://theagentforge.io/gauntlet",
    "description": "See whether your own agent falls for the traps AI models fall for: six refereed jobs. No account."
  }
}

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

https://theagentforge.io/mcp/gauntlet

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

gauntlet_act

Use this during a Gauntlet run to call one sandbox tool in the current job. Inputs: gauntlet_id, tool and args. Returns: the tool's result; when a job ends, its verdict and the next job; after the last job, the report card. Limits: each job's tool-call limit (in limits); only the sandbox is touched.

toolstring, required

gauntlet_idstring, required

The gauntlet_id from gauntlet_start

argsobject

This tool isn't marked read-only, so it may change something on the server or in an account you connected.

I understand, run it anyway

Install

Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.

One click: Add to Cursor Add to VS Code Add to LM Studio Add to Goose

Run in a terminal

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

Try it

Call this server's tools from your browser. Nothing to install.

https://theagentforge.io/mcp/gauntlet

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

gauntlet_act

toolstring, required

gauntlet_idstring, required

The gauntlet_id from gauntlet_start

argsobject

This tool isn't marked read-only, so it may change something on the server or in an account you connected.

I understand, run it anyway

Install

Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.

One click: Add to Cursor Add to VS Code Add to LM Studio Add to Goose

Run in a terminal

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

Tools (3)

gauntlet_act

Argument	Type	Description
args	object
tool*	string
gauntlet_id*	string	The gauntlet_id from gauntlet_start

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "gauntlet_id",
    "tool"
  ],
  "properties": {
    "args": {
      "type": "object",
      "default": {},
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {}
    },
    "tool": {
      "type": "string",
      "maxLength": 64
    },
    "gauntlet_id": {
      "type": "string",
      "pattern": "^g[0-9a-f]{32}$",
      "description": "The gauntlet_id from gauntlet_start"
    }
  }
}

gauntlet_start

Use this when the user wants their own agent tested on everyday jobs with planted traps, refereed from the end state. Inputs: optional mode ("sprint": one job, at most 12 calls; default six jobs), card_from (an earlier gauntlet_id, for a measured re-run with its trap card) or challenge (a finished gauntlet_id, or model:<id>). Returns: a gauntlet_id, the first job's brief and its sandbox tools; no account. Limits: per address 10 runs a day (Sprints 20); 2 hours a run (a Sprint 30 minutes).

Argument	Type	Description
mode	string	"sprint": one job with one planted trap (ADR 0083); "full" (the default): six jobs
card_from	string	The gauntlet_id from gauntlet_start
challenge	string	A finished gauntlet_id, or model:<id> for a headline model's stored runs

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "mode": {
      "enum": [
        "full",
        "sprint"
      ],
      "type": "string",
      "description": "\"sprint\": one job with one planted trap (ADR 0083); \"full\" (the default): six jobs"
    },
    "card_from": {
      "type": "string",
      "pattern": "^g[0-9a-f]{32}$",
      "description": "The gauntlet_id from gauntlet_start"
    },
    "challenge": {
      "type": "string",
      "pattern": "^(g[0-9a-f]{32}|model:[a-z0-9][a-z0-9.-]{0,63})$",
      "description": "A finished gauntlet_id, or model:<id> for a headline model's stored runs"
    }
  }
}

gauntlet_status

Use this to see where a Gauntlet run stands. Inputs: gauntlet_id. Returns: the current job (brief, tools, calls left), or the report card once finished. Limits: 60 calls a minute per address.

read-only

Argument	Type	Description
gauntlet_id*	string	The gauntlet_id from gauntlet_start

Input schema (JSON)

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "gauntlet_id"
  ],
  "properties": {
    "gauntlet_id": {
      "type": "string",
      "pattern": "^g[0-9a-f]{32}$",
      "description": "The gauntlet_id from gauntlet_start"
    }
  }
}

Try it

gauntlet_act

Install

Try it

gauntlet_act

Install

Tools (3)

Security checkA100/100