The Forge Gauntlet MCP Server

by theagentforge Your server? Claim it

answering

The Forge Gauntlet is answering right now. Last checked 13 min ago. It exposes 3 tools. Last commit 6 Nov 2026.

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

Uptime history 37 hours of history

37 hours agonow

100.0%

Uptime 24h

91 of 91 checks

Tools

read from the server

391 ms

Response time

average over 24h

Stars

last commit 6 Nov 2026

Nothing serious here today

Today is the operative word: we check The Forge Gauntlet every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 13 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

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

Settings → Connectors → Add custom connector, then paste this address

https://theagentforge.io/mcp/gauntlet

~/.codex/config.toml

[mcp_servers.forge-gauntlet]
url = "https://theagentforge.io/mcp/gauntlet"

.cursor/mcp.json

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

.vscode/mcp.json

{
  "servers": {
    "forge-gauntlet": {
      "type": "http",
      "url": "https://theagentforge.io/mcp/gauntlet"
    }
  }
}

Available tools 3

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

gauntlet

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.

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).

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.

Endpoints

URL	Transport	State	Latency	Checked
https://theagentforge.io/mcp/gauntlet	streamable-http	answering	828 ms	13 min ago

Alternatives to The Forge Gauntlet

same job, measured the same way

The Agent Forge

by theagentforge

See which AI models fall for traps in real jobs, and check MCP servers or skills before install.

6 tools answering

Overllm

by theadamdanielsson

Find the LLM/AI calls you didn't need — where plain code or a regex does the job. No model.

221 installs/wk local only

Authn8

by authn8

Shared 2FA for teams: let AI agents get TOTP codes for the accounts your Authn8 token can see.

579 installs/wk answering

fleet

by sinolion

Every machine you have, for your agent: free GPUs, jobs, served models, software, over SSH.

368 installs/wk local only

fleet

by lion-zhang

Every machine you have, for your agent: free GPUs, jobs, served models, software, over SSH.

local only

Orbilo

by orbilo

Check whether a website is ready for AI agents (UCP, WebMCP, Access) and monitor your own sites.

5 tools answering

Agent Access Door Check

by textforagents

Before your agent sets out, ask whether the site will let it in

5 tools answering

Yab, Yet Another Browser

by yetanotherbrowser

Your own signed-in Mac browser for any agent: open, read and act in tabs. Local and free.

291 installs/wk local only

The Forge Gauntlet — questions

Answers built from our own checks of this server.

What can The Forge Gauntlet do?

It exposes 3 tools, read directly from the server on our last check. Among them: gauntlet_act, gauntlet_start, gauntlet_status. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is The Forge Gauntlet working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 391 ms. The bar chart above shows every period we have measured.

How do I connect The Forge Gauntlet?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does The Forge Gauntlet need an API key?

No. The Forge Gauntlet completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 3 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is The Forge Gauntlet?

It answers our handshake in 391 ms on average, which is faster than 33% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.

Is The Forge Gauntlet open source?

The code is open source: it is published under the MIT licence and 0 stars on GitHub. The licence covers the code in the repository, not the hosted service at theagentforge.io, which runs on its operator's own terms.