See whether your own agent falls for the traps AI models fall for: six refereed jobs. No account.
Connect Remote server
claude mcp add --transport http forge-gauntlet https://theagentforge.io/mcp/gauntlet
{
"mcpServers": {
"forge-gauntlet": {
"url": "https://theagentforge.io/mcp/gauntlet"
}
}
}
{
"servers": {
"forge-gauntlet": {
"type": "http",
"url": "https://theagentforge.io/mcp/gauntlet"
}
}
}
Settings > Connectors > Add custom connector
URL: https://theagentforge.io/mcp/gauntlet
Tools 3 found in our last check
gauntlet_startUse 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 ch…
gauntlet_actUse 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 th…
gauntlet_statusUse 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.
Details
| Endpoint | https://theagentforge.io/mcp/gauntlet (Streamable HTTP) |
| First published | 6 Nov 2026 |
| Last updated | 6 Nov 2026 |
| Registry name | io.theagentforge/forge-gauntlet |
More ai and media servers See all
Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.
