The Forge Gauntlet MCP server
io.theagentforge/forge-gauntlettheagentforge.iostreamable-httpv0.5.2Scanned
See whether your own agent falls for the traps AI models fall for: six refereed jobs. No account.
3 tools: 2 change things and 1 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
2 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the The Forge Gauntlet MCP server can do
The The Forge Gauntlet MCP server is published by theagentforge.io, a domain the MCP Registry verified. It has 3 tools. It can create or change data (2 tools: gauntlet_start and gauntlet_act), but cannot delete data. 1 tool only reads.
None of its tools reads private data, brings in text other people write, or sends data out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 20, 2026, version 0.5.2.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
3 tools
Changes things 2Claude Code: ask
gauntlet_actUse this during a Gauntlet run to call one sandbox tool in the current job.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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.
Annotations the server declares
- title: Act in the Forge Gauntlet
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
gauntlet_startUse this when the user wants their own agent tested on everyday jobs with planted traps, refereed from the end state.No findings
Why it is in this group
- The name "gauntlet_start" says "start": a word for a change.
Description, as the server wrote it 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).
Annotations the server declares
- title: Start the Forge Gauntlet
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
Only reads 1Show 1 read-only tool
gauntlet_statusUse this to see where a Gauntlet run stands.No findings
Why it is in this group
- The name "gauntlet_status" says "status": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- title: Gauntlet status
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 21, 2026, 19:22 UTC, unchanged since Nov 7, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 2
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://theagentforge.io/.well-known/oauth-protected-resource
- Authorization servers
- https://theagentforge.io
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- yes
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://theagentforge.io/mcp/gauntlet: tools/list returned 3 tools to an anonymous client, including gauntlet_start (write), gauntlet_act (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.5.2. Values in angle brackets are yours to fill in.
claude mcp add --transport http forge-gauntlet https://theagentforge.io/mcp/gauntletclaude mcp add --transport http forge-gauntlet https://theagentforge.io/mcp/gauntletRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__forge-gauntlet__gauntlet_status"
],
"ask": [
"mcp__forge-gauntlet__gauntlet_start",
"mcp__forge-gauntlet__gauntlet_act"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as forge-gauntlet. Review it before you use it.
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.theagentforge/forge-gauntlet/verify?hash=7f8e80ef693297bec7792e6f1ee215edb8a4bc0db6dda5e8e3d7341993c21598" | jq -e '.changed == false'Pinned hash 7f8e80ef6932, from Nov 20, 2026, 11:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.theagentforge/forge-gauntlet/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.theagentforge/forge-gauntlet)Source: MCP Registry · repository. Synced Nov 6, 2026, 10:18 UTC.
The Forge Gauntlet MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the The Forge Gauntlet MCP server safe?
- No scan can promise that. What its definitions show: 3 tools, 2 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the The Forge Gauntlet MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the The Forge Gauntlet MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the The Forge Gauntlet MCP server have?
- 3 tools: 2 write, 1 read. gauntlet_start, gauntlet_act and gauntlet_status.
Does the The Forge Gauntlet MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the The Forge Gauntlet MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the The Forge Gauntlet MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.