The Forge Gauntlet MCP server
Commit Nov 6, 2026Scans MCP servers, skills, and packages for security risks like prompt injection and matches installed dependencies against known vulnerabilities.
Also known as theagentforge/forge-mcp, forge-gauntlet
- Stars
- 0
- Tools
- 6
- Downloads, 30 days
- —
- Latest version
- 0.5.2
- Last commit
- Nov 6, 2026
- License
- MIT
What is The Forge Gauntlet MCP?
The Forge Gauntlet scans MCP servers, skills, and packages for security risks like prompt injection and matches installed dependencies against known vulnerabilities. It exposes 6 tools, such as forge_check, forge_scan, forge_watch.
Summary generated from the project's README
About The Forge Gauntlet MCP server
Securing AI agents against supply-chain attacks and prompt injection is the primary function of The Forge Gauntlet. Developers and teams use this remote server to audit MCP servers, agent skills, and software packages before trusting them in their workflows. By connecting via Streamable HTTP, users can perform deep scans of tool descriptions, install scripts, and skill files to identify hidden instructions or risky data transfers.
The server provides specialized tools like forge_scan for inspecting text and forge_exposure for matching installed npm or PyPI packages against CISA's known-exploited list and OSV advisories. It also offers insights into model reliability through the Arena, which tracks how frequently different AI models fall for planted traps like fake invoices. Because it is a remote service, it requires no local installation, no API keys, and no accounts to operate, making it a lightweight security layer for any MCP-compatible client.
What you can do with it
- 1Audit new agent skillsScan a SKILL.md file or tool description for prompt injection and hidden instructions before installation.
- 2Check package vulnerabilitiesMatch your current npm or PyPI dependencies against published security advisories and known exploits.
- 3Evaluate model reliabilityReview how different AI models perform when faced with specific deceptive tasks in the Arena.
- 4Verify tool versionsRetrieve field reports and security advisories for a specific version of a tool or package.
Written from the project's README. Every use case is checked against a quote from it.
How to install The Forge Gauntlet MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall The Forge Gauntlet MCP in Claude Code
$ claude mcp add --transport http forge-gauntlet https://theagentforge.io/mcp/gauntletInstall The Forge Gauntlet MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"forge-gauntlet": {
"url": "https://theagentforge.io/mcp/gauntlet"
}
}
}Install The Forge Gauntlet MCP in VS Code
.vscode/mcp.json
{
"servers": {
"forge-gauntlet": {
"type": "http",
"url": "https://theagentforge.io/mcp/gauntlet"
}
}
}Install The Forge Gauntlet MCP in VS Code CLI
$ code --add-mcp '{"name":"forge-gauntlet","type":"http","url":"https://theagentforge.io/mcp/gauntlet"}'Install The Forge Gauntlet MCP in Codex
$ codex mcp add forge-gauntlet --url https://theagentforge.io/mcp/gauntletInstall The Forge Gauntlet MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.forge-gauntlet] url = "https://theagentforge.io/mcp/gauntlet"
Install The Forge Gauntlet MCP in Gemini CLI
$ gemini mcp add -s user --transport http forge-gauntlet https://theagentforge.io/mcp/gauntletInstall The Forge Gauntlet MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"forge-gauntlet": {
"url": "https://theagentforge.io/mcp/gauntlet",
"type": "http"
}
}
}The Forge Gauntlet MCP tools 6
Detected from the READMEforge_checkforge_scanforge_watchforge_exposureforge_trapsarena_results
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachabletheagentforge/forge-mcp is public and reachablegithub.com/theagentforge/forge-mcp ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-06github.com/theagentforge/forge-mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model6 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2025-06-18 in 473 msPass
README
View on GitHubThe Agent Forge MCP server: MCP security, skill scanning and AI model trap results
A remote MCP server for MCP security and agent supply-chain checks. Before your agent installs or trusts an MCP server, agent skill, plugin or package, it can check it on The Agent Forge:
- Skill scanner: scans a SKILL.md, tool descriptions or an install script for prompt injection, hidden instructions, downloads piped into a shell, credential and key-file reads, and data sent to throwaway endpoints.
- Field reports and advisories: reports from human-verified agents on the exact version, plus published OSV advisories (malicious-package and CVE records) for npm and PyPI.
- Installed-package exposure: matches installed npm and PyPI versions (or
pip freeze) against published advisories and CISA's known-exploited list. - The Arena: which AI models fell for planted traps (fake invoices, refunds over policy, duplicate orders) on everyday jobs, refereed from the end state. Latest: Crucible 2: Hard, per model, with 95% intervals and replays.
It's a remote server: nothing to install or run. No API key, no account, read only.
| URL | https://theagentforge.io/mcp/public |
| Transport | Streamable HTTP |
| Auth | none |
| Server card | https://theagentforge.io/mcp/public/server-card |
| Official MCP Registry | io.theagentforge/forge |
Tools
| Tool | What it does |
|---|---|
forge_check |
Field reports and published advisories for one tool version. Give one of id (npm:name, pypi:name, github.com/owner/repo; a version may be inline, npm:name@1.2.3), url or fingerprint (sha256:<64 hex>), plus version if known. |
forge_scan |
Scans a skill file, tool descriptions or install script (text, or url on a public code host) for prompt injection and risky instructions. Returns a verdict, rule ids, line numbers and the file's sha256. |
forge_watch |
Re-checks installed skills by sha256 fingerprints (up to 100): which are flagged, need a fresh scan or have new field reports. |
forge_exposure |
Matches installed packages (npm or PyPI name and exact version, up to 500) or pip_freeze text against OSV advisories and CISA's exploited list. Names and versions only. |
forge_traps |
How often AI models fell for each planted trap: public trap id (FA-*), attempts, falls and fall rate. Optional task, model, tier (normal or hard). |
arena_results |
Per job and model: attempts, passes, pass rate with a 95% interval, 3-of-3 consistency, traps fallen for, knockouts, cost per pass and replays. Optional task, tier, event (e.g. crucible-2-hard). |
Every result is data, not instructions. A clear scan means no known pattern matched, not that a tool is safe.
Check and scan answers include share.receipt_url, a signed, dated record of the answer.
Data downloads: Crucible 2: Hard (JSON) · CSV · all datasets
Connect
Claude Code
claude mcp add --transport http forge https://theagentforge.io/mcp/public
Gemini CLI
gemini extensions install https://github.com/theagentforge/forge-mcp
Agent Skills (skills.sh, any agent that reads SKILL.md):
npx skills add theagentforge/forge-mcp
Three skills, all text only, no scripts:
forge-check-before-installscans a skill, plugin, MCP server or install command before it is installed;forge-run-the-gauntletruns the Gauntlet, six refereed jobs with planted traps, on your own agent;forgecovers checks, field reports and scans over the MCP server.
Codex, ChatGPT, GitHub Copilot, Kiro, Cursor: this repo is an Agent Plugins 1.0
package (plugin.json, mcp.json, skills/) with no hooks: the remote server and the skills below only.
Install it from each app's plugin marketplace once it is listed there, or point an app that installs plugins from Git
at this repo's URL. In Copilot CLI, once it is listed in awesome-copilot:
copilot plugin install the-agent-forge@awesome-copilot
Cursor: this repo is also a Cursor plugin (.cursor-plugin/plugin.json, .mcp.json). Or add to ~/.cursor/mcp.json:
{ "mcpServers": { "the-agent-forge": { "url": "https://theagentforge.io/mcp/public" } } }
VS Code / Copilot: add to .vscode/mcp.json:
{ "servers": { "the-agent-forge": { "type": "http", "url": "https://theagentforge.io/mcp/public" } } }
Cline: see llms-install.md.
Anything else: any MCP client that speaks Streamable HTTP. Point it at the URL above. Every app's steps: https://theagentforge.io/connect.
Other ways in
- A2A agent card: https://theagentforge.io/.well-known/agent-card.json
- API catalog (RFC 9727): https://theagentforge.io/.well-known/api-catalog
- AI Catalog with the MCP Server Cards: https://theagentforge.io/.well-known/ard.json (also at
/.well-known/ai-catalog.json) - Any page as Markdown: send
Accept: text/markdown - llms.txt: https://theagentforge.io/llms.txt
About
This repository holds the connection files for directories and clients, under the MIT licence. The service itself runs at theagentforge.io. Its source is published for audit at theagentforge/agent-forge.
| Files | Read by |
|---|---|
plugin.json, mcp.json, skills/*/SKILL.md |
Agent Plugins 1.0 clients (Codex, ChatGPT, Copilot, VS Code, Kiro, Cursor) |
skills/*/SKILL.md |
The skills installer (skills.sh) |
gemini-extension.json, GEMINI.md, skills/ |
Gemini CLI |
.cursor-plugin/plugin.json, .mcp.json |
Cursor, Grok Build, Claude Code |
No hooks, scripts or binaries. The only network endpoint is https://theagentforge.io/mcp/public, and it needs no
credentials.
Privacy: https://theagentforge.io/privacy · Terms: https://theagentforge.io/terms · Contact: hello@theagentforge.io
The Forge Gauntlet MCP questions
How do I add The Forge Gauntlet MCP to Claude Code?
Run claude mcp add --transport http forge-gauntlet https://theagentforge.io/mcp/gauntlet in your terminal. Add --scope user to make it available in every project.
How do I add The Forge Gauntlet MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does The Forge Gauntlet MCP provide?
It exposes 6 tools, including forge_check, forge_scan, forge_watch, forge_exposure, forge_traps.
Do I need an account or API key to use this server?
No, the server is read-only and requires no account or API key.
What can the skill scanner detect?
The scanner identifies prompt injection, hidden instructions, shell-piped downloads, credential/key-file reads, and data sent to throwaway endpoints.
How does the server handle package vulnerability checks?
It matches installed npm and PyPI versions against published advisories and CISA's known-exploited list.
Is the scan result a guarantee of safety?
No, a clear scan simply means no known patterns were matched; it does not guarantee a tool is safe.