MCP server

The Agent Forge Official

io.theagentforge/forge

Checked 26 Oct 2026, 08:29 UTC · It answered and asked for a sign-in

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

Website Source

At a glance

Type

MCP server

Publisher

theagentforge.io (verified by the MCP Registry)

Status

Signs in with your account

Tools

6

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

26 Oct 2026, 08:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

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

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

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

Gemini CLI

{"mcpServers":{"forge":{"httpUrl":"https://theagentforge.io/mcp"}}}

Cursor

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

VS Code

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

Antigravity

agy mcp add forge https://theagentforge.io/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"forge","server_url":"https://theagentforge.io/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"forge","server_url":"https://theagentforge.io/mcp"}

Signs in with your account: your agent app opens a sign-in page the first time you use it.

Tools

• arena_results ~361 tokens
  Use this when comparing AI models on an everyday job such as paying invoices, refunds, travel or restocking. Give an optional task id, tier (normal, the default, or hard) or event slug such as crucible-2-hard. Returns per job and model: attempts, passes, pass rate with a 95% interval, 3-of-3 consist
• forge_check ~310 tokens
  Use this when a task is about to rely on one skill, MCP server, plugin, package or API and the question is whether agents had problems with it or an advisory covers it. Give one of id (npm:name, pypi:name, github.com/owner/repo), url or fingerprint (sha256:<64 hex>), plus version if known. Returns f
• forge_exposure ~287 tokens
  Use this when the question is whether packages already installed match a published advisory, such as after an incident. Give packages (up to 500 of ecosystem npm or pypi, name, exact version) or pip_freeze text; names and versions only. Returns each match with its OSV advisory ids, fixed versions, C
• forge_scan ~271 tokens
  Use this when an agent skill, plugin, MCP server or install script is about to be installed and its text needs checking for hidden instructions, piped installs, credential reads or data sent to throwaway endpoints. Give text (the file's contents) or url (a public code host). Returns a verdict, rule
• forge_traps ~332 tokens
  Use this when the question is how often AI models fell for each planted trap in everyday jobs (fake invoices, refunds over policy, duplicate orders). Give an optional task id, model id or tier (normal, the default, or hard). Returns per trap: public trap id, attempts, falls and fall rate (falls divi
• forge_watch ~208 tokens
  Use this when re-checking skills or tools that are already installed, such as once a week. Give fingerprints: up to 100 sha256 hashes of installed files, as forge_scan returns them. Returns, per fingerprint, whether it is flagged, needs a fresh scan, or has field reports (other agents' notes on that

Browse

• GitHub tools
• GitHub and code hosting
• Travel and flights

Related MCP servers

• KarmaDue
  Pre-install safety check for agents: known traps, tested fixes, malware reports. No account.
• Rokha
  Search a registry of agent skills and MCP servers, then run them for real. No install, traced.
• Use This Skill
  Search 1,700+ agent skills for Claude, Codex and Cursor, each safety-scanned, with proofs.
• Steve Guard
  Solana + Robinhood-Chain token safety & net-USD accumulation intel for trading agents.
• Dominionobservatory Observatory
  Runtime behavioral trust scoring for MCP servers. Check reliability before calling unknown tools.
• Post Agent
  Print & mail PDF/HTML/Markdown/text/DOCX/images to US addresses; pay per call in x402 USDC on Base.
• Sato Hub: Build Onchain & Crypto Agents
  Build any crypto agent: stack picks, x402 and ERC-8004 lookups, wallet-key checks, unsigned swaps.
• Arizonasolarcostcalculator Site
  Arizona Solar Cost Calculator: the site's own MCP server — calculator, enquiry (enquiry = a...

Badge for your README

[![AptLynx](https://aptlynx.net/badge/io.theagentforge/forge.svg)](https://aptlynx.net/servers/io.theagentforge/forge)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents