The Agent Forge MCP server

• Registry nameio.theagentforge/forgeverified in the MCP registry

The registry name sits under theagentforge.io. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-27
• Tools6
• Server calls itselfthe-agent-forge-public
• Server version0.5.1
• Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 104 ms.

• Its tools do every use case we checked: scan a skill or MCP server for risky patterns before installing; compare how AI models handle planted traps in sample jobs.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP score90 of 100answers 100 · does the job 100 · definitions 100 · context 100 · use 0 · connects 100
• What an agent can do with it2 of 2 use cases
• Answered100% of days7 of 7 daily checks
• Median first answer485 ms
• Space in an agent's context≈ 1,651 tokensthe definitions of all its tools (6), which an agent carries on every turn
• Tool definitionsA · 100 of 100
• Typed results6 of 6 toolsdeclared outputSchema: results come typed, read once

• Every tool passes all six checks.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• forge_check

  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…

• forge_scan

  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…

• forge_watch

  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…

• forge_exposure

  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…

• forge_traps

  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…

• arena_results

  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…