evaluate
13 registry entries were observed exposing a tool named evaluate — 7 of them as a privileged capability (a name matching exec / write / delete keywords).
Every row is point-in-time scan output, dated below. Forge has an observed tool surface for 12,342 of 40,590 scannable entries (30%) — an entry that has not been scanned cannot appear here, so absence from this list is not evidence that an entry does not expose this tool.
- v2.18.0↓ 350/wk
AtlaSent for AI agents: with an API key, actions wait for approval with signed proof. No key: demo.
ClaudeCursorCopilotGeminimcp - v0.13.0↓ 600/wk
Overwing MCP server: guardrails for LLM output. Score any text for safety, quality and compliance and get pass / fail / review verdicts with calibrated confidence, from any MCP-capable agent. Plus Overwing Atlas: identify any User-Agent string against a r
ClaudeCursorCopilotChatGPTGeminioverwingmcpmodel-context-protocolmcp-serverllmguardrails - v0.3.8↓ 165/wk
Let your AI coding agent test its own frontend work. Connects Claude Code, Cursor, and any MCP client to your real Chrome browser — real sessions, real cookies, no headless conflicts.
ClaudeCursorCopilotGeminimcpbrowserautomationplaywrightthinkrunai-agent - v1.5.9↓ 54/wk★ 5
SideButton MCP server for AI agents — REST API, web dashboard, knowledge packs, and workflow engine
ClaudeCursorCopilotGeminimcpmcp-servermodel-context-protocolai-agentsknowledge-packsworkflow - v1.1.1★ 5
Open-source MCP server with browser automation and knowledge packs for AI agents
ClaudeCursorCopilotGeminimcp - v2.0.0↓ 31/wk
Quality advisor for AI agents. Evaluates, recommends, and finds alternatives for MCP servers and tools using real maintenance and adoption signals.
ClaudeCursorCopilotChatGPTGeminimcpmcp-serveragentrankai-toolsagent-toolsmodel-context-protocol - v1.0.4★ 1
Chrome breakpoint debugging MCP server for inspecting runtime values and stepping through code
ClaudeCursorCopilotGeminimcp - v0.10.0-preview.1★ 1
MCP simulator for dairy barn cooling: evaluate equipment, roof and weather on heat, water and milk.
ClaudeCursorCopilotChatGPTGeminimcp - v1.0.0
Headless browser primitives for AI agents when sites need real JS rendering.
ClaudeCursorCopilotChatGPTGeminicom.thenextgennexusUnknown5mo agoobserved · live tools/listmcp - v1.7.1
CI-1T prediction stability engine. Detect ghosts, evaluate drift, monitor fleets. 20 tools.
ClaudeCursorCopilotGeminimcp - v1.9.1
Hosted Playwright API for AI agents. Returns a11y trees instead of screenshots.
ClaudeCursorCopilotGeminimcp - v0.1.2
Math.js MCP — wraps the mathjs.org API (free, no auth)
ClaudeCursorCopilotChatGPTGeminimcp - v1.2.1
Google for AI agents. Gives your AI live search across 25,000+ scored MCP servers and tools.
ClaudeCursorCopilotGeminimcp