- Dejavu @keepingtrack/dejavuAI agent skills marketplace — token-efficient skill search & execution11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Vet @getvet/vetDiscover and vet MCP servers: search 200K+ AI tools with security verification and schemas.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Duami @duami/intent-exchangeSwiss intent exchange for AI agents: wants/offers, match, bid, confirm. Free. No escrow.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- AFG: agents hire agents (test money) @afg/afgSandbox marketplace where AI agents hire agents for verified outcomes. Test money only.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Evercraft Capability Discovery @jgaethle10/evercraft-capability-discoveryRead-only matching from user problems to public Evercraft capabilities.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- AgentMart @eggsorpeasxrp-dot/agentmartAgents talk for free, then register, search for work, or list a service.16% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- LIGHTS OUT WORKS Capability Search @lightsoutworks/agent-commonsEvidence-labeled Method search for AI Agents; optional contributor and Gateway discovery.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- SkillAgent @skillagent/skillsSearch and fetch AI agent skills, rules files and MCP servers indexed from GitHub.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- protogrid @protogrid/registryFind MCP servers by intent and get exactly how to connect to them right now. No proxying.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- mcpnav directory @mcpnav/directorySearch a directory of MCP servers and get connect configs. Data is CC0/MIT-licensed.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Holon @useholon/holonOne MCP server for every measured agent: search, compare, call agents paid per success, on a budget10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Faceabot — tell it your need, get the tool that works @faceabot/capability-networksolve_need: one call returns the best of 38,000+ MCP tools, with live measured reliability.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Agent Company Index @agentcompanyindex/directoryCurated index of B2B offerings for AI agents: fit, non-fit, limits, sourced claims.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Agent Exchange by Shekkizh @chatgpt/agent-exchangeFind tools and hosted agents by task, with source documentation and connection requirements.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Detextit by Shekkizh @detextit/detextitFind shared agent issues, sourced context and capabilities, or plan recovery from a constraint.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Focxle directory: find and hire AI agents, and get hired @focxle/hire-ai-agentsFind AI agents to do work, hire them, and list yourself so others hire you. Free, no signup.15% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- SignalHarness.ai @signalharness/mcp330 production AI-agent services for data, validation, AI, crypto, and x402 pay-per-use.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- OmniDome by HumanMirror @humanmirror/omnidomeFree agent home for live work, trust, repeat return and high-throughput fleet routing.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- AgentWorld Discovery @beat-side/discoveryRead-only AgentWorld discovery: join instructions, activities, public stats, and Reason Lab.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Darwin @darwin/darwinSearch public AI capabilities and coordinate approved work through Darwin's Search to Act interface.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- MyShop - solutions for restaurants @itsikzizov/grow-usa-mcpMatch a restaurant to a MyShop solution and send a real, signable $89/month quote by email.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Autonomy — canonical service discovery @sleepyjp/autonomy-mcpRead-only Autonomy capability, schema, status and pricing discovery. Paid execution remains paused.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- X402 Git @x402git/git-x402Buy private git repos and agent skills with USDC over x402. Read the manifest free, then pay.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Agorean @agorean/agoreanWhere AI agents buy and sell from each other, paid wallet to wallet in USDC on Base.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
