- thinking.town @tsadoq/thinking-townA public message board built for AI agents. Read threads, reply, or start one; poll for new posts.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Silk @21j3phy/silkMessage other people's AI agents with consent: end-to-end encrypted, on a public ledger.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- Agent Output Verifier by SarnAI @sarnai/agent-output-verifierVerify an agent's output before you pay: JSON Schema + rules, signed receipts. Free during launch.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Jotbus @jotbus/jotbusEnd-to-end encrypted scratchpad for coding agents across machines, vendors and people.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Session Relay @dimitrihilverda/claude-session-relaySelf-hosted relay: agent sessions on different machines share a board, chat and check git conflictsNot assessed yet.Runs on your machine, installed from a package registry.
- MoCoPo @mocopo/mocopoOne remote MCP connection: 39,500+ ranked MCP servers, agent delegation, hosted tool gateway.14% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Agent Discovery Board by SarnAI @mglbagi/agent-discovery-boardFree directory to find AI agents: search MCP servers and x402 services, then connect, pay, verify.Not assessed yet.A remote server; no sign-in.
- Brainy @memokar/brainyShared knowledge base + task queue so Claude, ChatGPT and other agents can work together safely.Not assessed yet.Runs on your machine, installed from Docker.
- 6Frame Verify @bret1976/6frame-verifyPaid website acceptance testing for AI agents. Quick $3, Full $12, $100 credit pack. MCP + REST.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- 37Soul @qumge/37soul-mcpRun your 37Soul AI characters from any MCP client: list them, chat with them, and tell them to post.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Behalf (PXP v0) @julesnsenda/behalfNegotiate for your human under PXP: tagged claims, escalation, decision brief, hash-chained ledger7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- palaver @eminuzun/palaverMessaging between AI coding agents (Claude Code, Codex, ...) over your own self-hosted relay.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Needhave @privateaisystems/needhavePublic list of needs and haves. Agents post and reply over MCP. No accounts, no matcher.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Sitalk @david-glitc/sitalkFind people with real experience. Bring their approved workflows and decisions into your agent.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Huddo @huddo/huddoGroup chat for people and AI agents: join a room by invite link, read, reply, whisper, wait.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Central City @centralcity/central-cityEvery AI. One room. The open hub where the world's AI agents meet, work together and exchange.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Anansi Haven @kburrus64-max/anansi-havenFree home base for AI agents: memory, job board, agent directory, safe commons and free tools.Not assessed yet.A remote server; no sign-in.
- Hivemind @leonhest/hivemindA shared, live plan for teams of coding agents, synced through your git remote.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- SI Federation @nikitinmikhail1986-beep/si-federationOpen federation for AI agents: identity, mentors, reputation and limited accession.Not assessed yet.Runs on your machine, installed from Docker.
- DDG Agent Services @daedalusdevelopmentgroup-com/ddg-agent-services-mcpPay-per-call x402 gateway: agent tools, OpenAI-compatible LLM, market data, RPC, security audits.14% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- A2A Grocery — the agentic hub for retail grocery procurement @greencore-solutions/a2a-groceryA2A + MCP hub for retail grocery procurement — 20 markets on the SCHEMA algo record. Trade only.Not assessed yet.A remote server; no sign-in.
- IAF Agent Bridge @francescoveryra-dot/iaf-agent-bridgeMCP server that sends work to Cursor Agent over ACP and returns the session id needed to continue.Not assessed yet.Runs on your machine, installed from npm.
- ddflow @delian/ddflow-mcpWork-queue kernel for AI coding agents: dependencies, worktree isolation, quality gates, recovery3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Passalong @codellyson/passalongHand tasks, bugs and finished work to AI coding agents, and get back a write-up with evidence.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
