- COTAL actions (cotal.ai) @cotal/cotalcotal.ai actions: product overview, site search, build log, feedback, Cloud waitlist, updates, calls4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.308 GitHub stars.
- Lobu @lobu-ai/lobuShared, permission-aware company context for AI agents, with provenance, approvals and audit.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.225 GitHub stars.
- e2a — email for AI agents @e2a/mcp-serverAuthenticated email gateway for AI agents — per-agent inboxes, HITL approval, SPF/DKIM verified.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.193 GitHub stars.
- e2a — email for AI agents @mnexa-ai/mcp-serverAuthenticated email gateway for AI agents — per-agent inboxes, HITL approval, SPF/DKIM verified.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.192 GitHub stars.
- Technocore Chat @flop-labs/technocore-chatShared rooms and durable notes for agents over plain HTTP: rendezvous, hand-off, coordination.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.162 GitHub stars.
- Joxo @joxo/joxoOne shared project for a team's coding agents: decisions, a task board and handoffs.21% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.85 GitHub stars.
- emem, the verifiable memory protocol for the physical world @vortx-ai/ememShared, verifiable memory for machines and AI. Encode where data lives; decode with any AI.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.66 GitHub stars.
- Agoragentic Agent OS MCP @rhein1/agoragenticTriptych OS (Agent OS) MCP for governed routing, receipts, and USDC settlement on Base.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.40 GitHub stars.
- Axint @agenticempire/axintProof and repair for Apple coding agents: validate Swift, run Xcode evidence, and repair failures.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.18 GitHub stars.
- BuyWhere @buywhere/buywhere-mcpAgent-native product catalog: 300M+ products, 150,000+ stores, deliver_to ranking.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.15 GitHub stars.
- Pinchwork MCP Server @pinchwork/pinchwork-mcpMCP server for Pinchwork - an agent-to-agent task marketplace with credits-based economy8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.11 GitHub stars.
- 1F3D9 City Life for AI Agents @onetapstudiogames/1f3d9A persistent AI world where agents walk, build, own things, talk, and make agreements.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.10 GitHub stars.
- Nodiom Cloud @synexiom-labs/nodiom-cloudA shared board your AI agents read and write: they claim work, hand it off, and stop for review.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.9 GitHub stars.
- Llm Bus @llm-bus/llm-busCoordinate multiple AI agents over MCP: atomic claims, leases, shared ledger, handoffs, tasks.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.9 GitHub stars.
- AIMEAT @aimeat/aimeatAIMEAT - the Linux of AI. An open, federated, self-hosted AI operating system you own. MIT.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.8 GitHub stars.
- PlanWright @planwright/planwrightControl plane for autonomous software labor. Agents claim objectives over MCP with audit trail.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.7 GitHub stars.
- Axis @useaxis/axisCoding agents from Claude Code, Cursor and Codex claim jobs and lock files on one shared board.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.6 GitHub stars.
- Ethora MCP Server @dappros/ethora-mcp-serverEthora chat platform MCP: apps, users, rooms, AI agents, chat widgets. Hosted or stdio.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.6 GitHub stars.
- aX @ax-platform/ax-platformAgent-native collaboration network: orchestrate a team of long-running agents from any MCP client.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.6 GitHub stars.
- Materialmodel @materialmodel/materialmodelExplore discoveries, ask questions, share findings, and build collaborations with other agents.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.5 GitHub stars.
- Builderforce @seanhogg/builderforceRun tickets, boards, OKRs and cloud coding agents in your Builderforce workspace8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.5 GitHub stars.
Agent collaboration MCP servers
A server here lets AI agents message, delegate tasks to, hire or coordinate with other agents.
Not here: human chat apps and team chat.
1,028 remote629 localTagged by Odel's AI, which can make mistakes
Most popular in Agent collaboration
By GitHub stars, at most two per publisher- Number 1: Agent-Native Dispatch@builderio/agent-native-dispatchCentral Slack/Telegram router with jobs, memory, approvals, and A2A delegation5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.7,121 GitHub stars.
- Number 2: Omnara@omnara/omnaraDeploy durable AI agents with Omnara, an open-source managed-agent platform.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.2,905 GitHub stars.
- Number 3: Nautilus Compass Memory@chunxiaoxx/nautilus-compassLocal-first long-term memory for AI agents, with byte-recomputable signed verification receipts.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.1,260 GitHub stars.
