- Engram @tomcat65/engramCoordination bus + shared truth for AI agent fleets — self-hosted MCP server + stdio bridge.Not assessed yet.Runs on your machine, installed from npm.
- DojoGenesis MCP @dojogenesis/mcpPractice library for coding agents: skill search/invoke, seed patches, scout, reflect, ADR writer6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
- Agent Hub @blackaxgit/agent-mcp-hubOne MCP server bridging the Codex, Cursor, OpenCode, Claude, and Antigravity CLI agents6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- agentsync @jarmstrong158/agentsyncMulti-agent coordination MCP: claim work, survey peers, resolve conflicts via a git branch as CAS.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- HPP x402 MCP Bridge @hpp-io/x402-mcp-bridgeMCP bridge for autonomous x402 payments in HPP USDC.e — discover and pay for services per call.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Datasieve @gitwormq/datasieveOn-chain watches, web-page monitors, dead-man switches, cron, and agent coordination, paid via x402.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Claude Context Sync @ybin4548/claude-context-syncShare context, detect conflicts, and message across parallel Claude Code sessions6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- xete @xetenet/xete-mcpEnd-to-end-encrypted, sovereign inbox for AI agents. The server only ever sees ciphertext.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Agora @vorluno/agora-mcpShared per-repo space for Claude Code sessions: see activity, get collision warnings, notes.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Agent Claim @vk0dev/agent-claim-mcpFile-claim coordination for parallel AI coding agents: claim files before edits, no stomping.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Axp @tradewr333-lgtm/axpTrust scores, opportunity feed, contracts and a paid crypto Decision API for AI agents.18% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Machine Hearts @trainmyagent/machineheartsAutonomous agent matchmaking and relationship actions for Machine Hearts.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Agentschat @swswordholy-tech/agentschat-mcpShared live rooms for AI agents to chat, vote, run OKRs, hand off to humans - join, don't rebuild.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Synpareia Trust Toolkit @synpareia/trust-mcpVerifiable dealings with other agents: prove what you did, vet who you deal with, bind agreements6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Sooda MCP @sooda-ai/sooda-mcpAI agent relay — message business agents across company boundaries via A2A protocol7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- Humanaway @seankim-android/humanaway-mcp-serverMCP server for humanaway, a social network for AI agents.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Negotiate @sanjana-pier39/negotiate-mcpNegotiate prices at any negotiate.v1 store. AI shopper tools for Claude.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- OceanBus @ryanbihai/oceanbus-mcp-serverRegister, discover, message, and transact with other AI agents on the OceanBus network.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- MindForge @sairam0424/mindforgeRead the MindForge engine over MCP: knowledge graph, project health, and audit log.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- MCP OpenClaw Extensions @romainsantoli-web/mcp-openclaw138-tool MCP server for AI agent firms: security, A2A, Hebbian memory, fleet mgmt7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Aichat @rcgalbo/aichatInter-agent communication for multi-agent Claude Code workflows.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- AgentTrust @raditotev/agent-trustMCP Server for Agent Reputation & Trust Scoring6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Casemgr @mstang/casemgr-mcpShared workspace your AI agent writes to. 184 tools, persistent memory, semantic search.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Minuet @minuetai/minuet-mcpMCP server exposing Minuet's ERC-8004 agent relationship graph.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
