- DRAIN @kimbo128/drain-mcpPay for AI inference with USDC micropayments on Polygon. No API keys needed.22% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- FCoP @joinwell52-ai/fcopFCoP Core adapter with 25 canonical tools and 6 read-only resources for durable agent work.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Arbitova @jiayuanliang0716-max/arbitovaEscrow + AI arbitration for A2A payments. Lock funds, confirm delivery, dispute if needed.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- GopherHole Agent Hub @helixdata/gopherholeStandards-based A2A hub. One MCP connection to thousands of agents, with shared persistent memory.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- agenthold @edobusy/agentholdShared versioned state for multi-agent AI workflows4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- ANP2 @anp2dev/anp2-mcp-serverAI-agent economic protocol over MCP — identity, reputation, tasks, credit, Sybil resistance8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Airlock @adamorad/airlockLocal daemon giving AI agents named locks, shared state, events, and a task queue over MCP.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.2 GitHub stars.
- Shrike @shrike-security/shrike-mcpGoverns what AI agents do: tool calls, SQL, commands, files checked against policy before they run.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Task Graph @oortonaut/task-graph-mcpMCP server for agent task workflows with phases, prompts, gates, and multi-agent coordination3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.2 GitHub stars.
- Cli Bridge @joaoberne/cli-bridge-mcpOther AI CLIs (Gemini, GPT, Claude, opencode, Ollama) as a council — ban-safe, no API keys.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- NebulaMind @duhokim/nebulamindAI astronomy wiki with open agent peer-review. Vote on evidence, propose edits, earn reputation.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Amicus @bourbondog/amicusMulti-model LLM Council and parallel AI window for Claude Code. Fork any model, fold results back.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- 1Claw Vault @1clawai/1claw-mcpHSM-backed vault secrets for AI agents (JIT fetch) plus prompt-injection and threat scanning.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- CueAPI MCP @cueapi/mcpSchedule agent work and report write-once outcomes via CueAPI from any MCP host.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Agent Uplink @pkj8282/agent-uplinkLocal messaging between AI sessions: role accounts, DMs, channels via MCP. Windows only.Not assessed yet.Runs on your machine, installed from npm.1 GitHub stars.
- Puenteo @mano7onam/puenteoLet coding agents talk: search every agent session's history and message live sessions.Not assessed yet.Runs on your machine, installed from PyPI.1 GitHub stars.
- AgentGo @nishkalkashyap/agentgoRun Codex and Claude Code on your computer from an MCP client, and track or continue their runs.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Swarmail @bompus/swarmailLocal mail between coding-agent sessions on one machine; relays to a running Swarmail server.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Parley @5uper0/parleyMulti-party decisions for agents: red lines rejected in code, max-min pick, SHA-256 receipt. Stdlib.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Stratum MCP @smartmemory-io/stratum-mcpStructured execution for Claude Code — contracts, postconditions, gates, guardrails.Not assessed yet.Runs on your machine, installed from PyPI.1 GitHub stars.
- Agent Mesh @johnmwhitman/agent-meshAuditable multi-agent coordination: fleets, P2P messaging, witnessed receipts, quorum.Not assessed yet.Runs on your machine, installed from npm.1 GitHub stars.
- AgentBrain Handoffs @willykeenan/agentbrain-handoffsExact, durable handoffs between AI coding agents: one turn in the right session, never twice.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1 GitHub stars.
- Safebot Chat @alexkirienko/safebot-chatEnd-to-end encrypted multi-agent chat rooms. Client-side crypto; zero chat logs.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- AgentFolio @0xbrainkid/agentfolio-mcp-serverAI agent identity verification via SATP on Solana. Trust scores and on-chain attestations.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
