- node9 @node9-ai/node9Access control for AI agents and MCP servers: allow, hold for approval, or block each tool callNot assessed yet.Runs on your machine, installed from npm.217 GitHub stars.
- MCP Task Orchestrator @jpicklyk/task-orchestratorServer-enforced workflow discipline for AI agents: work items, dependency graphs, quality gates5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.208 GitHub stars.
- Slim Guard @lennney/mcp-slim-guard76% fewer MCP tokens in our standard benchmark. Same upstream call. Exact recovery.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.186 GitHub stars.
- AISIX AI Gateway @api7/aisixSelf-hosted AI gateway that governs MCP servers, LLM traffic, and A2A agents behind one endpoint3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.184 GitHub stars.
- Forge Orchestrator @nxtg-ai/forge-orchestratorAI orchestration: Claude Code, Codex, Gemini on shared repos. 11 MCP tools, stdio (stage: internal)6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.162 GitHub stars.
- Prism @dcostenco/prism-mcpMoved to io.github.dcostenco/prism-coder — install prism-mcp-server v20+ from npm.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.158 GitHub stars.
- Prism Coder @dcostenco/prism-coderSession memory for coding agents: local-first recall, drift detection, on-device inference.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.158 GitHub stars.
- Shellward @jnmetacode/shellwardAI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.140 GitHub stars.
- Vessel Browser @unmodeled-tyler/vessel-browserAI-native browser runtime for autonomous agents with human-in-the-loop supervision7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.136 GitHub stars.
- Codex Control Plane MCP @aresyn/codex-control-plane-mcpDurable MCP control plane for long-running Codex Desktop tasks.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.124 GitHub stars.
- Agent Security Scanner @sinewaveai/agent-security-scanner-mcpSecurity layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.123 GitHub stars.
- jevmem @avinash-jetwani/jevmemAutomatic project memory for Claude Code. Also works with Cursor and Codex.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.121 GitHub stars.
- Continuum @pouyahasanamreji/continuumShared memory + orchestration for your coding agents. Local-first MCP, vector RAG.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.110 GitHub stars.
- CHAP Coordinator @brightbeamai/chapAuditable records of human decisions over AI agent work. Approvals, edits, overrides, escalations.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.107 GitHub stars.
- Sqlsure @sqlsure/sqlsureSemantic SQL inspector: catches double-counting, wrong joins, PII exposure before execution.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.99 GitHub stars.
- Sub Agents @shinpr/sub-agents-mcpMCP server for delegating tasks to specialized AI sub-agents across coding tools5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.98 GitHub stars.
- agentgate @ciceroyang/agentgateRead-only evidence for the tools agents run: MCP server records, coverage and policy.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.96 GitHub stars.
- reevesagents @mertkayacs/reevesagentsSpawn, read and steer AI coding CLIs (Claude Code, Codex, Kimi and more) in local tmux windows.Not assessed yet.Runs on your machine, installed from npm.88 GitHub stars.
- Vouch @vouchdev/vouchGit-native, review-gated knowledge base for LLM agents. Cited retrieval, audited writes.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.82 GitHub stars.
- Raxol @droodotfoo/raxolElixir/OTP runtime where every UI component auto-exposes MCP tools; stdio server: mix mcp.server5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.79 GitHub stars.
- Agentos @imran-siddique/agentosBuild and manage policy-compliant AI agents with safety enforcement and compliance checking6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.74 GitHub stars.
- Trustabl @trustabl/agent-reliability-analyzerFind and fix reliability and safety gaps in agent code, across nine agent SDKs.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.72 GitHub stars.
- Autodesk Revit MCP Server @sam-aec/autodesk-revit-mcp-serverMCP server connecting AI assistants to Autodesk Revit through a local bridge.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.68 GitHub stars.
- Vorim @vorim-ai-labs/vorim-mcp-serverAI agent identity, permissions, trust scores, and tamper-evident audit trails via Vorim AI8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.66 GitHub stars.
