- World Model @saravananjaichandar/world-model-mcpTemporal knowledge graph for codebases with constraint enforcement at the edit boundary.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.23 GitHub stars.
- NEUS MCP @neus/neus-mcpThe trust harness for AI agents. Set what an agent can do before it acts.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.23 GitHub stars.
- Strategic Agent Reasoning MCP @putervision/agent-reasoning-mcpStrategic BDI reasoning engine for autonomous AI agents with spatial utility and replanning.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.21 GitHub stars.
- Claude Octopus @xiaolai/claude-octopusSpawn multiple specialized Claude Code agents as MCP servers, each independently configured.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.21 GitHub stars.
- Mastyf Ai @mastyf-ai/mastyf-aiRuntime proxy for MCP security, cost governance & audit7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.21 GitHub stars.
- Codex Octopus @xiaolai/codex-octopusSpawn multiple specialized Codex agents as MCP servers, each independently configured.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.20 GitHub stars.
- Context Foundry @context-foundry/context-foundryRecursive Claude spawning for autonomous project builds with self-healing test loops8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.20 GitHub stars.
- DOS — the trust substrate for agent fleets @anthony-chaudhary/dos-kernelVerify what agents actually shipped, arbitrate file collisions, refuse with structured reasons.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.20 GitHub stars.
- Sdd @juanklagos/sdd-mcpSpec-Driven Development workflow: specs, plans, gates, status and logbook tools. Bilingual EN/ES.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.19 GitHub stars.
- nable @getnable/finops-mcpSee where your cloud and AI bills go, and spend less. Local-first, in your terminal or editor.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.19 GitHub stars.
- Ironclaw @ironsecco/ironclawSandboxed shell exec for MCP clients: run untrusted agent commands in a gVisor container.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.19 GitHub stars.
- ToolTrust Scanner @agentsafe-ai/tooltrust-scannerScans MCP servers for prompt injection, data exfiltration, and privilege escalation.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.19 GitHub stars.
- Ekbasis @openinterpretability/ekbasisForesee what git commands and multi-step changes will do, as calibrated probabilities3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.18 GitHub stars.
- Iconnect @heznpc/iconnectMCP server for the entire Apple ecosystem — 123 tools across 14 modules. macOS only.Not assessed yet.Runs on your machine, installed from npm.18 GitHub stars.
- mcp-airlock @shalimov04/mcp-airlockGovernance proxy for MCP servers: allowlist, forced dry run, human confirmation, blast radius, audit3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.18 GitHub stars.
- MetaMCP @mentu-ai/metamcpRoute long-tail MCP servers through three lazy tools and reviewed declarative Methods.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.18 GitHub stars.
- AirMCP @heznpc/airmcpGoverned MCP runtime for the Apple ecosystem, available on macOS with per-call approval.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.18 GitHub stars.
- Lockkeeper @hannay001/lockkeeperRoutes each task to the few skills, MCP servers and tools that fit it.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.17 GitHub stars.
- CALM @eilodon/calm-mcpMCP server giving coding agents a call-graph-aware, hash-verified view of a codebase, not grep.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.17 GitHub stars.
- Cruxible Core @cruxible-ai/cruxible-coreDeterministic decision engine with receipts. Define rules in YAML, query a graph, get proof.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.17 GitHub stars.
- as a Judge @othervibes/mcp-as-a-judgeMCP as a Judge: a behavioral MCP that strengthens AI coding assistants via explicit LLM evaluations6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.17 GitHub stars.
- Aegis — AI Agent Governance @acacian/aegisPolicy-based governance for AI agent tool calls. YAML policy, approval gates, audit logging.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.17 GitHub stars.
- ScopeGate @alifanov/scopegatePermission gateway for AI agents: scoped MCP endpoints over 27 services, audited and revocable.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.17 GitHub stars.
- MCP Hangar @mcp-hangar/hangarPolicy enforcement plane for MCP: every tool call ends in a verdict. Self-hosted, MIT.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.16 GitHub stars.
