- LoopPause @soteeabam/looppauseLoopPause MCP server — pause agent execution and route human approval requests4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Umbra @elberacasa/umbraTrust score for AI-generated code: scan repos, guard agent file writes, get a 0-100 score.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Orangerail @kimhyeongrae0/orangerailTurns your Prisma schema into typed MCP tools, with destructive writes gated behind human approval4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Gateco @gateco/gatecoPermission-aware retrieval for AI systems: policy-enforced access to organizational knowledge.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Taplid @taplid/taplidAudit AI responses and artifacts with ALLOW, REVIEW, or BLOCK decisions and trust scores.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Context @honeycrisp-suite/contextLocal-first personal context over MCP: mail/calendar metadata, briefings, person lookups. No cloud.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Vantic @vanticlabs/vanticVerify an AI agent's payment authority: signed mandates, allowlists, and tamper-proof receipts.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- X402 Accept @cryptoapis-io/mcp-x402-acceptSelf-hosted MCP proxy that puts an x402 paywall in front of an existing MCP server6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Proof @toremlabs/proofGovern your AI coding agent: frame the work, review the changes, keep a signed decision record.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Moneo @moneolabs/moneoA guarded wallet for AI agents on Robinhood Chain: a spending policy runs before every signature.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Rails @jaimenbell/rails-mcpDefault-deny action registry, append-only spend ledger, and human sign-off audit trail (MCP tools).5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- BailingHub for Business Operations @bailinghub/bailinghub-governanceLet AI agents query and operate business systems with authorization, approval and audit trails.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Ghostlink @bgorzelic/ghostlinkSandboxed repo access for coding agents: search, read, patch, run, git -- confined to a repo root.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Agent Guard @kavachh/agent-guard-mcpGit-aware safe file ops for AI agents: delete anything except git-tracked source code.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- Ai Consensus @thestevenjohnstone/ai-consensusStanding review layer for coding agents: Claude, GPT and Gemini debate, return consensus + dissent.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- ODGS @metricprovenance/odgs-mcp-serverODGS governance enforcement — validation, regulation compilation, drift detection, signed S-Certs.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Understand Anything - MCP @uamcp/ua-mcpA powerful MCP server for codebase architecture analysis and automated governance.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Panella @panellatech/panellaGoverned, self-hosted memory for AI agents: writes queue until a named person approves.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Phaedo @phaedo-labs/phaedo-mcpCarry your Phaedo cognitive fingerprint into any MCP client: inject, consult, escalate, sign.18% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Repotector @dir-ai/repotectorThe repo guardian AI agents handshake with before they touch your code.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Agent Toolbox @solhammer/agent-toolbox26 deterministic, offline pre-action safety gates for AI agents, each with a signed verdict.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- kcp-agent — KCP navigation planner @cantara/kcp-agentDeterministic, fail-closed planner for KCP knowledge manifests: kcp_plan, kcp_load, kcp_validate.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- kcp-harness — KCP compliance proxy @cantara/kcp-harnessMCP compliance proxy between agent and tools: deterministic governance, fail-closed, audit trail.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- PLwC Personal @mhoedt-ai/plwc-gatewayWindows x64/Python 3.12 MCPB preview: governed local tools and persistent profiles.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
