- Osmcp @krushnavardhanreddy/osmcpA typed, policy-controlled OS capability layer for AI agents.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
- sw-postgres-mcp @jpka/sw-postgres-mcpSafe-write Postgres MCP server with preview-before-execute writes and rollback safety.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Attestify OS @attestifyagent/attestify-mcpMCP stdio server for Attestify OS — governed agent execution and Attestify Trust signed evidence.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Toolgovern @rudrendupaul/toolgovernWraps the toolgovern CLI as a single generic MCP tool for agent-tool policy validation.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- VITNA – Containment for rogue AI agents @costrinity/vitna-compliance-preflightGuard wraps stdio MCP servers: risky calls wait for a person; no answer, no run. Remote: cooperative5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- SafeNode MCP Gateway @sp3ak/safenode-mcp-gatewayPolicy proxy for MCP tool calls. A denied call never reaches the downstream server.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Procheiron @logotheusneuro-cpu/procheironReview gate for shared agent memory: an unreviewed or hand-edited memory is never served.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- DeskCert @rudrendupaul/deskcertEvaluates whether an AI agent is safe to operate internal web apps via an MCP run_suite tool.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Tally MCP @tally/mcpAn AI agent for prop firm challenges on Propr; the connector reads it, never trades.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Bay Run @barneywohl/bay-runFree OpenAI-compatible inference with signed provenance receipts and 3 focused MCP tools.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Kaval @usekaval/kavalVerify the facts an agent's action depends on before it acts — ALLOW, REVIEW, or BLOCK.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Stigmer @stigmer/stigmer-mcpExecution graph of AWS: verified contracts, least-privilege IAM policies, pre-flight authorization.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Arbiter @godwin105/arbiterIs this transaction safe to sign? Decodes what it really does and answers allow, warn or block.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- LineBreak Gate & Spec Bridge @linebreakapp/linebreak-gateApproved acceptance criteria served over MCP to Claude Code, Cursor, or Codex. Git-only, sealed.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- 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.6% 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.
- AgentGuard @tooloracle/agentguardAgentGuard — 20-tool AI safety MCP: policy preflight, risk scoring, audit logging, rate limits.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- 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.
- Gentkey @gentkey/mcpOne MCP URL for all your connectors — scoped writes, enforced constraints, and a full audit trail.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
