- Release Gate @vamsisudhakaran1/release-gatePre-deploy security auditor for AI agent code — the risks generic SAST misses.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
- Pathmodeio MCP @pathmodeio/mcp-serverDeterministic intent preflight before your agent builds: six gates, keyless, no model call.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- signet-eval @jmcentire/signet-evalDeterministic policy enforcement and MCP management for AI agent tool calls.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.3 GitHub stars.
- mcpm @getmcpm/cliMCP security guard + package manager: trust-scored installs, blocks prompt injection and rug-pulls.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Sanction @ericlovold/sanctionApproval and budget checks before agent spending or tool use. Cooperative MCP; host must ask.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.3 GitHub stars.
- Aegis @cleburn/aegis-mcpRuntime governance enforcement for AI agents. Zero token overhead.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Sigil @cdrn/sigilLocal keystore + MCP server. Claude can sign EVM transactions but never sees the private key.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Calllint @calllint/calllintStatic preflight safety gate for MCP servers — scan configs before you run them. Never executes.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Air Blackbox @airblackbox/air-blackbox-mcpEU AI Act compliance scanner for Python AI agents. 14 tools across 6 articles.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
- WAKE Protocol @omodaka9375/wakeA post-mortem succession protocol for AI agents. Black Box, handoff, time-locks.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- oraclemcp @muhdur/oraclemcpEngine-free, governed Oracle Database MCP server with a fail-closed SQL guard (unofficial).5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.3 GitHub stars.
- Agent Gate @jott2121/agent-gateFail-closed quality gate and hash-chained receipt ledger for AI agent workflows.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
- Defenter Proxy @defenter-ai/defenter-proxyReal-time semantic security for AI coding agents and MCP tools13% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
- NOMOS Cross-Border Broker @agentnomos/nomos-crossborder-brokerCross-border preflight, x402 quote and evidence receipts for A2A/MCP agent workflows.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.3 GitHub stars.
- ThinkNEO Control Plane @thinkneo/control-planeEnterprise AI Control Plane: governance, guardrails, spend tracking, compliance & smart routing.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.3 GitHub stars.
- EK Bridge @bereciartua/ek-bridgeScoped Apple Calendar and Reminders access for AI agents, with per-client grants and approvals3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.2 GitHub stars.
- Tower @rohanxmalik/towerMultiplayer for AI coding agents: collision detection before the edit, messaging, delegation.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Solumbe @bashbop/solumbeDeterministic local repository context, impact analysis, and merge-readiness evidence for AI agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Arroway @oaleviola/arrowayArroway orchestrates people and AI agents around the decisions in force.Not assessed yet.A remote server; you sign in with your account.2 GitHub stars.
- MIMIR @abderahmane-ai/mimirTyped, calibrated and certified decisions over a context, with abstention and evidence.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- AgentRaaS wrap @sumedhchatse/agentraasWraps any MCP server: identical write-tool calls run once, and every tool call is audit-logged.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- MCP Verification Gate: check an MCP server or an A2A agent before you connect or delegate @ogasurfproject-jpg/hs-verify-gateCheck an A2A agent before you delegate, or an MCP server's measured conduct. Free, no key.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.2 GitHub stars.
- MCP Sentinel @oaslananka/sentinelZero-trust MCP security proxy with policy enforcement, PII scrubbing, approvals, and audit trails.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- vaultgate @adamrowles1996/vaultgateSelf-hosted remote MCP server for Bitwarden and Vaultwarden with OAuth 2.1; agents hold tokens only4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.2 GitHub stars.
