- 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.
- 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.
- 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 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.
- bundlebox @blackswanalpha/bundleboxWhere the work is, packed before the agent reads: brief, symbol tables, findings, token bill.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- jevnav @dtduc-git/jevnavReplayable browser automation: Jev picks the element, a gate blocks risky actions, every run traces.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- TollWarden @tollwarden/tollwardenScreens x402 payments before settlement for injected payee addresses and sellers who never deliver.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- SpendShield @felixpg13-glitch/spendshieldAuthorization layer between AI agents and money: ALLOW/APPROVAL/DENY, budgets, audit.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Keel @lutfizp/keelControl plane MCP that dedups scanner output, rate-limits hosts, and runs non-destructive proofs.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Securedact MCP @giganteshji/securedact-mcpLocal-first privacy MCP server for sensitive AI workflows4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- mcp-audit @firatmio/mcp-audit-proxyTransparent audit proxy for MCP servers: logs every tool call, flags poisoning and rug pulls.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Cursor Chat Bridge @udah1/cursor-chat-bridgeDrive the Cursor agent from Telegram, Discord, or GitHub — with images and voice notes.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Kāhea @copyleftdev/kaheaDeterministic HTTP/WebSocket testing and policy-gated API execution for AI agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.2 GitHub stars.
- Gpp @mahabubul470/gppProject knowledge graph with history-checked belief staleness, changeset proposals, cost reporting5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from cargo.2 GitHub stars.
- Inspectrum @yannmenec/inspectrumReview coding-agent plans on demand with peer models, attributed findings, and a structured verdict.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Actenon Kernel @actenon/kernelVerify consequential AI actions before they execute.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Agentic MCP @hugolsramos01-bit/mcp-agentic-serverLocal coding tools for ChatGPT Developer Mode and MCP clients with safe editing and shell execution.11% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
