- Postbag @parasxos/postbagLocal Claude Code and Codex sessions on one machine exchange letters through native inputs.Not assessed yet.Runs on your machine, installed from PyPI.9 GitHub stars.
- Ducklab @jrullan/ducklabMulti-LLM dev harness, MCP-operable: bugs, cycles, gates. Verdicts are exit codes, never opinions.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.9 GitHub stars.
- OpenScout @oscout/scoutCoordinate local coding agents and track handoffs. For high-trust developer pilots.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.8 GitHub stars.
- Weckr @useweckr/weckrAsk which of your customers cost more in LLM calls than they pay, per user and per feature.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.8 GitHub stars.
- Unified AI System MCP Gateway @happy520ai/unified-ai-systemSelf-hosted MCP gateway for Codex, Cursor, and Cline with provider-free prompt enhancement.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.8 GitHub stars.
- NV oOS MCP Bridge @nvdigitalsolutions/nvoos-mcp-bridgeStdio relay connecting Zed, Claude Desktop, Cursor and Codex to NV oOS WordPress MCP endpoints.Not assessed yet.Runs on your machine, installed from npm.7 GitHub stars.
- Pi Durabletask MCP @nyarlathoteppppp/pi-durabletask-mcpDelegate Claude/Codex tasks to configured Pi, with steering and optional SQLite restart recovery.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
- Claude Agy @pymodel/claude-agy-mcpDelegate heavy tasks from Claude Code to the Antigravity CLI (Gemini) with quota-aware failover.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
- Kie @elibarnett/kie-mcpMCP for kie.ai: 45+ image, 70+ video, 20+ audio models with model intelligence6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
- MCP Bench Router @k1ta141k/mcp-bench-routerRoutes design tasks to designarena.ai's top-ranked model via OpenRouter across 14 categories.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
- gut @kungie/gutJudgment calls on small, cheap models: is this spam, which team, how urgent. YES, NO or UNSURE.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.6 GitHub stars.
- Tokenectomy Razor @tokenectomy-labs/razorCut 95% of framework noise and token bloat from error logs for AI agents.17% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
- Tokenectomy Razor @daffa2555/razorAutonomous log surgery & secret redaction MCP server for AI coding agents.16% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from cargo.6 GitHub stars.
- Ennodia @cherninlab/ennodiaConnects the AI agents you use: your agent hands a task to another and gets the answer back6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
- Aiterm @kitepon/aiterm-mcpPersistent terminals and one launcher for Claude, Codex, Grok, and Cursor harnesses.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
- Tuning Engines - Governed AI Runtime @cerebrixos-org/tuning-enginesGovern model, agent, skill, and MCP workflows with policy, approvals, traces, and usage analytics.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
- Pincer @vouchlyai/pincerSecure grip for your agent's secrets - security-hardened MCP gateway with proxy token architecture8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
- Portkey Admin @codeswhat/portkey-admin-mcpPortkey Admin API control-plane MCP server with Prisma AIRS interoperability guidance.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
- Aetherwave @aetherwave-studio/aetherwave-mcpMusic, image, video and audio generation across top AI providers - one key, one credit pool.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.6 GitHub stars.
- Talkies @psyb0t/talkiesSelf-hosted MCP server for speech: ASR transcription, TTS synthesis, and file staging tools.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.5 GitHub stars.
- AgenticLedger @shekharbhardwaj/agentic-ledgerLocal-first flight recorder for AI agents: sessions, costs, loop runs, and stuck-loop flags.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.5 GitHub stars.
- Wiff @xxxoooxoxo/wiffDeterministic, resumable multi-agent workflows across Codex, Claude, Cursor, and Kimi.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.5 GitHub stars.
- LLM Usage @zhaoyue722/llm-usage-mcpLocal-first, multi-provider tool that captures LLM API spend and exposes it to coding agents via MCP4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.5 GitHub stars.
- Local Delegate @zahirinatzuke/local-delegateDelegate mechanical text tasks to a local OpenAI-compatible LLM to save Claude quota.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.5 GitHub stars.
