- Replicate @mcparmory/replicateRun AI models, create deployments, and manage predictions via cloud API6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.32 GitHub stars.
- Ai Cli @mkxultra/ai-cli-mcpRun Claude, Codex, Gemini, Forge, and OpenCode CLIs through MCP with background jobs6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.27 GitHub stars.
- Agent Intern @sinantufekci/agent-internDelegate from Claude Code to Gemini, Codex, Copilot, Cursor and opencode CLIs as sub-agents.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.26 GitHub stars.
- Pitroom @atastech/pitroomHands bounded coding work to cheaper worker agents: verified answers, exact diffs, cost receipts.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.24 GitHub stars.
- Delimit — Keep the state. Change the model. @delimit-ai/delimit-mcp-serverKeep the state. Change the model. Shared context and a multi-model panel across coding assistants.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.24 GitHub stars.
- Claude Octopus @xiaolai/claude-octopusSpawn multiple specialized Claude Code agents as MCP servers, each independently configured.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.21 GitHub stars.
- Prompt To Asset @mohamedabdallah-14/prompt-to-assetGenerate app icons, favicons, OG images, and logos by routing across 30+ image models.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.21 GitHub stars.
- DeepSeek @arikusi/deepseekMCP server for DeepSeek AI with chat, reasoning, sessions, function calling, and cost tracking4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.20 GitHub stars.
- Ask Claude @lykhoyda/ask-claudeBridge Codex and other MCP clients with Anthropic Claude Code CLI for read-only second opinions5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.18 GitHub stars.
- Ask Antigravity @lykhoyda/ask-antigravityBridge Claude with Google's Antigravity CLI (agy) for code review and second opinions6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.18 GitHub stars.
- Jev-Style @lawrence3699/jev-styleLocal 2B and 0.8B decision models: calibrated yes/no, choice and score answers for your agent.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.16 GitHub stars.
- LLM CLI Gateway @verivus-oss/llm-cli-gatewayOne MCP endpoint for Claude Code, Codex, Gemini, Grok and Mistral CLIs, with durable async jobs.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.16 GitHub stars.
- Llmkit @smigolsmigol/llmkitAI cost tracking: 11 tools for spend, budgets, and Claude Code + Cursor + Cline costs6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.16 GitHub stars.
- MCP Imagenate @mimo-3/mcp-imagenateMCP server for image generation using multiple providers (Google Gemini, OpenAI, BFL FLUX)4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.15 GitHub stars.
- Spanlens MCP @spanlens/mcp-serverQuery Spanlens LLM observability from Cursor, Claude Desktop, or Continue via MCP.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.13 GitHub stars.
- Tachibot @bypawel/tachibot-mcpMulti-model AI orchestration with 31 tools, YAML workflows, and 5 token-optimized profiles.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.13 GitHub stars.
- OrcaRouter @continuum-ai-corp/orcarouter-mcpBrowse 160+ LLM models and live pricing — no API key needed for catalog. Add key to route chat.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.13 GitHub stars.
- Agent Link @mikusnuz/agent-linkBidirectional AI agent collaboration — spawn and communicate with any agent CLINot assessed yet.Runs on your machine, installed from npm.11 GitHub stars.
- AitherOS ADK @aitherium/aither-adkAgent runtime with typed memory, knowledge and code graphs, plus file and web tools7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.11 GitHub stars.
- Mcacp @oortonaut/mcacpMCP-to-ACP bridge — let any MCP client drive ACP coding agents6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.11 GitHub stars.
- Orchestrator @crak1644/orchestrator-mcpLet one coding-agent CLI consult another: Codex, Claude Code, OpenCode, Copilot or Antigravity.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.10 GitHub stars.
- magents @abnegate/magentsShared session bus MCP+CLI for Claude/Codex/Cursor/Grok: list, read, handoff, send, spawn.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.10 GitHub stars.
- Gemini Media @mordor-forge/gemini-media-mcpGenerate images (Nano Banana), video (Veo, Gemini Omni), speech and music (Lyria) with Google modelsNot assessed yet.Runs on your machine, installed from Docker.9 GitHub stars.
- skgate @helv-io/skgateOAuth MCP gateway. SI proxy with model aliases. Grok subscription as OpenAI-compatible API, no key.Not assessed yet.Runs on your machine, installed from Docker.9 GitHub stars.
