AI & Machine Learning MCP Servers

Tokmeter MCP server, daemon and statusline — tokens and cost for AI coding agents from local session files

Lint an MCP server against the Claude connector directory, ChatGPT plugin directory and MCP spec review criteria.

DSH 插件 · 刷贴吧：读帖挑重点、写日报、自动签到；学习每个吧的语风（风格库），回帖与楼中楼可选（默认关）。支持人设、日记、峰谷定时，另带只读 MCP stdio server（未逐客户端实测）。

Expose DeepSeek Harness sessions, agents, and tools to any other agent harness over the Model Context Protocol.

Exposes DSH as an MCP server over Streamable HTTP: streaming thinking/tool/file notifications, shared intent, a floor lock that physically denies DSH writes while held, mid-turn alert injection, and review delegation.

Mebular memory, task graph, and shared Console for DeepSeek Harness

DSH 设置页内统一管理 MCP 服务器与技能(Skills):增删改、启停、hmr 热生效,写盘保留注释。内置 OAuth 2.1 + PKCE 授权链路。

Test any MCP server: connection, tools, security, login, resources and prompts. Hard facts, no AI judging.

Local MCP server that gives coding agents a verifiable project memory, trims what enters their context, and masks secrets — with honest accounting of what it saves and costs.

See every MCP message: chat with any LLM and MCP server, compare models, call tools, and see what your AI editor sends to your MCP servers. 100% local. One command: npx @mokalabs/sandbox

MCP server for Volcengine Ark, Alibaba Bailian, MiniMax, Doubao Speech and OpenAI: image, video, speech, music and chat tools for Claude Code, Codex, Cursor and Claude Desktop