3394 Model Context Protocol servers — searchable, rated, ready to install.
Measures whether your Claude subscription is paying off, from local logs. No upload.
Shared memory for AI coding agents. Save once, reuse from Cursor, Claude Code, Codex.
Claude on Windows or Linux works in your WorkFlow tasks, notes and projects via your own iCloud.
Maths a model gets wrong: units with dimensional checking, equations, sheets. 5 tools, local.
Read, search, move, and delete Yahoo Mail over IMAP — MCP server for Claude
Shared memory and delegation for Codex, Cursor, Claude Code, and OpenCode.
Injects secrets into shell commands at exec time; plaintext never reaches the LLM context
Find real people for a task right in ChatGPT and Claude. Everyone chose to appear in AI answers.
AI-powered life cycle assessment and modelling: connect to LCA databases, build and analyze systems
Local MCP server for the Cloudflare Clef-Flash decision model: structured decisions, fully offline
Search and open dashboards, reports, decks and PRs that Claude Code and Codex made on your Mac.
Wallet auth: send a wallet and conditions, get a signed boolean across 37 chains.
What happened in AI coding agents like Claude Code, Codex, Cursor and Copilot, and what people say.
Local Claude Code and Codex sessions on one machine exchange letters through native inputs.
Publish apps from Claude Code, Codex or Cursor to your team, behind sign-in, with a database.
Schedule, check and retry social posts from Claude or ChatGPT; going live waits for a tap.
Prove you made it first. Blockchain Timestamp creative work via Claude or any MCP-enabled AI Agent.
Generate images and videos with frontier AI models. Pay per use; credits never expire.
Generate and edit images, video, voice, lip-sync and 3D models from your AI agent.
Give Claude a whiteboard: notes, links, images and diagrams on a board you both see and edit.
Revit tools over MCP stdio. Actions are enabled by default; the workstation lock disables them.
Shared memory for Claude, ChatGPT and any MCP client. Read and edit it in Obsidian or the web app.
Convert JSON samples into TypeScript interfaces and Zod schemas, with inference caveats.
MCP server caching expensive LLM responses: HTTP-style freshness plus semantic recall.
POST /mcp