macOS app that intercepts and audits MCP server traffic between Claude Desktop or Cursor and connected tools for security oversight.
Results for “Documentation MCP d'Anthropic”
268 tools found
Turns OpenAPI specs into safe, typed tools that AI agents can call, without manual wiring.
Free, open-source, keyboard-first web browser for macOS with an integrated AI sidebar and MCP-based agent control.
An unofficial, zero-dependency local dashboard for Claude Code that shows sessions, cost burn rate, git worktrees, CI status and MCP server analytics in one place.
An open-source payment layer that lets AI agents pay for MCP tools on a per-call basis, with spending limits so they can't run up an unexpected bill.
A platform that centralizes AI-agent access to 100+ third-party accounts (Gmail, Slack, GitHub, Notion...) behind one self-hostable, permissioned MCP layer, plus a dev environment for running several coding agents in parallel.
A free library of nearly 40 ready-made diagram styles — flowcharts, architecture maps, timelines and more — that produces clean, on-brand diagrams for documentation without opening a design tool.
A tiny, extremely fast piece of plumbing that lets AI assistants like Claude talk to your files, databases and dev tools safely, instead of each app reinventing that connection from scratch.
AI social media manager that writes, adapts, and publishes posts across 7 networks from a plain-English instruction, with native Claude/ChatGPT integration
One-line analytics integration for MCP servers, showing which AI clients connect, tool adoption, and silent failures
Compiles OpenAPI specs, MCP servers or SQLite databases into lightweight CLI tools, cutting agent context by ~4x
React hooks that expose your app's features as typed tools AI agents can discover and call in the browser
Zero-execution static scanner that audits MCP servers for command injection, path traversal and prompt injection
Rust daemon that runs Claude Code, Codex and other AI coding agents on cron-like schedules, with a dashboard, REST API and MCP
AI-powered project documentation and knowledge management platform that creates a unified graph connecting vision, objectives, requirements, decisions, risks, and work items to preserve critical project context.
An MCP proxy that sits between LLMs and MCP servers, providing dynamic tool retrieval and security policy enforcement through deterministic rules rather than LLM reasoning.
Uptime and reliability monitoring for MCP (Model Context Protocol) servers, tracking 26,000+ servers with live checks every 15 minutes instead of relying on GitHub star counts.
A one-command CLI that exposes a local MCP server to a public URL, so you can test or demo it with ChatGPT, Claude, or Cursor without deploying anything.
Open-source tool that generates slide decks directly from a code repository and automatically flags slides whose code citations have gone stale, so documentation decks don't quietly drift from the actual codebase.
MCP Locker provides a private, hosted endpoint for securely managing and hosting personal MCP (Model Context Protocol) servers and WebMCP resources. It enables developers to run and share MCP servers through a single private endpoint without exposing infr