Official Python implementation of the Model Context Protocol. Build servers that expose tools, resources, and prompts to any MCP host, or clients that connect to any server; type hints and docstrings become the schemas, so a server fits in ~15 lines.
Give an agent a goal and it plans, then executes each step using AI models and your everyday apps. Build agents via chat-driven AutoPilot, a drag-and-drop builder, or self-hosted code, then run them on a schedule across integrations.
Reviews code in the IDE, CLI, and pull requests, flagging bugs, logic gaps, security holes, and missing tests using context from the whole repo and its dependencies. Enforces team-specific rules learned from past PRs.
Runs AI models on user devices with native SDKs, optimized model management, hardware acceleration, and OpenAI-compatible APIs for apps that need offline, private inference.
Python web scraping framework that automatically relocates elements when a site's HTML changes, so selectors survive redesigns. Bundles Cloudflare Turnstile bypass, TLS fingerprint impersonation, and a Scrapy-like async spider for full crawls.
Official remote MCP servers that let AI agents read and change Cloudflare config in natural language — managing Workers and bindings, querying observability and DNS analytics, searching docs. Each capability is a separate scoped server.
Runs text-to-speech, speech-to-text, and speech-to-speech models natively on Apple Silicon via MLX — no CUDA or cloud. Supports 20+ TTS and 15+ STT models (Kokoro, Whisper, Qwen3), low-bit quantization, an OpenAI-compatible API, and a Swift package.
Exposes a managed cloud browser to an LLM as MCP tools, letting an agent open sessions, navigate, click, read page elements, and pull data from live websites. Built on Stagehand, so steps are written in plain language, not brittle CSS selectors.
Connects an AI agent to a Supabase project over MCP to run SQL, manage tables and migrations, deploy Edge Functions, fetch keys and types, and read logs. Read-only mode and project scoping cap what the agent can touch.
Connects AI agents to 50+ apps and databases — Notion, Slack, Salesforce, GitHub, Jira — then continuously syncs and indexes their data behind one search API, with auth, ingestion, and retrieval exposed via MCP, REST, and SDKs.
Provides a shared runtime that composes, extends, and observes services in real time by modeling capabilities as discoverable workers, functions, and triggers. It collapses separate integration surfaces (queues, cron, HTTP, observability) into one live catalog so agents and services can call and trace each other immediately.