Runs SQL queries against 40+ data sources — local files, databases, and apps like Notion, GitHub, and Google — through one SQLite-based engine. Doubles as an MCP server, so LLMs like Claude or ChatGPT can query that data directly via SQL.
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.
Agentive operating system for physical robots that lets developers compose agent-native modules in Python to connect perception, spatial memory, and control across humanoids, quadrupeds, drones, and simulators.
Converts PDF, Office docs, EPUB, images, audio, HTML and ZIP archives into structured Markdown for LLM pipelines, preserving headings, tables and links instead of visual layout. Adds optional OCR, audio transcription and LLM image captions.
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.
Expose Python functions as MCP‑compliant servers and clients so LLMs can call tools and resources directly; includes automatic schema generation, input validation, transport negotiation, authentication, and in‑conversation interactive UIs.
Provides a local-first Markdown knowledge graph that LLMs and humans can both read and write via the Model Context Protocol (MCP). Features two-way, editable notes, semantic search (embeddings + hybrid ranking), and optional cloud sync and team workspaces.
Bridges AI assistants to Jira and Confluence via the Model Context Protocol, exposing ~72 tools for JQL search, issue/page CRUD, status transitions, and comments. Supports Cloud and Server/Data Center with API-token, PAT, or OAuth 2.0 auth.
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.
Provides programmatic access to Google Flights via a Python library, CLI, and an MCP server — enabling assistants and apps to search flights with filters (time windows, cabin, stops, airlines) by reverse‑engineered API rather than HTML scraping.
Wires retrievers, rerankers, and generators as standalone MCP servers orchestrated in YAML, so iterative RAG logic fits in dozens of lines instead of glue code. Adds loops, conditional branches, one-command web UIs, and shared evaluation benchmarks.