"Pydantic" matching MCP servers:

An MCP server for inspecting and interacting with Pydantic models and Python type contracts. It enables LLMs to perform deterministic validation, schema generation, model explanation, and Pydantic v1 to v2 migration analysis.

Serve a pydantic-ai toolset as an MCP server, enabling reuse of tools across agents and MCP surfaces.

An MCP server that gives AI agents read access to a Zotero library, enabling search, item metadata, collections, tags, notes, and full-text search of attached PDFs.

Enables AI coding assistants to inspect FastAPI applications, routers, and Pydantic models, including generating TypeScript interfaces and Zod schemas and discovering backend routes without hallucination.

Exposes FastAPI routes as MCP tools with auto-discovery, Pydantic schema extraction, and built-in observability.

Policy-based governance for AI agent tool calls. YAML policies, approval gates, risk assessment, and audit logging across LangChain, OpenAI, Anthropic, and MCP.

Enables secure execution of Python code in a sandboxed WebAssembly environment using Pyodide and Deno. Automatically handles package management and captures complete execution results including stdout, stderr, and return values.

Model Context Protocol server to run Python code in a sandbox.