pydantic-mcp is an MCP server for inspecting, validating, and working with Pydantic models and Python type contracts in LLM workflows, providing deterministic validation, serialization, schema generation, and migration assistance.

• Discover Models: Scan configured packages to find exported Pydantic BaseModel classes, with optional filtering and package selection.

• Inspect & Explain Types: Resolve any Python type annotation or model into a structured description, and generate human-readable documentation covering fields, defaults, aliases, constraints, and nested structures.

• Validate Data: Validate arbitrary payloads against a model or Python type expression, with support for strict mode, Python/JSON mode, and validation context.

• Serialize Data: Dump validated data using Pydantic serialization, with options for aliases, excluding unset/none/default values, round-trip mode, and Python/JSON output.

• Generate JSON Schema: Produce validation or serialization JSON Schema for any model or type, with optional $defs definitions.

• Create Example Payloads: Generate valid (and optionally invalid) example payloads for a target model or type.

• Compare Validation Modes: Contrast model vs. TypeAdapter, strict vs. non-strict, and Python vs. JSON validation behavior for the same data.

• Migrate v1 to v2: Analyze code snippets or model sources for common Pydantic v1-to-v2 migration issues, with optional auto-fix suggestions.

• Parse Partial JSON: Best-effort parse incomplete JSON strings and validate the resulting fragment against a target type.

• Generate Model from JSON: Infer and generate candidate Pydantic model definitions from a sample JSON payload.

• MCP Integration: Expose tools, resources, and prompts via the MCP protocol, with HTTP health and readiness endpoints for server monitoring.

Enables inspection and management of Pydantic models, offering capabilities for data validation, serialization, JSON schema generation, and migration from Pydantic v1 to v2.

Provides tools for resolving and inspecting Python type contracts and expressions across configured packages and import paths.

1. Click on "Install Server".

2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.

3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@pydantic-mcp Generate a JSON schema for the UserProfile model"

That's it! The server will respond to your query, and you can continue using it as needed.

Here is a step-by-step guide with screenshots.