Schema | pydantic-mcp

Describes the environment variables required to run the server.

Name	Required	Description
`PYDANTIC_MCP_HOST`	No	The host address to bind to when using HTTP transport.
`PYDANTIC_MCP_PORT`	No	The port number to bind to when using HTTP transport.
`PYDANTIC_MCP_TRANSPORT`	No	Transport method for the MCP server (e.g., 'stdio' or 'http').
`PYDANTIC_MCP_ERROR_HISTORY_LIMIT`	No	Limit for the number of errors kept in history.
`PYDANTIC_MCP_ALLOWED_IMPORT_ROOTS`	No	Roots allowed for imports (e.g., paths to your application code).
`PYDANTIC_MCP_DEFAULT_SCAN_PACKAGES`	No	Packages to scan for Pydantic models by default.
`PYDANTIC_MCP_IMPORT_TIMEOUT_SECONDS`	No	Timeout for importing packages in seconds.

Features and capabilities supported by this server

Capability	Details
`tools`	{ "listChanged": true }
`prompts`	{ "listChanged": false }
`resources`	{ "subscribe": false, "listChanged": false }
`experimental`	{}

Functions exposed to the LLM to take actions

Name	Description
list_models	Discover exported Pydantic models in configured packages.
inspect_type	Resolve a Python type annotation or model into a structured description.
explain_model	Turn a model or type into a human-readable contract.
validate_data	Validate input against a model name or Python type expression.
serialize_data	Dump validated data using Pydantic serialization behavior.
generate_json_schema	Generate JSON Schema for a model or type.
create_example_payload	Generate example valid and invalid payloads for a target model or type.
compare_validation_modes	Compare model, TypeAdapter, strict, and JSON-vs-Python validation behavior.
migrate_v1_to_v2	Analyze a snippet or model source for common Pydantic v1-to-v2 migration issues.
parse_partial_json	Best-effort parse partial JSON, then validate the parsed fragment.
generate_model_from_json	Infer candidate Pydantic models from a JSON string or JSON-like payload.

Interactive templates invoked by user choice

Name	Description
`explain model`	Explain a model's fields, constraints, defaults, aliases, and edge cases.
`generate api contract docs`	Turn a model or schema into docs for API consumers.
`debug validation error`	Given a validation trace, suggest the smallest payload fix.
`design a model from example json`	Infer a candidate Pydantic model from sample payloads.
`review schema compatibility`	Compare two models or schemas for breaking changes.
`migrate to pydantic v2`	Inspect code and produce a migration checklist.

Contextual data attached and managed by the client

pydantic-mcp