Pydantic · Agent SDKs
Pydantic AI
Build typed agents with validated outputs, dependency injection, and model integrations.
- Languages
- Python
- API surface
- Typed Python SDK
- MCP capability
- MCP client
APIs & SDKs
Build agents with typed dependencies and validated output structures. The library exposes a Python API for model calls, tools and application integration.
Explore the developer documentation ↗Integrations
Model integrations and dependency injection connect agents to application services. Typed results help validate data passed to downstream code.
View framework integration resources ↗MCP client
MCP support
Pydantic AI publishes an MCP client guide for connecting agents to external server tools. Use that guide to configure transports and the lifetime of the connection.
Evidence scope: Python MCP client guide. Documentation reviewed; runtime compatibility has not been tested.
Sources & review
Integration notes reviewed . Check the linked documentation for current package versions, language support and authentication requirements.
How we review directory entries →Related frameworks
Explore frameworks in the same category or from the same maintainer.
AI SDK
Mastra
LangChain