---
title: "Pydantic AI: MCP vendor profile | Agent MCP Directory"
description: "Pydantic AI: SDK or framework. Products: Pydantic AI. 6 dated facts, prices and two checks, each sourced, read 5 November 2026."
canonical: https://agentmcpdirectory.com/vendors/pydantic-ai
site: "Agent MCP Directory"
last_updated: 2026-11-05
section: "Vendors"
---

# Pydantic AI: MCP vendor profile | Agent MCP Directory

> Pydantic AI: SDK or framework. Products: Pydantic AI. 6 dated facts, prices and two checks, each sourced, read 5 November 2026.

Source: https://agentmcpdirectory.com/vendors/pydantic-ai
Site: Agent MCP Directory
Last reviewed: 2026-11-05

# Pydantic AI: MCP vendor profile

Pydantic AI is a Python agent framework that connects agents to MCP servers through an MCP capability, runs servers locally by default with an opt-in for model providers' native MCP, and can serve agents as MCP servers, as documented by the vendor.

## At a glance

| Type | SDKs and frameworks |
| --- | --- |
| Operator | Pydantic |
| Home | ai.pydantic.dev |
| Price | open source |
| Read | 5 November 2026 |

## What it does for this layer

Pydantic AI says agents "can connect to MCP servers and use their tools" and can also be used within MCP servers ([ai.pydantic.dev](https://ai.pydantic.dev/mcp/)). The recommended way to give a Pydantic AI agent an MCP server is the MCP capability, which runs the server locally by default to keep credentials, hooks and tracing under the developer's control ([ai.pydantic.dev](https://ai.pydantic.dev/mcp/)). With native=True, the Pydantic AI MCP capability uses the model provider's native MCP support and falls back to local if the model does not support it ([ai.pydantic.dev](https://ai.pydantic.dev/mcp/)).

Pydantic AI's local MCP side accepts a URL, a FastMCP transport, a pre-built fastmcp.Client, an in-process FastMCP server or a local script ([ai.pydantic.dev](https://ai.pydantic.dev/mcp/)). For lower-level control, Pydantic AI offers MCPToolset to manage the toolset lifecycle or share one MCP server across several agents, and MCPServerTool for provider-native MCP only ([ai.pydantic.dev](https://ai.pydantic.dev/mcp/)). Pydantic's MCP page names its own Logfire MCP server for logs, traces and metrics and a Run Python MCP server that runs code in a sandbox ([ai.pydantic.dev](https://ai.pydantic.dev/mcp/)).

## Products and plans

| Product | What it does | Price |
| --- | --- | --- |
| Pydantic AI | Open-source Python agent framework with MCP client and server support. | open source; from 0 USD (source, as of 5 November 2026) |

## Checks on its own domain

| Check | Domain | Result | Scanned | Method |
| --- | --- | --- | --- | --- |
| Ora cached score | pydantic.dev | 90 of 100, grade A | 4 November 2026 | how it was taken |
| Cloudflare agent-readiness scan | pydantic.dev | 60 of 100, L5 Agent-Native; 9 of 15 counted checks passed | 5 November 2026 | how it was taken |

## What it does not do

-   Pydantic AI does not host remote MCP servers; it runs them locally or calls them by URL.

## Related on this site

Type

-   [SDKs and frameworks](https://agentmcpdirectory.com/vendors/by-type/sdk-or-framework/)

Section

-   [All vendors](https://agentmcpdirectory.com/vendors/)

Edition

4 November 2026

Method

[How rows are verified](https://agentmcpdirectory.com/method/)

Data

[CSV and JSON](https://agentmcpdirectory.com/data/)

Markdown

[This page as markdown](https://agentmcpdirectory.com/vendors/pydantic-ai/index.md)

## Sources

-   [Model Context Protocol (MCP) | Pydantic Docs](https://ai.pydantic.dev/mcp/), read 5 November 2026

Last reviewed 5 November 2026