Back to MCP Servers

Pydantic Ai

Run Python code in a secure sandbox via MCP tool calls

code-executionpythonai
By pydantic
19k2.6kUpdated 1 day agoPythonMIT

Installation

npx -y pydantic-ai

Configuration

{
  "mcpServers": {
    "pydantic-ai": {
      "command": "npx",
      "args": ["-y", "pydantic-ai"]
    }
  }
}

How to use

  1. Run the installation command above (if needed)
  2. Open your Claude Code settings file (~/.claude/settings.json)
  3. Add the configuration to the mcpServers section
  4. Restart Claude Code to apply changes
<div align="center"> <a href="https://pydantic.dev/docs/ai/"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://pydantic.dev/docs/ai/img/pydantic-ai-dark.svg"> <img src="https://pydantic.dev/docs/ai/img/pydantic-ai-light.svg" alt="Pydantic AI"> </picture> </a> </div> <div align="center"> <h3>How Python does AI</h3> </div> <div align="center"> <a href="https://github.com/pydantic/pydantic-ai/actions/workflows/ci.yml?query=branch%3Amain"><img src="https://github.com/pydantic/pydantic-ai/actions/workflows/ci.yml/badge.svg?event=push" alt="CI"></a> <a href="https://coverage-badge.samuelcolvin.workers.dev/redirect/pydantic/pydantic-ai"><img src="https://coverage-badge.samuelcolvin.workers.dev/pydantic/pydantic-ai.svg" alt="Coverage"></a> <a href="https://pypi.python.org/pypi/pydantic-ai"><img src="https://img.shields.io/pypi/v/pydantic-ai.svg" alt="PyPI"></a> <a href="https://github.com/pydantic/pydantic-ai"><img src="https://img.shields.io/pypi/pyversions/pydantic-ai.svg" alt="versions"></a> <a href="https://github.com/pydantic/pydantic-ai/blob/main/LICENSE"><img src="https://img.shields.io/github/license/pydantic/pydantic-ai.svg?v" alt="license"></a> <a href="https://logfire.pydantic.dev/docs/join-slack/"><img src="https://img.shields.io/badge/Slack-Join%20Slack-4A154B?logo=slack" alt="Join Slack" /></a> </div> <p align="center"> Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end. </p>

Pydantic AI is the Python AI SDK: a typed, extensible agent loop with every model a string swap away. The same agent runs everywhere you need it: behind a web frontend, in the terminal, on a voice call, on a durable background queue, or as a plain object you call run() on. Image generation and embeddings come in the same box.

Pydantic AI Harness has everything an agent needs for complex, long-running work, snapped on as capabilities, from memory, sub-agents, and context management to a complete coding agent.

View the complete documentation at pydantic.dev/docs/ai.

What are you building?

From simple typed data extraction to complex, long-running multi-agent collaboration, Pydantic AI and Pydantic AI Harness have got you covered.

Coding agent

A complete coding agent in your terminal: workspace-rooted file access, allowlisted shell, repo orientation, planning, and context management that survives long sessions. Here with web search and a second-opinion advisor snapped on alongside:

uv add pydantic-ai pydantic-ai-harness
from pydantic_ai import Agent
from pydantic_ai.capabilities import WebSearch
from pydantic_ai_harness import Advisor, Coder

agent = Agent(
    'anthropic:claude-fable-5',
    capabilities=[
        Coder(),  # files, shell, repo context, planning, sub-agents, context management
        WebSearch(),  # look up docs and error messages on the web
        Advisor('openai:gpt-5.6-sol'),  # a second opinion from another model when stuck
    ],
)
agent.to_cli_sync()

Coder is a regular combined capability, not a black box: use it whole, or use the blocks it bundles directly; the two are equivalent:

capabilities = [
    FileSystem('.'), Shell(cwd='.'), RepoContext(), Planning(), SubAgents(...),
    ClearToolResults(), WarnNearLimits(), ToolOutputLimits(),
]

Run the file and you're chatting with the agent in your terminal. To try it before writing any code, run the exported coder_agent with clai (the Pydantic AI CLI), via uvx:

uvx --with pydantic-ai-harness clai -a pydantic_ai_harness.coder:coder_agent -m anthropic:claude-fable-5

Build this → Coder, from the Harness

Data extraction

Give the agent an output type and tools, and every run comes back validated and typed:

uv add pydantic-ai
from typing import Literal

from pydantic import BaseModel, Field

from pydantic_ai import Agent, RunContext


class Sentiment(BaseModel):
    label: Literal['positive', 'negative', 'neutral']
    score: float = Field(ge=-1, le=1)


agent = Agent('openai:gpt-5.6-sol', output_type=Sentiment)


@agent.tool
def recent_reviews(ctx: RunContext[None], product: str) -> list[str]:
    """Fetch recent review snippets for a product."""
    return ['The new release fixed everything I complained about!']


result = agent.run_sync('How are people feeling about the Extract app?')
print(result.output)
#> label='positive' score=0.9

The @agent.tool function receives a RunContext that carries your dependencies in; the rest of its signature and its docstring become the tool schema, arguments are validated before your code runs, and the run is guaranteed to return a Sentiment, so your IDE, type checker, and the LLM all agree on the returned type.

Build this → Agents, Function Tools, and Structured Output

Realtime voice

Put the same agent on a live voice session, tools and capabilities included:

uv add "pydantic-ai[openai-realtime]"
import asyncio

from pydantic_ai import Agent
from pydantic_ai.capabilities import MCP

agent = Agent(
    instructions='You are a helpful voice assistant.',
    capabilities=[MCP('https://internal.example.com/mcp')],  # capabilities work in voice too
)

@agent.tool_plain
def order_status(order_id: str) -> str:
    """Look up the status of an order."""
    return f'Order {order_id}: shipped, arriving Thursday.'

async with agent.realtime('openai:gpt-realtime-2.1').session() as session:
    microphone = asyncio.create_task(stream_microphone(session))  # chunks → session.send_audio()
    speaker = asyncio.create_task(play_audio(session.stream_audio()))  # model audio → your speaker
    async for part in session.stream_transcripts():
        print(f'{part.speaker}: {part.transcript}')

The model calls your tools mid-conversation while it keeps talking, and every session is instrumented; voice is just another frontend, on OpenAI Realtime, Gemini Live, Azure, and xAI Grok Voice.

Build this → Realtime Voice

Durable background agent

Attach TemporalDurability and the same agent runs inside a Temporal workflow: every model and tool call becomes a durable activity, so a run working through a background queue survives restarts, failures, and long waits:

uv add "pydantic-ai[temporal]"
from temporalio import workflow

from pydantic_ai import Agent
from pydantic_ai.capabilities import WebFetch, WebSearch
from pydantic_ai.durable_exec.temporal import PydanticAIWorkflow, TemporalDurability

agent = Agent(
    'openai:gpt-5.6-sol',
    instructions='Research the topic and write a structured brief.',
    name='researcher',
    capabilities=[WebSearch(), WebFetch(), TemporalDurability()],
)


@workflow.defn
class ResearchWorkflow(PydanticAIWorkflow):
    __pydantic_ai_agents__ = [agent]

    @workflow.run
    async def run(self, topic: str) -> str:
        result = await agent.run(f'Write a brief on: {topic}')
        return result.output

DBOS and Prefect attach the same way, first-party and co-maintained, with Restate, Kitaru, and Airflow integrations besides.

Build this → Durable Execution

Image generation

Ask for an image and make it the run's typed output:

uv add pydantic-ai
from pathlib import Path

from pydantic_ai import Agent, BinaryImage

agent = Agent('openai:gpt-5.6-sol', output_type=BinaryImage)
result = agent.run_sync('Generate a minimalist logo for a coffee shop called Extract.')
Path('logo.png').write_bytes(result.output.data)

Provider-native generation on models that support it (like this one), a subagent fallback you can configure for the rest, and a standalone image API on the way.

Build this → Image Generation

<!-- Embeddings section parked (bd54): restore by removing this comment. ### Embeddings Embed documents and queries for semantic search or a [RAG pipeline](https://pydantic.dev/docs/ai/examples/data-analytics/rag/): ```python from pydantic_ai import Embedder embedder = Embedder('openai:text-embedding-3-small') result = embedder.embed_query_sync('What is machine learning?') print(len(result.embeddings[0])) #> 1536 ``` Seven providers behind one typed API, [instrumented](https://pydantic.dev/docs/ai/integrations/logfire/) like everything else. It lives next to the agent that will use the results. **Build this →** [Embeddings](https://pydantic.dev/docs/ai/guides/embeddings/) -->

Why Pydantic AI

  • Any model, one Python API. Virtually every model and provider (OpenAI, Anthropic, Google, Bedrock, Azure AI Foundry, Groq, Mistral, xAI, Ollama, and dozens more), swappable with a string, or through the Pydantic AI Gateway: one key for all of them, with failover and cost monitoring built in. No flagship feature is locked to one vendor.

View source on GitHub