How to Use the DevDocs MCP in Pydantic AI

Get type-safe documentation retrieval for your Pydantic AI agents using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DevDocs MCP to Pydantic AI

Create your Vinkius account to connect DevDocs to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup DevDocs with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validated Library Discovery

Use `list_libraries` to get a list of available docs that your Pydantic AI agent can consume. Every response is checked against your defined models. This prevents the agent from operating on malformed data. You get a clean list of slugs ready for further investigation.

Type-Safe Search Queries

Run `search_docs` to find the exact documentation path for any framework. The MCP tools return predictable structures that integrate perfectly with your schema. Your agent won't hallucinate a documentation path because the Pydantic models force it to stick to the returned structure. It ensures your research phase is as rigid as your code.

Clean Markdown Injection

Call `read_page` to retrieve documentation content in a format your agent can validate. It strips away the web clutter and leaves only the technical spec. This allows your Pydantic AI agent to process documentation with total confidence. If the data is weird, the validation fails and you catch it immediately.

Setup guide

Set up DevDocs MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "devdocs-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to DevDocs tools.",
)

result = await agent.run("List recent DevDocs transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by DevDocs. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect DevDocs now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about DevDocs MCP in Pydantic AI

The MCPToolset automatically maps tool responses to Pydantic models. If the server returns unexpected data, the agent triggers a validation error before proceeding.

Yes. The server supports non-blocking I/O, allowing your Pydantic AI agent to fetch multiple documentation pages concurrently without stalling your pipeline.

The server requires an active connection to fetch data from the DevDocs API. It is designed for real-time retrieval, not as an offline cache.

Pydantic AI catches the exception during tool execution. You can define custom error handling logic in your agent to retry or notify the developer.

Only your search strings and page requests are sent. The server does not handle any of your application's private documentation or user data.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python