How to Use the GitHub MCP in Pydantic AI

Q: How do I initialize the GitHub toolset in pydantic-ai?

Use the MCPToolset class with your Vinkius HTTP endpoint to connect the server. Pass this toolset to your Pydantic AI Agent constructor to instantly expose tools like getmygithubprofile to your model.

Q: Can I use pydantic-ai to search GitHub repositories securely?

Yes, your agent can call searchgithubrepositories to find public and private repos. The framework validates the search results against strict schemas, ensuring your application only processes well-formed repository metadata.

Build type-safe agent workflows with Pydantic AI and the GitHub MCP Server to guarantee runtime code validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect GitHub MCP to Pydantic AI

Create your Vinkius account to connect GitHub to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup GitHub with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Validate repository metadata at runtime

The `get_repository_details` tool fetches structured metadata that Pydantic AI validates against strict Python type models before your code runs. If the GitHub API returns unexpected fields, your agent fails immediately instead of processing corrupted data. This type-safe execution ensures that your automated pipelines never crash silently. Your agent can safely query `list_user_repositories` and know exactly what data structures to expect in every response.

Ensure strict issue tracking validation

The `create_new_issue` tool allows your agent to open issues, with Pydantic AI enforcing exact schemas on the title, body, and labels. This guarantees that every ticket created by your agent conforms to your project's strict formatting standards. When reading existing issues with `list_repo_issues`, the framework parses the response data into type-safe Python objects. Your agent can then safely extract issue numbers and assignees without worrying about missing fields.

Search code safely using the Pydantic AI MCP Server

The `search_github_code` tool returns code snippets that your Pydantic AI agent can search and analyze. Because the framework is model-agnostic, you can use these search results with OpenAI, Anthropic, or local models while maintaining strict type validation. You can also call `get_file_contents` to read raw files, ensuring that the file path and content structures match your defined Pydantic models. This prevents prompt injections from tricking your agent into reading unauthorized files.

Setup guide

Set up GitHub 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": {
        "github-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent GitHub 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 GitHub. 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 GitHub 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 GitHub MCP in Pydantic AI

Use the `MCPToolset` class with your Vinkius HTTP endpoint to connect the server. Pass this toolset to your Pydantic AI Agent constructor to instantly expose tools like `get_my_github_profile` to your model.

If the GitHub API returns unexpected data, Pydantic AI will raise a validation error at runtime. This prevents your agent from making decisions based on malformed or incomplete repository data.

Yes, your agent can call `search_github_repositories` to find public and private repos. The framework validates the search results against strict schemas, ensuring your application only processes well-formed repository metadata.

Yes, this MCP Server must be running externally, and Pydantic AI connects to it via the Streamable HTTP or SSE transport. Vinkius hosts and manages this server for you, so you only need to provide the endpoint URL.

Your GitHub API tokens are passed securely through HTTPS headers and are never stored on disk. The Vinkius MCP infrastructure uses zero-trust, ephemeral sandboxes to execute each tool call, ensuring your access tokens are immediately discarded after use.

Use it with your favorite AI tools

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

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript