How to Use the GitHub MCP in Pydantic AI

Q: How do I register the GitHub MCP Server in Pydantic AI?

Instantiate the MCPToolset with your Vinkius server HTTP endpoint. Then, pass this toolset instance inside the toolsets argument of your Agent constructor to automatically register tools like getrepositorydetails with full type validation.

Build type-safe GitHub agents with Pydantic AI that validate repository data at runtime before execution.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GitHub MCP to Pydantic AI

Create your Vinkius account to connect GitHub 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 GitHub with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe issue creation with Pydantic AI

The `create_new_issue` tool allows your agent to open tracked issues while Pydantic AI validates the input payload against strict schemas. If your agent attempts to pass malformed data, the framework catches it before hitting the GitHub API. You can pair this with `list_repository_issues` to verify the state of open tickets. The returned JSON is parsed directly into Python models, eliminating parsing errors and runtime crashes in production.

Fail-safe profile and organization lookups

The `get_my_profile` tool fetches your authenticated user profile with guaranteed type safety. Pydantic AI inspects the API response, ensuring fields like email and username match your defined Python schemas. This strict validation extends to `list_my_organizations` and `list_my_repositories` over the MCP connection. If GitHub changes its API payload structure, your agent fails loudly and safely instead of passing corrupted data downstream.

Validated pull request and branch audits

The `list_pull_requests` tool retrieves open pull requests for automated code reviews. Pydantic AI parses the pull request metadata, giving you clean, typed objects that your agent can safely analyze. Your agent can also use `list_repo_branches` to inspect the branch topology. This MCP Server maps out target branches and ensures your automated merging scripts only target valid git refs.

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-extended-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

Instantiate the `MCPToolset` with your Vinkius server HTTP endpoint. Then, pass this toolset instance inside the `toolsets` argument of your `Agent` constructor to automatically register tools like `get_repository_details` with full type validation.

The framework raises a validation error immediately if the server response does not match the expected schema. This prevents your agent from hallucinating properties on objects returned by `list_recent_notifications` or `list_my_gists`.

Yes, Pydantic AI is model-agnostic, meaning you can connect this toolset to local models or commercial APIs. The agent will use tools like `search_repositories` to find codebases regardless of which LLM powers it.

Yes, the Vinkius platform supports both Streamable HTTP and SSE transports. You can configure your `MCPToolset` to connect via the transport that best fits your networking architecture.

The server processes file contents, issue descriptions, user profiles, and organization structures. Vinkius runs the server in an ephemeral sandbox, and all connections are secured with TLS to ensure no repository data is saved to disk.

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