How to Use the Forgejo (Gitea Fork) MCP in Pydantic AI

Q: How do I initialize the Forgejo (Gitea Fork) MCP Server with Pydantic AI?

Install pydantic-ai-slimmcp. Create an MCPToolset pointing to your HTTP endpoint and pass it to the toolsets list when building your Agent.

Q: Why is MCPServerHTTP deprecated when connecting Pydantic AI to Forgejo (Gitea Fork)?

Pydantic AI unified its connection approach. You now use MCPToolset with an HTTP or SSE URL instead of the older, specific transport classes.

Enforce strict runtime validation on your repository actions using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Forgejo (Gitea Fork) MCP to Pydantic AI

Create your Vinkius account to connect Forgejo (Gitea Fork) 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 Forgejo (Gitea Fork) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe MCP Server Pipelines

The `dispatch_workflow` tool lets your agent manually trigger Forgejo Actions. CI/CD automation requires exact inputs. If the agent hallucinates a branch name or workflow ID, Pydantic AI catches the malformed request before it hits your server. You care about correctness. When the agent fires the workflow, the MCP response validates against your defined Pydantic models. If the API returns unexpected JSON, the framework throws a loud validation error instead of silently corrupting your deployment state.

Strictly Validated Tokens

This integration includes the `create_token` tool for generating new API tokens on demand. Managing credentials dynamically is risky if the agent gets confused about scopes. Pydantic AI ensures the agent passes exactly the correct parameters to the token endpoint. There is no room for silent failures here. The agent requests a token, and the framework verifies the response structure. You get a guaranteed valid token string back, ready to be injected into your next automated task.

Version Metadata Verification

The `get_forgejo_version` and `get_gitea_version` tools extract the instance version strings. Forked software means API endpoints drift over time. Your agent queries these tools to verify the exact server capabilities before attempting complex operations. Pydantic AI forces the agent to handle the version data correctly. If the version string format changes unexpectedly, the validation fails immediately. Your agent stops execution rather than making blind, destructive API calls against an unknown server version.

Setup guide

Set up Forgejo (Gitea Fork) 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": {
        "forgejo-gitea-fork-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Forgejo (Gitea Fork) 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 Forgejo. 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 Forgejo (Gitea Fork) 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 Forgejo (Gitea Fork) MCP in Pydantic AI

Install `pydantic-ai-slim[mcp]`. Create an `MCPToolset` pointing to your HTTP endpoint and pass it to the `toolsets` list when building your Agent.

Yes. The framework is model-agnostic. You can use local LLMs to trigger workflows or generate tokens, provided the model understands tool calling.

Pydantic AI fails loudly. It raises a validation error at runtime, halting the agent before it can act on bad information.

Pydantic AI unified its connection approach. You now use `MCPToolset` with an HTTP or SSE URL instead of the older, specific transport classes.

The server interacts directly with API tokens, version numbers, and workflow execution parameters. Pydantic AI keeps this data strictly within your local Python process memory. It enforces strict schema boundaries so no sensitive strings leak into unintended external API calls.

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