Can my agent list open changes across all Gerrit projects?

Yes. Use the 'query_changes' tool with the query 'status:open'. The agent will retrieve the global array of all matching changes, including subjects, numbers, and owners natively.

How do I see the approval labels (Code-Review, Verified) for a specific change via chat?

Use the 'get_change' tool. It retrieves the full details of a Gerrit change, including the 'labels' section where you can see the Code-Review and Verified scores assigned by reviewers natively.

Can I check which groups have access to a specific project through the agent?

Absolutely. Use the 'list_groups' tool to identify existing groups. While project access rules are often defined in the project settings, the agent can help you verify group definitions and ownership within your organizational tree flawlessly.

Gerrit MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Gerrit
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Gerrit through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Gerrit "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Gerrit?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Gerrit MCP Server

Connect your Gerrit Code Review instance to any AI agent and take full control of your collaborative code reviews, project repositories, and patch set management through natural conversation.

Pydantic AI validates every Gerrit tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Change & Review Orchestration — Query Gerrit changes using advanced syntax like 'status:open' or 'owner:self' to retrieve subjects, numbers, and owners natively
Patch Set Auditing — List all revisions (patch sets) of a change to track commit SHAs, uploader info, and parent commits for detailed version history flawlessly
Reviewer & Approval Oversight — Enumerate reviewers on any change and retrieve approval labels (Code-Review, Verified) to monitor the consensus process synchronousy
Project & Repository Navigation — List all projects and retrieve detailed metadata including states (ACTIVE/READ_ONLY) and default branch configurations securely
Branch Management — Identify and list all branches within a Gerrit project, extracting the latest commit SHAs to verify repository boundaries natively
Account & Identity Discovery — Fetch authenticated user profile information and list associated verified email addresses to verify account contexts flawlessy
Group & Access Auditing — List all Gerrit groups to identify who controls access to projects and grants specific permissions within your organizational tree

The Gerrit MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Gerrit to Pydantic AI via MCP

Follow these steps to integrate the Gerrit MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Gerrit with type-safe schemas

Why Use Pydantic AI with the Gerrit MCP Server

Pydantic AI provides unique advantages when paired with Gerrit through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Gerrit integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Gerrit connection logic from agent behavior for testable, maintainable code

Gerrit + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Gerrit MCP Server delivers measurable value.

Type-safe data pipelines: query Gerrit with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Gerrit tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Gerrit and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Gerrit responses and write comprehensive agent tests

Gerrit MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Gerrit to Pydantic AI via MCP:

get_account

Get the authenticated Gerrit account

get_change

Get full details of a Gerrit change

get_project

Get full details of a Gerrit project

list_branches

List all branches in a Gerrit project

list_emails

List all email addresses associated with the authenticated Gerrit account

list_groups

Returns group names, IDs, owners, and descriptions. List all groups on Gerrit

list_patchsets

List all patch sets (revisions) of a Gerrit change

list_projects

List all projects (repositories) on Gerrit

list_reviewers

List all reviewers on a Gerrit change

query_changes

Uses syntax: "status:open", "owner:self", "project:myproj". Returns subjects, numbers, statuses, owners, projects, patches. Query changes (code reviews) on Gerrit

Example Prompts for Gerrit in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Gerrit immediately.

"List my open changes in project 'core-engine'"

"Who are the reviewers for change #501?"

"List all branches in project 'frontend-v2'"

Troubleshooting Gerrit MCP Server with Pydantic AI

Common issues when connecting Gerrit to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Gerrit + Pydantic AI FAQ

Common questions about integrating Gerrit MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Gerrit MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.