How to Use the GitScrum MCP in Pydantic AI

Q: How do I set up the GitScrum MCP toolset in Pydantic AI?

Initialize the MCPToolset with your Vinkius HTTP URL and pass it to the toolsets parameter of your Agent. The framework automatically registers all 16 tools, including listtasks and listworkflows.

Q: Can Pydantic AI agents generate GitScrum workspace statistics?

Yes, the agent calls workspacestats and projectstats to fetch structured performance metrics. The returned data is parsed into strongly-typed Python models for immediate down-stream analysis.

Q: How does Pydantic AI handle GitScrum label validation using MCP?

The agent uses listlabels to pull the exact allowed labels for a project. It validates any proposed label updates against this list before modifying a task, ensuring no invalid tags are created.

Build type-safe Pydantic AI agents that interact with GitScrum boards with strict runtime validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GitScrum MCP to Pydantic AI

Create your Vinkius account to connect GitScrum 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 GitScrum with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Task Retrieval

The `get_task` and `list_tasks` tools return structured board data that Pydantic AI validates against runtime schemas. Connecting this MCP server ensures that if the GitScrum API returns a malformed payload, your agent catches the error immediately. This strict validation guarantees that your agent always has clean task descriptions, correct labels, and valid status fields. You write safer code that won't break when the external API changes.

Verified Board Configuration

The `create_project` and `create_workspace` tools let your Pydantic AI agent build new boards with guaranteed structural integrity. Your agent validates the input parameters before sending the request, preventing half-baked setups. It checks the resulting configuration using `get_project` to ensure all workflows and labels are correctly applied. Programmatic board templates become easy to enforce across your entire engineering team.

Strict Role and Permission Checking on this MCP Server

The `my_role` and `get_me` tools provide your Pydantic AI agent with authenticated user context that is validated at runtime. Your agent checks these permissions before executing any write operations on this MCP Server. It uses `list_project_members` to verify target assignees before updating task details. This verification prevents the agent from assigning work to non-existent users or locked accounts.

Setup guide

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

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

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

Initialize the `MCPToolset` with your Vinkius HTTP URL and pass it to the `toolsets` parameter of your Agent. The framework automatically registers all 16 tools, including `list_tasks` and `list_workflows`.

The framework will raise a validation error at runtime, preventing the agent from processing bad data. This ensures your agent never writes corrupted task statuses or malformed project descriptions back to your boards.

Yes, the agent calls `workspace_stats` and `project_stats` to fetch structured performance metrics. The returned data is parsed into strongly-typed Python models for immediate down-stream analysis.

The agent uses `list_labels` to pull the exact allowed labels for a project. It validates any proposed label updates against this list before modifying a task, ensuring no invalid tags are created.

Your GitScrum API tokens and task data are transmitted over secure, encrypted transport layers directly to isolated Vinkius sandboxes. No credentials or board schemas are stored on disk. All MCP data processing occurs in memory and is destroyed immediately after the tool execution completes.

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