How to Use the GitScrum Knowledge MCP in Pydantic AI

Q: How do I set up GitScrum Knowledge with Pydantic AI?

Install the library with MCP support, then initialize the MCPToolset with the Vinkius HTTP endpoint. This MCP Server exposes all 28 tools with strict validation.

Q: Does this MCP Server support the deprecated HTTP client?

No, you should use the unified MCPToolset class for all connections. This handles both streamable HTTP and SSE transports, ensuring a stable MCP connection.

Q: Can I use Pydantic AI to back up my GitScrum Knowledge wiki pages?

Yes, you can use listwikipages to fetch all pages and write them to local storage. Because the outputs are typed, you can easily serialize the wiki structure to JSON or markdown.

Build type-safe knowledge agents with Pydantic AI that query and update your GitScrum workspace 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 Knowledge MCP to Pydantic AI

Create your Vinkius account to connect GitScrum Knowledge 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 Knowledge with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe memory operations using Pydantic AI

`create_note` writes structured markdown memory files with strict schema validation. If your model attempts to write a note with missing fields or malformed markdown, Pydantic AI catches the error at runtime before making the API call. This prevents corrupt or incomplete notes from entering your workspace. You can safely update these records using `update_note` to append new context. The framework guarantees that every note revision matches your defined Python schemas, keeping your agent's memory clean and predictable.

Validated wiki page structures

`create_wiki_page` builds nested documentation hierarchies using parent UUIDs. The tool validates the hierarchy structure so your agent never creates orphaned pages. This ensures your wiki stays organized and easy to navigate for both humans and models. To track changes, `wiki_revisions` returns structured history logs that parse cleanly into Python models. If an agent writes invalid content, `restore_wiki_revision` lets you roll back the page to a validated state.

Structured workspace search via an MCP Server

`global_search` queries your entire workspace and returns structured results grouped by resource type. Pydantic AI validates the MCP search payload to ensure your agent receives clean, typed data. This eliminates parsing errors when handling raw search results. For targeted lookups, `search_wiki` and `search_channel_messages` allow your agent to pinpoint specific information. The framework guarantees that search hits map directly to your local type definitions.

Setup guide

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

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

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

Install the library with MCP support, then initialize the `MCPToolset` with the Vinkius HTTP endpoint. This MCP Server exposes all 28 tools with strict validation.

The framework will raise a validation error immediately instead of passing bad data to your model. This prevents silent failures and ensures your agent only acts on accurate workspace information.

No, you should use the unified `MCPToolset` class for all connections. This handles both streamable HTTP and SSE transports, ensuring a stable MCP connection.

Yes, you can use `list_wiki_pages` to fetch all pages and write them to local storage. Because the outputs are typed, you can easily serialize the wiki structure to JSON or markdown.

Your channel messages, wiki pages, and notes are transmitted over HTTPS directly to the GitScrum API. The Vinkius sandbox acts as an ephemeral proxy, ensuring your workspace credentials never touch persistent storage.

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