How to Use the GitScrum Knowledge MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK use GitScrum Knowledge to pass context between agents?

Yes, agents write shared context to notes using createnote and updatenote. When a handoff occurs, the receiving agent reads the updated note to resume the task with full context.

Q: Does this MCP Server support markdown for wiki pages?

Yes, createwikipage and updatewikipage support standard markdown formatting. Your agent can write tables, code blocks, and headers directly into your GitScrum wiki.

Build production-ready agents with OpenAI Agents SDK that read, write, and search your GitScrum Knowledge workspace with built-in guardrails.

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 OpenAI Agents SDK

Create your Vinkius account to connect GitScrum Knowledge to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Persistent agent memory via notes

`create_note` serves as the primary tool for establishing long-term memory across your agent runs. Your agent can write markdown files to document decisions, architecture choices, or meeting outcomes directly in your workspace. It keeps your deployment history and system context organized without manual intervention. Use `update_note` to append new information or refine existing records as your agents complete tasks. If you need to organize these memories by topic, `create_note_folder` and `move_note_to_folder` let your system structure its own workspace dynamically.

Structured wiki and revision management

`create_wiki_page` builds hierarchical documentation inside your project using parent UUIDs. This tool lets your OpenAI Agents SDK write structured guides and technical references that your human team can read. When requirements shift, `update_wiki_page` modifies the content programmatically. You can audit how your documentation changes over time using `wiki_revisions`. If an agent makes a mistake or writes incorrect data, `restore_wiki_revision` rolls the page back to a clean state instantly.

Global workspace search for an MCP Server

`global_search` queries all notes, wiki pages, and discussion channels in a single call. This MCP tool returns grouped results by resource type, saving your agent from executing multiple search loops. It speeds up context retrieval during complex task execution. For targeted lookups, the agent can use `search_wiki` or `search_channel_messages` to pinpoint specific files or conversations. This keeps the agent's context window small and focused on relevant data.

Setup guide

Set up GitScrum Knowledge MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all GitScrum Knowledge tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives GitScrum Knowledge tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate GitScrum Knowledge tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="GitScrum Knowledge Agent",
            instructions="You have access to GitScrum Knowledge tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the SDK and streamable HTTP package, then define your server configuration pointing to the Vinkius endpoint. This MCP Server lets your agent auto-discover all 28 tools during initialization.

Yes, agents write shared context to notes using `create_note` and `update_note`. When a handoff occurs, the receiving agent reads the updated note to resume the task with full context.

Yes, `create_wiki_page` and `update_wiki_page` support standard markdown formatting. Your agent can write tables, code blocks, and headers directly into your GitScrum wiki.

The SDK uses the MCP search tool to query all workspace resources in one round trip. You can set `cacheToolsList=True` in your connection manager to avoid fetching the tool definitions on every single request.

Your GitScrum wiki pages, notes, and messages are processed through an isolated V8 sandbox on Vinkius. We do not store your credentials or write history, and transport is secured via HTTPS with single-token authentication.

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