Can my AI agent use notes as persistent memory across sessions?

Absolutely — this is a core design goal. Use `create_note` to store decisions, context, or meeting summaries as markdown notes. Organize them into folders with `create_note_folder` and `move_note_to_folder`. Use `toggle_note_share` to publish findings to the team. Every edit is versioned via `note_revisions` so you can track how knowledge evolves.

Can the agent search across everything in my workspace at once?

Yes! The `global_search` tool performs a unified search across tasks, wiki pages, discussions, user stories, sprints, and notes. Results are grouped by resource type, so you instantly see where every mention lives. It's the fastest way to find anything in your workspace.

Can the agent participate in team discussions and reply to threads?

Yes. Use `send_message` to post updates to any discussion channel, and `reply_to_message` for threaded conversations. The agent can also create channels with `create_channel`, search message history with `search_channel_messages`, and review thread replies with `thread_replies` — enabling fully automated status updates and knowledge sharing.

GitScrum Knowledge MCP Server for OpenAI Agents SDK 28 tools — connect in under 2 minutes

Name: GitScrum Knowledge
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 28 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect GitScrum Knowledge through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

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 agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

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

        agent = Agent(
            name="GitScrum Knowledge Assistant",
            instructions=(
                "You help users interact with GitScrum Knowledge. "
                "You have access to 28 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from GitScrum Knowledge"
        )
        print(result.final_output)

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 GitScrum Knowledge MCP Server

What you can do

Agent memory via notes — create, update, share, and organize notes as persistent AI memory with full revision history and folder management
Wiki knowledge base — build and maintain project documentation with nested pages, markdown content, revision tracking, and restore capabilities
Team discussions — create channels, send messages, search conversations, and reply in threads for structured team communication
Global search — search across tasks, wiki pages, discussions, user stories, sprints, and notes in a single query
Knowledge versioning — track how information evolves over time with note and wiki revision histories

The OpenAI Agents SDK auto-discovers all 28 tools from GitScrum Knowledge through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries GitScrum Knowledge, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

The GitScrum Knowledge MCP Server exposes 28 tools through the Vinkius. Connect it to OpenAI Agents SDK 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 GitScrum Knowledge to OpenAI Agents SDK via MCP

Follow these steps to integrate the GitScrum Knowledge MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 28 tools from GitScrum Knowledge

Why Use OpenAI Agents SDK with the GitScrum Knowledge MCP Server

OpenAI Agents SDK provides unique advantages when paired with GitScrum Knowledge through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

GitScrum Knowledge + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the GitScrum Knowledge MCP Server delivers measurable value.

Automated workflows: build agents that query GitScrum Knowledge, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries GitScrum Knowledge, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through GitScrum Knowledge tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query GitScrum Knowledge to resolve tickets, look up records, and update statuses without human intervention

GitScrum Knowledge MCP Tools for OpenAI Agents SDK (28)

These 28 tools become available when you connect GitScrum Knowledge to OpenAI Agents SDK via MCP:

channel_messages

Get messages in a channel

create_channel

Create a discussion channel

create_note

Use this as persistent agent memory: store decisions, context, meeting notes, or ADRs. Content supports full markdown. Create a new note

create_note_folder

E.g., "Agent Memory", "Architecture Decisions", "Meeting Notes". Create a note folder

create_wiki_page

Supports nested pages via parent_uuid. Create a wiki page

delete_note

Delete a note permanently

delete_wiki_page

Delete a wiki page

get_channel

Get channel details

get_wiki_page

Get a wiki page with full content

global_search

Returns grouped results by resource type. Search across all workspace resources

list_channels

List discussion channels

list_discussions

List all discussions in a project

list_note_folders

Use folders to categorize agent memory by topic or project. List note folders

list_notes

Perfect for agent memory — store context, decisions, and key information across sessions. List all notes in the workspace

list_wiki_pages

Wiki pages support markdown and nested hierarchies. List wiki pages in a project

move_note_to_folder

Move a note into a folder

note_revisions

Useful for tracking how knowledge evolved over time. Get note revision history

rename_note_folder

Rename a note folder

reply_to_message

Reply to a message in a thread

restore_wiki_revision

Restore a wiki page to a previous revision

search_channel_messages

Search messages in a channel

search_wiki

Search wiki pages

send_message

Useful for agents to communicate findings or status updates. Send a message to a channel

thread_replies

Get thread replies for a message

toggle_note_share

Useful for publishing agent findings to the team. Toggle note sharing visibility

update_note

Use to append context or refine agent memory over time. Update an existing note

update_wiki_page

Update a wiki page

wiki_revisions

Get wiki page revision history

Example Prompts for GitScrum Knowledge in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with GitScrum Knowledge immediately.

"Save a note with today's architecture decision about using event sourcing."

"Search everything in our workspace for 'payment gateway integration'."

"Post an update in the #engineering channel about today's deployment."

Troubleshooting GitScrum Knowledge MCP Server with OpenAI Agents SDK

Common issues when connecting GitScrum Knowledge to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

GitScrum Knowledge + OpenAI Agents SDK FAQ

Common questions about integrating GitScrum Knowledge MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.