An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Gitscrum Knowledge to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Turn your AI agent into a central repository for team knowledge.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 28 capabilities

We ship only the actions that matter.

Capability set01 / 07

01-04

4 capabilities in this set.

Part of 28 available through GitScrum.

  1. 01

    List discussions

    This capability retrieves a list of all discussions within a specific project.

  2. 02

    Create note folder

    Use this to set up new organizational folders like Architecture Decisions or Meeting Notes.

  3. 03

    List note folders

    This capability lists all existing note folders to help your agent navigate organized memory.

  4. 04

    Rename note folder

    This capability allows your agent to change the name of an existing note folder.

Capability set02 / 07

05-08

4 capabilities in this set.

Part of 28 available through GitScrum.

  1. 05

    Search channel messages

    This capability searches through messages within a specific discussion channel.

  2. 06

    Send message

    Your agent uses this to post findings or status updates directly to a channel.

  3. 07

    Delete note

    This capability permanently removes a specific note from the workspace.

  4. 08

    List notes

    This capability pulls a list of all notes in the workspace to provide context to your agent.

Capability set03 / 07

09-12

4 capabilities in this set.

Part of 28 available through GitScrum.

  1. 09

    Note revisions

    Use this to check the version history of a specific note.

  2. 10

    Get channel

    This capability fetches the details of a specific discussion channel.

  3. 11

    Reply to message

    Your agent can use this to respond to a specific message within a thread.

  4. 12

    Create channel

    This capability creates a new discussion channel for team communication.

Capability set04 / 07

13-16

4 capabilities in this set.

Part of 28 available through GitScrum.

  1. 13

    Toggle note share

    Use this to change whether a note is visible to the rest of the team.

  2. 14

    Global search

    This capability searches across all tasks, wiki pages, discussions, and notes in one go.

  3. 15

    Thread replies

    This capability retrieves all replies within a specific message thread.

  4. 16

    Delete wiki page

    This capability removes a wiki page from the project documentation.

Capability set05 / 07

17-20

4 capabilities in this set.

Part of 28 available through GitScrum.

  1. 17

    Get wiki page

    This capability retrieves the full content of a specific wiki page.

  2. 18

    Create wiki page

    Use this to build new wiki pages, including nested pages using parent IDs.

  3. 19

    Search wiki

    This capability searches through the existing wiki pages for specific information.

  4. 20

    Update wiki page

    This capability allows your agent to modify the content of an existing wiki page.

Capability set06 / 07

21-24

4 capabilities in this set.

Part of 28 available through GitScrum.

  1. 21

    Wiki revisions

    Use this to view the history of changes made to a wiki page.

  2. 22

    Channel messages

    This capability fetches the messages contained within a specific channel.

  3. 23

    Create note

    Your agent uses this to create markdown notes for storing decisions or context.

  4. 24

    List channels

    This capability provides a list of all available discussion channels.

Capability set07 / 07

25-28

4 capabilities in this set.

Part of 28 available through GitScrum.

  1. 25

    List wiki pages

    This capability lists all wiki pages within a project hierarchy.

  2. 26

    Move note to folder

    Use this to reorganize notes by moving them into specific folders.

  3. 27

    Restore wiki revision

    This capability reverts a wiki page to a previous version from its history.

  4. 28

    Update note

    This capability lets your agent add more context or refine an existing note.

Real work

What teams actually run

01

Architecture Decision Records

An agent records a technical decision in a note and moves it to an Architecture folder for the team to review.

02

Automated Status Updates

An agent summarizes completed tasks and posts the update to a specific discussion channel.

03

Documentation Maintenance

A user asks an agent to update a wiki page with new deployment details found in a recent chat.

04

Knowledge Retrieval

A developer asks an agent to find the specific discussion where a certain feature requirement was decided.

Automate a task

Put GitScrum to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

GitScrum works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put GitScrum to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

1077ms average. Fast in production.

GitScrum is checked daily against the live service.

Daily averagePeak 1302ms
Oct 3Today
Fastest day
944ms
Slowest day
1302ms
14-day trend
Slowing+8%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 28 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of GitScrum, so you can see the experience inside your AI.

It does not authenticate your account with GitScrum. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

GitScrum Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_aYZl75U8HMoTFXDX8n3M42NkJHirirx5iNI2BRUo/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — GitScrum capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "gitscrum-knowledge-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_aYZl75U8HMoTFXDX8n3M42NkJHirirx5iNI2BRUo/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up GitScrum in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work GitScrum owners hand off.

This MCP is built for technical teams who want to integrate their AI agents directly into their existing GitScrum workflows.

  • 01

    AI Practitioners

    They use notes to give their agents structured, long-term memory.

  • 02

    Technical Writers

    They manage and update project wikis through natural language conversations.

  • 03

    Team Leads

    They use the agent to track decisions and communicate updates without switching platforms.

FAQ

Questions GitScrum owners ask.

  • 01

    How does the agent remember things between sessions?

    The agent uses the create_note capability to save information into GitScrum. These notes act as a persistent memory bank that the agent can read later.

  • 02

    Can my team see what the AI agent writes?

    Notes are private by default. You can tell the agent to toggle the sharing visibility if you want to publish findings to the team.

  • 03

    Does this work with my existing GitScrum wiki?

    Yes, the MCP can read, create, update, and delete wiki pages within your existing GitScrum project.

  • 04

    What happens if the agent makes a mistake in a wiki page?

    The MCP includes capabilities to view revision histories and restore wiki pages to previous versions.

  • 05

    Can the agent search through my team's chat messages?

    Yes, the agent can search through specific channels or perform a global search across all discussions and messages.

  • 06

    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.

  • 07

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

    Yes! The global_search capability 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.

  • 08

    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.

Explore

More in Collaboration

Suggestions

Connect GitScrum to Claude, Cursor, ChatGPT & more