GitScrum MCP. Manage every project, board, and label from your chat.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
GitScrum. Manage your entire organizational backbone directly from your AI agent. Use this server to list workspaces, create projects, configure workflows, and track labels—all without switching tabs.
Your AI client can browse your entire structure, inspect project metadata, and set up new boards using natural language commands.
It's a command center for your entire GitScrum environment.
What your AI agents can do
Create project
Creates a new project within GitScrum.
Create workspace
Creates a new organizational workspace.
Find project
Locates a project using its name.
The agent can create new projects (create_project) or find existing ones by name or ID, giving you immediate access to the necessary board structure.
You can list and retrieve details for all workspaces (list_workspaces, get_workspace), letting you understand the full scope of your company's projects at a glance.
The agent lists available labels (list_labels) and filters tasks by status (list_tasks), giving you immediate visibility into the actual work items and how they're categorized.
You can list all members in a project (list_project_members) and check your own access level (get_me, my_role) to keep everyone accountable.
The agent retrieves the full workflow definition, listing all Kanban columns and templates (list_workflows), so you know exactly how work moves from 'To Do' to 'Done'.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
GitScrum MCP Server: 16 Tools for Project & Workspace Ops
Use these 16 tools to programmatically manage project creation, workspace structure, task listing, and user roles within GitScrum.
019d8441create project
Creates a new project within GitScrum.
019d8441create workspace
Creates a new organizational workspace.
019d8441find project
Locates a project using its name.
019d8441get me
Retrieves the authenticated user's profile details.
019d8441get project
Gets all specific details for a given project.
019d8441get task
Gets the full details for a task using its unique UUID.
019d8441get workspace
Retrieves all details for a specified workspace.
019d8441list labels
Lists all color-coded labels associated with a project.
019d8441list project members
Lists every user member assigned to a specific project.
019d8441list projects
Lists all projects belonging to a selected workspace.
019d8441list tasks
Filters and lists tasks within a project by status (todo, in-progress, done).
019d8441list workflows
Lists the defined workflow columns (Kanban stages) for a project.
019d8441list workspaces
Lists every available organizational workspace in GitScrum.
019d8441my role
Retrieves the user's specific role and permissions within the current workspace.
019d8441project stats
Fetches quantitative statistics about a project's current state.
019d8441workspace stats
Fetches quantitative statistics about an entire workspace.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with GitScrum, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
You've got your whole GitScrum setup running through your AI agent. You'll treat your organizational structure—workspaces, projects, and workflows—like a command line, calling tools instead of clicking menus. It's a total command center for your entire GitScrum environment.
Create and Locate Projects
Your agent can create new projects using create_project and find existing ones by name or ID with find_project, giving you instant access to the board structure you need. You can list all projects in a specific workspace using list_projects, or grab every detail for a single project with get_project.
Map the Organizational Structure
You can list every available workspace with list_workspaces and pull all the specific details for any given workspace using get_workspace, letting you see the full scope of your company's projects at a glance. You can also check the quantitative stats for an entire workspace using workspace_stats and get the project stats for any board with project_stats.
Manage Project Content and Labels
The agent lists all available color-coded labels on a project using list_labels and filters tasks by status—todo, in-progress, or done—using list_tasks, giving you immediate visibility into the work items and how they're categorized. You can also get the full details for any task using its UUID with get_task.
Inspect Team Roles and Membership
You can list every user assigned to a project using list_project_members. To check your own access level, the agent retrieves your profile details using get_me and determines your specific role and permissions in the current workspace with my_role.
Understand Project Flow Definitions
The agent pulls the full workflow definition, listing all Kanban columns and templates for a project using list_workflows, so you know exactly how work moves from 'To Do' to 'Done'. You can also see the user's role and permissions in the current workspace using my_role.
How GitScrum MCP Works
- 1 Subscribe to the GitScrum integration on the Vinkius Marketplace and generate a personal API token.
- 2 Provide the API token and your company slug to your AI agent (Claude, Cursor, etc.).
- 3 Ask your agent to perform an action, like 'List all projects in the Acme Engineering workspace.' The agent executes the necessary tool calls and gives you the structured result.
The bottom line is, your AI agent becomes the command line for GitScrum, executing complex multi-step queries that used to require manual navigation through the UI.
Who Is GitScrum MCP For?
The engineering manager who needs to audit the full workspace structure without clicking through ten different dashboards. The team lead who needs to set up a new project with specific labels and workflows in seconds. Developers who need to inspect member lists and project settings during a planning session, all without leaving their terminal.
Audits workspace structure, checks project configurations, and audits project details across multiple teams, all in a single chat session.
Creates new projects, sets up workflows, and adds standardized labels for new initiatives instantly, using natural language prompts.
Inspects project settings, checks member lists, and reviews project stats to prepare for planning meetings or debugging tasks.
What Changes When You Connect
- Instantly map your entire structure. Instead of opening the UI to see all workspaces, use
list_workspacesto get an immediate list of every organizational silo. - Setup projects in seconds. Use
create_projectto provision a new board andlist_workflowsto ensure it starts with the correct columns, all from a simple text command. - Deep visibility into work. Run
list_tasksto filter a project by status (e.g., 'Show me all tasks in progress'), bypassing the need to click status filters on the board view. - Accountability tracking. Use
list_project_membersto instantly get the full roster for any project, or runget_meto check your own access level (my_role). - Understand the scope. Check
project_statsorworkspace_statsto get metrics on workload or project health without manually running reports. - Organize faster. Use
list_labelsto see existing color-coded labels and then create new ones, keeping all project categorization in one flow.
Real-World Use Cases
The Q3 planning audit
The Engineering Manager needs to audit every active project and its members across three different workspaces. Instead of logging into three different boards and clicking through settings, they ask their agent to run list_workspaces first, then loop through the results calling list_projects and finally list_project_members for each. The agent compiles the full list, saving hours of manual cross-checking.
New initiative board setup
A Team Lead needs a new project for 'Mobile App v2' with specific labels and a standard workflow. They prompt the agent to run create_project, providing the name and description. The agent then calls list_workflows to verify the columns and uses list_labels to confirm the standard label set, completing the setup in one sequence.
Reviewing stalled tasks
A Developer notices a project has too many tasks stuck in 'In Progress.' They ask the agent to run list_tasks and filter by 'In Progress' status for that project. The agent returns only the UUIDs and titles of the stalled tasks, letting the developer know exactly where to focus their effort.
Getting a project's full status
A Project Manager wants a high-level overview of a specific project. They ask the agent to run get_project to get the core data, followed immediately by project_stats to get the current workload count. The agent combines these calls, giving a single, comprehensive status report without requiring multiple manual API calls.
The Tradeoffs
Over-relying on the UI
A user wants to know who is on the 'Design Studio' project. They navigate to the workspace, click the project, then click the 'Members' tab. This is three clicks, plus the time to load the page.
→
Just ask your agent to run list_project_members and specify the project name. It returns the full roster immediately, skipping the entire UI navigation.
Guessing the project scope
A developer needs to know what tasks are ready to be reviewed, but they just look at the board and manually count the cards in the 'Review' column. This is slow and doesn't account for hidden tasks.
→
Use list_tasks and specify the project and the 'Review' status. This command pulls a definitive list of all tasks that meet the criteria, regardless of how they are displayed on the board.
Manual cross-referencing
A manager needs to check the project stats vs. the workspace stats. They run one report, then have to switch tabs and run a second report. This creates two separate, hard-to-compare data points.
→
Ask your agent to run workspace_stats first, and then project_stats for the specific project. The agent presents both data sets in a single, side-by-side report.
When It Fits, When It Doesn't
Use this server if your goal is to treat your GitScrum environment like a database: if you need to list everything, create something, or pull metadata (e.g., 'List all workspaces' or 'Get project details'), this is your tool. Don't use it if you only need to visually see a board or perform a manual drag-and-drop action—those require the UI. If you need to act on data (e.g., 'Create a project' or 'List members'), this is what you use. If you just need to read the raw text content of a task description, you might need a different, content-focused API.
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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 16 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Having to check project status by jumping between tabs is a huge time sink.
Today, figuring out project status means clicking from the workspace overview to the project board, then checking the status filter. If you want to know who's on the team, you click another tab, and if you need to check the task count, you run a separate report. It's a painful sequence of clicks and context switches.
With the GitScrum MCP Server, you just ask your agent. You tell it, 'Show me all projects and their active tasks.' The agent runs `list_projects` and then loops through calling `list_tasks` for every result. You get the compiled, filtered data set in one response. It's that simple.
GitScrum MCP Server: Get project details and stats instantly.
You don't have to open the project view to get core metadata. You can use `get_project` to pull the foundational settings, and then run `project_stats` immediately after. This two-step process gives you the setup data and the current performance metrics without opening the UI.
The difference is that your agent doesn't just link to a page; it runs the functions. It pulls the data into the conversation, giving you the exact numbers and metadata you need, right when you need it.
Common Questions About GitScrum MCP
How do I use the `list_workspaces` tool with the GitScrum MCP Server? +
Run list_workspaces to get a complete list of every workspace you have access to. This is the first step if you don't know which environment holds the project you're looking for.
Can I use `list_tasks` to filter by status in the GitScrum MCP Server? +
Yes, list_tasks is designed to filter tasks. You provide the project ID and the desired status (todo, in-progress, done) to get a clean list of only the relevant items.
What does `get_project` do in the GitScrum MCP Server? +
get_project retrieves all core metadata for a single project. This includes settings and structure, which is often more detail than just viewing the project on the board.
How do I check if a user is part of a project using `list_project_members`? +
Use list_project_members and provide the project ID. It returns a comprehensive list of every user assigned to that specific board.
How do I use `create_project` to ensure the new project inherits the correct workflow columns? +
You specify the desired workflow columns as an argument when calling create_project. This allows you to build out a project's structure right away, ensuring consistency across your board.
What information does `get_project` return about a project's members? +
The get_project tool returns a list of members, including their unique IDs and roles within that specific project. You can then cross-reference this data with other tools to check permissions.
Can I use `list_labels` to find out what types of work are already categorized in a project? +
Yes, list_labels retrieves all existing color-coded labels for a given project. This lets you see what categories are available before you try to apply new ones.
If I need to check the overall health of my organization, which tool should I use, and what does it tell me? +
Use workspace_stats to get an overview of the entire organizational workspace. It provides key metrics on project counts and overall activity, giving you a quick health check.
Can my AI agent list all workspaces and drill into specific project details? +
Absolutely. Use list_workspaces to browse all your organizational workspaces, then list_projects to see every project within a workspace. Your agent returns full metadata including member counts, settings, and creation dates — all without leaving your conversation.
I need to set up a new project with custom workflows and labels — can I do it all conversationally? +
Yes. Tell your agent to create the project, then ask it to configure the workflow columns and create color-coded labels. The agent chains create_project, list_workflows, and create_label tools automatically to set up your board exactly as you describe it.
Does this integration let me modify or delete projects? +
This core integration focuses on workspace exploration, project creation, and configuration management — including workflows and labels. For task-level operations like CRUD, subtasks, and checklists, use the dedicated GitScrum Tasks integration. All actions respect your GitScrum account permissions.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Clockwise
Automate scheduling via Clockwise — manage focus time, track team availability, and optimize calendar events directly from any AI agent.
Guidebook
Automate mobile app content management via Guidebook — manage guides, sessions, speakers, and custom lists directly from any AI agent.
Bizzabo
Orchestrate your event experience via Bizzabo — manage events, registrations, and attendees directly from any AI agent.
You might also like
Lightcast Labor Market
Equip your AI agent to access labor market data, track skill taxonomies, and monitor job titles via the Lightcast API.
GetStream
Build and manage scalable activity feeds and social networks. Manage activities, feeds, and follower relationships directly through your AI agent.
PokéAPI
Access Pokémon data, stats, abilities, types, and evolution chains via AI.