Plane MCP. Pull structured project data without leaving 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.
Plane MCP Server gives your AI client direct read access to your entire Plane workspace. It lets your agent autonomously pull project architectures, list active sprints (`list_cycles`), track every work item/issue (`list_work_items`), and map out the full module taxonomy without you touching a kanban board.
What your AI agents can do
Get project
Retrieves detailed data for a specific Plane project using its unique ID.
List cycles
Lists all active development cycles (sprints) associated with a given project.
List labels
Pulls a list of all available category labels defined in your Plane workspace.
Runs the list_projects tool to retrieve a structured list of every project within your Plane account.
Uses get_project to extract specific data parameters and descriptions for a single, named Plane project.
Invokes the list_cycles tool to list all current development cycles and their expected completion statuses.
Runs list_work_items to pull a comprehensive, structured report of all tasks and tickets within a designated project scope.
Executes list_modules to find the main module groups or epics assigned to a specific project.
Retrieves categorization data by listing all available labels (list_labels) across your workspace, clarifying how issues are grouped.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Plane MCP Server: 6 Tools for Project Management Data
These tools allow your AI client to read specific structured data from Plane. It lets you list projects, check cycles, retrieve work items, and map modules.
019d75f6get project
Retrieves detailed data for a specific Plane project using its unique ID.
019d75f6list cycles
Lists all active development cycles (sprints) associated with a given project.
019d75f6list labels
Pulls a list of all available category labels defined in your Plane workspace.
019d75f6list modules
Retrieves the major feature groupings (modules/epics) related to a specific project.
019d75f6list projects
Lists all available projects across your entire Plane workspace, allowing you to find the correct scope.
019d75f6list work items
Retrieves a list of specific tasks or issues within a project, detailing their status and content.
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 Plane, 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
This server gives your AI client direct read access to everything in your Plane workspace. Your agent can pull structured data—projects, cycles, issues, modules, and labels—allowing it to analyze complex agile pipelines on demand. You won't need to click through kanban boards or run manual exports anymore; your agent handles the heavy lifting.
Discovering Your Scope
You start by needing a map of where you are working. Use the list_projects tool, and your AI client gets a structured list of every project in your account. If you need to know how issues are grouped across the board, run list_labels to pull all available category labels defined throughout your workspace.
These tools give you the full context needed before digging into any specific work.
Deep Project Details and Architecture
Once you've scoped out a project using list_projects, you can drill down with get_project. This tool extracts detailed data parameters, descriptions, and core metrics for that single Plane project. For understanding the overall architecture, your agent executes list_modules to find all major feature groupings or epics assigned to the scope.
You'll get a clear view of how the main components relate to one another.
Tracking Work Status and Timelines
To see what's happening right now, your agent checks the timeline using list_cycles. This tool lists all current development cycles—or sprints—and reports their expected completion statuses. When you need to know exactly what tasks are moving through the pipeline, run list_work_items. This pulls a comprehensive, structured report of every task and issue within that designated project scope, detailing its status and content.
You'll see everything your team's building.
Running Your Agent
Your AI client uses these tools to build an actionable picture of the entire workspace. It doesn't just pull lists; it builds relationships—mapping how labels define modules, which relate to projects that are currently in a specific development cycle, and finally leading down to the individual work items themselves. You don't need to manually cross-reference anything.
Just point your agent at the goal, and it pulls the necessary data points from list_projects, get_project, list_cycles, list_modules, list_labels, and list_work_items to give you a full picture of progress.
How Plane MCP Works
- 1 Install the Plane integration layer onto your agent's setup.
- 2 Supply your Personal API Key (and self-hosted URL if necessary).
- 3 Your AI client sends a prompt, and the server runs the required tool calls—like
list_work_itemsorlist_cycles—to return structured data directly to the chat.
The bottom line is: your agent treats Plane like a database, not a visual board. It pulls clean JSON outputs for analysis.
Who Is Plane MCP For?
This is for Product Managers and Lead Engineers who spend too much time clicking through UI filters to get simple data points. You're the person who knows exactly what question needs answering but hates leaving your IDE or chat window to check a dashboard.
You use list_work_items and list_cycles to instantly summarize project progress and identify blocked tickets without manually compiling status reports.
You run get_project or list_modules to verify requirements against the current state, then write code based on that retrieved data directly in your IDE.
You use all tools together—like cross-referencing labels (list_labels) with work items (list_work_items)—to audit the project's overall compliance or structure.
What Changes When You Connect
- Stop manually checking the board. Using
list_work_itemslets your agent pull a clean, actionable list of every ticket—status, assignee, description—in one shot. - Know exactly where things stand in development. Run
list_cyclesto see active sprints and their target completion dates without navigating the calendar view. - Pinpoint architectural scope instantly. By running
list_modules, you get a structured breakdown of project epics, letting you cross-reference requirements against the actual plan. - Audit your entire system structure. Combine
list_projectswithlist_labelsto see every workspace and what categories they use, giving a full organizational picture. - Validate technical dependencies. Use
get_projectto get core entity details, then runlist_work_itemsto see which specific tasks rely on that project's completion.
Real-World Use Cases
Need a sprint status report for leadership.
A PM needs to know if the current development cycle is blocked. They ask their agent: 'Check active issues in Project X.' The agent runs list_work_items and list_cycles, immediately identifying 3 unresolved tickets and flagging the oldest one, saving hours of manual status gathering.
Writing a feature that needs multiple components.
A Lead Engineer is starting a new task. They ask: 'What modules does Project Y contain?' The agent runs list_modules, returning the list (e.g., Auth, API Gateway). The engineer then uses this structured data to write code for all dependencies in sequence.
Finding out which features are tied to a specific label.
A Product Team member needs to see every task marked 'High Priority'. They ask the agent to list work items filtered by that label. The agent runs list_work_items and filters by the label, giving them a complete, sorted inventory without using the visual filter UI.
Quickly onboarding a new team member.
A manager asks: 'List all projects in the workspace.' The agent runs list_projects, providing an immediate, clean list of every active initiative. They can then follow up with get_project on any specific project name.
The Tradeoffs
Treating it like a general chat tool
Trying to ask, 'Tell me about the cool stuff happening in the company.' The agent will fail because the tool requires specific inputs (project IDs, cycle names).
→
You must scope your request. Start by running list_projects to find the right context, then specify the action: 'Run list_work_items for the project named [Project Name].'
Relying on visual board traversal
Asking the agent to 'Show me the column labeled Done.' The agent can't see columns; it only reads structured data points and fields.
→
Ask for specific data retrieval. Instead of showing the column, ask: 'Use list_work_items and filter by status: Complete.' This forces the tool to pull the raw, machine-readable data.
Ignoring the scope limitation
Asking for all tasks across your whole company. The agent needs a single project ID or workspace context to run list_work_items efficiently.
→
Always start by running list_projects first. This gives you the necessary Project IDs, which you then feed into tools like get_project.
When It Fits, When It Doesn't
Use this if your workflow requires extracting structured data points: lists of projects, current sprints, or ticket inventories. You need to know what is blocked, who owns it, and when it's due.
Don't use this if you are asking for subjective analysis ('What should we build next?') or unstructured documents. For those things, your agent needs general knowledge access (like a document search tool). This server only reads the structured data Plane provides through its API calls (list_work_items, get_project). It's a read-only database interface, not a brainstorming partner.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Plane. 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 6 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Getting project status used to mean clicking 5 different tabs and running three manual reports.
Right now, if you need an update on Project X's progress, your process is: open the Plane dashboard > click 'Issues' > filter by cycle Y > manually check every ticket status across Kanban columns > copy/paste the results into a spreadsheet for review. This takes 20 minutes of clicking and context switching.
With this MCP Server, you just tell your agent to run `list_work_items` on Project X. You get an instant, clean JSON list of every ticket's status, ID, module, and assignee—all delivered directly into the chat. The clicks are gone.
Plane MCP Server: Get project data via `list_work_items`
Before this, checking a ticket backlog required you to navigate to the specific board, find the correct filter (e.g., 'In Review'), and then manually scroll through every card. If the team had thousands of items, this was impossible.
Now, running `list_work_items` gives your agent a clean dump of all tickets matching criteria. It's raw data—no visual clutter, no pagination limits—just the precise information you need to analyze or script against.
Common Questions About Plane MCP
How does I use `list_work_items` with a specific project? +
You must reference the Project ID first. Ask your agent: 'Run list_work_items for Project ABC.' The tool then pulls all tickets and issues linked to that single scope.
Can I find out which projects exist using Plane MCP Server? +
Yes. Use the list_projects tool. It runs against your workspace and gives you a master list of every project title and ID available for subsequent queries.
What is the difference between `list_modules` and `list_labels`? +
Modules are large, structural groupings (Epics) that define major deliverables. Labels are smaller, flexible tags used to categorize items by type or priority (e.g., 'Bug', 'High Priority').
How do I check the status of the current sprint? +
Use list_cycles. This tool lists all active sprints and provides their timeline data, letting you see which cycle is currently running and when it was expected to finish.
What credentials must I use when calling `get_project`? +
You need a valid Plane Personal API Key or your self-hosted URL. The agent uses this key to authenticate the connection and scope the request directly to your workspace data.
Can I filter issues when running `list_work_items`? +
Yes, you can pass filters like status or module IDs. This limits the output dramatically, allowing you to check specific issue types without retrieving every single ticket in the project.
Does this MCP Server support both Cloud and self-hosted Plane instances? +
It does. You simply provide your API credentials—either the standard Plane Cloud key or a custom URL for your own server instance—during setup.
What is the maximum scope of data returned by `list_projects`? +
The tool handles pagination automatically. If you have hundreds of projects, it fetches them in manageable batches instead of failing due to excessive data volume.
Can my AI automatically aggregate all open issues inside our active sprint? +
Yes. First, request the active iteration window by calling list_cycles. The agent will isolate today's active cycle bounds. Following that, it will invoke list_work_items directly constrained by that cycle object, outputting an exhaustive summary of untouched or blocking tickets.
How does the agent handle custom workspace slugs or self-hosted URLs? +
The system dynamically accepts a PLANE_BASE_URL credential. If you are doing an on-premise installation running inside your homelab or company AWS cloud, you merely inject your private domain (e.g., https://plane.internal.acme.com). The workspace slug is seamlessly accepted as a contextual execution parameter during standard query prompts.
Can I request specific details of a long-term module (epic)? +
You can instruct the agent to execute list_modules. It extracts the cross-functional epics spanning your workspace project. Your AI can read these top-level module architectures to contextually understand what the core functionality of the project repository aims to achieve.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Shansong Swift Delivery
Bring Shansong's fast P2P Delivery Network into your LLM. Estimate logistics routing, dispatch riders, and track locations.
Doodle
Manage group scheduling via Doodle — create meeting polls, track participant votes, handle comments, and close polls directly from any AI agent.
NeetoCal
Let clients book appointments through your personalized scheduling page with calendar sync and automatic reminders.
You might also like
Xata (Serverless DB)
Manage your serverless databases via Xata — list organizations, manage projects, branches, and execute SQL queries directly from any AI agent.
HID Origo
Automate identity and access management via HID Origo — manage mobile identities, users, and readers directly from any AI agent.
HashiCorp Nomad
Manage workloads and orchestration via Nomad — track jobs, nodes, and deployments directly from your AI agent.