About Plane Workflow
Plane Workflow is an MCP server for coding agents that manage Plane work items under configurable team workflows. It supports previewing writes, recording completion evidence, and read-only project briefings and reports.
Key features
- 01Configurable planning rules
- 02Project-guarded work-item updates
- 03Preview writes with dry runs
- 04Completion evidence recording
- 05Read-only briefings and reports
Use cases
- 01Drafting tasks with team requirements
- 02Reviewing overdue and unassigned work
- 03Recording verified task completion
MCP support
The MCP server exposes Plane project and work-item operations to compatible clients. Setup includes adapters for Claude Code, Codex, Cursor, Claude Desktop, OpenCode, and Zed.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEPlane Workflow MCP
Keep Plane tasks in sync with your coding agent using configurable team workflows. Draft structured tasks, preview changes, record completion evidence, and get read-only project briefings or DOCX/PDF reports.
Install and get your first result
Requires Python 3.11+, uv, and a Plane workspace with an API key. Install from PyPI:
uv tool install plane-workflow-mcp
plane-workflow setup --client claude-code
plane-workflow project list
plane-workflow project activate PROJECT_ID
plane-workflow status
Replace PROJECT_ID with a listed ID. Setup also has --client codex, cursor,
claude-desktop, opencode, and zed adapters. Restart the client, then ask:
Confirm my active Plane workspace and project, then show overdue and unassigned work. Include identifiers and totals, flag truncated lists, and do not change Plane data.
To use an unreleased checkout, run uv tool install ./plugins/plane-workflow
from the repository root instead.
Workflow behavior
- Advisory planning accepts incomplete planning data; strict planning requires scope, complexity, assignment, an estimate mapping, dates, and an unstarted state.
- Project selection guards work-item mutations against conflicting projects.
- Completion requires a started item, a summary, and verification text; the completion record is written before the state transition.
- API keys are stored in the OS keyring by guided setup. Environment variables support headless use.
Preview supported writes with dry_run=true and ask the agent to wait for approval.
Some writes default to applying changes. Approval is a client workflow, not a
server-enforced human approval gate. Updates happen through tool calls, not a
background code-to-task sync.
Documentation
- Quick start and official-server comparison
- Installation and client compatibility
- Copyable workflow examples
- Planning and workflow configuration
- Demo
- Support
MIT licensed. Independent community project; not affiliated with Plane.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.