Skip to main content
Glama
goto-software

plane-mcp-server

update_epic

Update an existing epic in Plane by providing its project and epic IDs, with optional changes to name, assignees, labels, priority, dates, and other fields.

Instructions

Update an epic by ID.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
project_idYesUUID of the project
epic_idYesUUID of the epic
nameNoEpic name
assigneesNoList of user IDs to assign to the epic
labelsNoList of label IDs to attach to the epic
pointNoStory point value
description_htmlNoHTML description of the epic
description_strippedNoPlain text description (stripped of HTML)
priorityNoPriority level (urgent, high, medium, low, none)
start_dateNoStart date (ISO 8601 format)
target_dateNoTarget/end date (ISO 8601 format)
sort_orderNoSort order value
is_draftNoWhether the epic is a draft
external_sourceNoExternal system source name
external_idNoExternal system identifier
stateNoUUID of the state
estimate_pointNoEstimate point value

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
idNo
deleted_atNo
created_atNo
updated_atNo
pointNo
nameYes
descriptionNo
description_htmlNo
description_strippedNo
description_binaryNo
priorityNo
start_dateNo
target_dateNo
sequence_idNo
sort_orderNo
completed_atNo
archived_atNo
is_draftNo
external_sourceNo
external_idNo
created_byNo
updated_byNo
projectYes
workspaceYes
parentNo
stateNo
estimate_pointNo
typeNo
assigneesNo
labelsNo

Implementation Reference

  • The main handler function for the 'update_epic' tool. It takes project_id, epic_id, and various optional fields, validates priority, constructs an UpdateWorkItem payload, calls client.work_items.update() to update the epic, and then retrieves and returns the updated Epic via client.epics.retrieve().
    @mcp.tool()
    def update_epic(
        project_id: str,
        epic_id: str,
        name: str | None = None,
        assignees: list[str] | None = None,
        labels: list[str] | None = None,
        point: int | None = None,
        description_html: str | None = None,
        description_stripped: str | None = None,
        priority: str | None = None,
        start_date: str | None = None,
        target_date: str | None = None,
        sort_order: float | None = None,
        is_draft: bool | None = None,
        external_source: str | None = None,
        external_id: str | None = None,
        state: str | None = None,
        estimate_point: str | None = None,
    ) -> Epic:
        """
        Update an epic by ID.
    
        Args:
            project_id: UUID of the project
            epic_id: UUID of the epic
            name: Epic name
            assignees: List of user IDs to assign to the epic
            labels: List of label IDs to attach to the epic
            point: Story point value
            description_html: HTML description of the epic
            description_stripped: Plain text description (stripped of HTML)
            priority: Priority level (urgent, high, medium, low, none)
            start_date: Start date (ISO 8601 format)
            target_date: Target/end date (ISO 8601 format)
            sort_order: Sort order value
            is_draft: Whether the epic is a draft
            external_source: External system source name
            external_id: External system identifier
            state: UUID of the state
            estimate_point: Estimate point value
    
        Returns:
            Updated Epic object
        """
        client, workspace_slug = get_plane_client_context()
    
        # Validate priority against allowed literal values
        valid_priorities = get_args(PriorityEnum)
        if priority is not None and priority not in valid_priorities:
            raise ValueError(f"Invalid priority '{priority}'. Must be one of: {valid_priorities}")
        validated_priority: PriorityEnum | None = priority  # type: ignore[assignment]
    
        data = UpdateWorkItem(
            name=name,
            assignees=assignees,
            labels=labels,
            point=point,
            description_html=description_html,
            description_stripped=description_stripped,
            priority=validated_priority,
            start_date=start_date,
            target_date=target_date,
            sort_order=sort_order,
            is_draft=is_draft,
            external_source=external_source,
            external_id=external_id,
            state=state,
            estimate_point=estimate_point,
        )
    
        work_item = client.work_items.update(
            workspace_slug=workspace_slug,
            project_id=project_id,
            work_item_id=epic_id,
            data=data,
        )
    
        return client.epics.retrieve(
            workspace_slug=workspace_slug,
            project_id=project_id,
            epic_id=work_item.id,
        )
  • Import of UpdateWorkItem from plane.models.work_items, which is the schema/model used to structure the data payload for the update.
    from plane.models.work_items import (
        CreateWorkItem,
        UpdateWorkItem,
    )
  • The register_epic_tools function that registers all epic tools (including update_epic) with the FastMCP server via the @mcp.tool() decorator.
    def register_epic_tools(mcp: FastMCP) -> None:
  • The call to register_epic_tools(mcp) inside the register_tools function, which is the top-level registration entry point.
    register_epic_tools(mcp)
  • Import of register_epic_tools from plane_mcp.tools.epics in the tools package __init__.py.
    from plane_mcp.tools.epics import register_epic_tools
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden but only states 'Update an epic by ID.' It fails to disclose side effects, whether changes are permanent, or any behavioral traits beyond the minimal mutation implication.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence, which is efficiently front-loaded. However, it may be overly sparse for a complex tool, but it is not verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (17 parameters, many optional) and no annotations, the description is incomplete. An output schema exists but is not described. Missing context about partial update behavior, required fields, or what happens when nulls are provided.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds no additional meaning beyond the schema, which already provides descriptions for all 17 parameters. No improvement over schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Update', the resource 'epic', and the method 'by ID'. It effectively distinguishes from sibling tools like create_epic, delete_epic, and retrieve_epic.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives, such as other update tools like update_work_item. No prerequisites, permissions, or when-to-avoid advice is given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/goto-software/plane-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server