Skip to main content
Glama

Kelvia MCP — task manager for coding agents

CI npm License: MIT MCP Registry kelvia-mcp MCP server

Kelvia is a shared task manager for people and coding agents. One concrete use: hand off an unfinished task from Claude Code to Codex. The guide includes a copyable repo-file handoff that works without Kelvia, then shows when a shared task helps. Through the Model Context Protocol, an agent can create and update tasks, move work across a Kanban board, comment, log time, run stages, and plan the day. Its changes stay visible and attributed in the same UI the human uses.

The server exposes 58 tools and works with Claude Code, Codex, Cursor, and other MCP clients. The hosted endpoint uses OAuth, so there is no API token to paste into the recommended setup. A local stdio mode is available for CI and clients without remote MCP support.

Try for free · MCP documentation · Hosted endpoint

Connect in one command

Client

Command

Claude Code

claude mcp add --transport http --scope user kelvia https://mcp.kelvia.app/mcp

Codex

codex mcp add kelvia --url https://mcp.kelvia.app/mcp

Cursor

Add https://mcp.kelvia.app/mcp in Settings → Tools & MCP

The first connection opens Kelvia in the browser for OAuth approval. After it connects, ask the client: List my Kelvia boards.

A Kelvia board whose tasks were created through this MCP server

Related MCP server: Weeek MCP Server

Why Kelvia MCP

  • Complete workflow coverage — create and triage tasks, move work across a board, log time, run stages, and plan a day. Not a read-only bridge.

  • Controlled write access — agent keys have read/create/edit/delete scopes intersected with the agent's role on each board.

  • Visible agent activity — changes, comments, and worklogs appear in Kelvia; supported task changes can be reverted by a human in the app.

  • Load only what you need — toolsets let a client publish one part of the product instead of all 58 tools.

  • Modern remote auth — Streamable HTTP with OAuth 2.1 + PKCE, or a Bearer token when an explicit agent identity is required.

  • A local option when you need one — stdio for clients without remote MCP support, for CI, and for keeping the key on one machine.

See it work

From the client side — one prompt, and the agent reads the board, decides what matters, files a follow-up task and comments on the blocker:

A Claude Code session calling Kelvia MCP tools

A real session against mcp.kelvia.app, typeset from its transcript. create_task really did create #17, and add_task_comment really did comment on #9 — which is what the rest of this section shows.

And from the product side. Everything below was created by an agent over this server — the board, the tasks, the discussion, and the logged time.

An agent creating and triaging tasks on a Kelvia board

Watch the same run as video

Every change an agent makes is attributed to it and filterable, so a human can review exactly what happened rather than trusting a summary:

A task history showing changes attributed to Release Agent

The personal day planner is part of the surface too, so an agent can block out the work it just triaged:

A time-blocked day plan built through the MCP server

The production endpoint is:

https://mcp.kelvia.app/mcp

OAuth is the default. The client opens Kelvia in a browser, you approve access, and the client stores and refreshes its OAuth credentials. No API token needs to be pasted into a configuration file.

Claude Code

claude mcp add --transport http --scope user kelvia https://mcp.kelvia.app/mcp
claude mcp list

Start Claude Code, enter /mcp, choose kelvia, and complete Authenticate in the browser. After authentication, verify the connection with:

List my Kelvia boards.

Codex app, CLI, and IDE extension

codex mcp add kelvia --url https://mcp.kelvia.app/mcp
codex mcp login kelvia
codex mcp list

The Codex app, CLI, and IDE extension share the same MCP configuration on a Codex host. In an interactive Codex session, use /mcp to inspect the server.

Equivalent ~/.codex/config.toml:

[mcp_servers.kelvia]
url = "https://mcp.kelvia.app/mcp"
auth = "oauth"

Cursor

Add the server globally in ~/.cursor/mcp.json, or per project in .cursor/mcp.json:

{
  "mcpServers": {
    "kelvia": {
      "url": "https://mcp.kelvia.app/mcp"
    }
  }
}

Open Cursor Settings → Tools & MCP, enable kelvia, and select Connect to complete OAuth in the browser. Ask Cursor to list your Kelvia boards after it reports the server as connected.

Agent-key authentication

OAuth acts as the approving Kelvia user. Use an agent key instead when the connection needs its own identity, board membership, role, expiry, and granular read/create/edit/delete scopes.

Create one in Kelvia → Profile → Agents:

  1. Create an agent identity.

  2. Add it to only the required boards and choose its board role.

  3. Create a key with the minimum required scopes and an expiry date.

  4. Copy the klv_… value when shown; Kelvia stores only its hash.

Codex with an agent key

Keep the token in the environment; Codex stores only the variable name:

export KELVIA_API_TOKEN='klv_your_agent_key'
codex mcp add kelvia --url https://mcp.kelvia.app/mcp \
  --bearer-token-env-var KELVIA_API_TOKEN
codex mcp list

Equivalent ~/.codex/config.toml:

[mcp_servers.kelvia]
url = "https://mcp.kelvia.app/mcp"
bearer_token_env_var = "KELVIA_API_TOKEN"

Claude Code with an agent key

Claude Code expands environment variables in MCP JSON. Single quotes below keep your shell from expanding the token into its command history:

export KELVIA_API_TOKEN='klv_your_agent_key'
claude mcp add-json --scope user kelvia \
  '{"type":"http","url":"https://mcp.kelvia.app/mcp","headers":{"Authorization":"Bearer ${KELVIA_API_TOKEN}"}}'
claude mcp list

Do not put tokens in URLs. The Streamable HTTP endpoint accepts authentication only through the Authorization header.

Local stdio setup

Most people should use the hosted endpoint above. Running the server locally does not keep your tasks on your machine — they live in Kelvia either way, and the local process talks to the same API. What it changes is the path your credential takes, and which clients can connect.

Use stdio when one of these applies:

  • Your client cannot do remote MCP or OAuth. The major clients can, but older versions, some IDE plugins, and locked-down machines where a browser redirect will not open, cannot.

  • You are automating in CI, where nobody is around to approve an OAuth prompt. (An agent key against the hosted endpoint also works — this just removes a dependency.)

  • Your key should not leave the machine. With the hosted endpoint your token reaches mcp.kelvia.app and stays in its memory for the session; over stdio it only ever goes to the Kelvia API.

Requirements: Node.js 20+.

Run the published package without installing anything:

npx kelvia-mcp

Or build from source (Node.js 20+ and pnpm 9+), then use an absolute path to dist/index.js in client configuration:

git clone https://github.com/gonnagetapower/kelvia-mcp.git
cd kelvia-mcp
pnpm install
pnpm build

MCP Bundle for Claude Desktop

For local installation in Claude Desktop, build the MCP Bundle (.mcpb):

pnpm run bundle:mcpb

This produces build/kelvia-mcp-<version>.mcpb. Open that file in Claude Desktop and enter a dedicated Kelvia agent key when prompted. The bundle is a packaged form of the same local stdio server; for the hosted OAuth connection, use the recommended quick start instead.

Claude Code (stdio)

claude mcp add --scope user \
  --env KELVIA_API_TOKEN=klv_your_agent_key \
  --transport stdio kelvia -- node /absolute/path/to/kelvia-mcp/dist/index.js

Codex (stdio)

codex mcp add kelvia \
  --env KELVIA_API_TOKEN=klv_your_agent_key \
  -- node /absolute/path/to/kelvia-mcp/dist/index.js

Cursor (stdio)

{
  "mcpServers": {
    "kelvia": {
      "command": "node",
      "args": ["/absolute/path/to/kelvia-mcp/dist/index.js"],
      "env": {
        "KELVIA_API_TOKEN": "klv_your_agent_key"
      }
    }
  }
}

Available tools

Boards (9) — list_boards, get_board, create_board, update_board, archive_board, unarchive_board, delete_board, list_board_columns, get_board_activity

Tasks (12) — list_tasks, list_daily_tasks, list_calendar_tasks, get_task, get_task_by_number, create_task, update_task, reorder_task, delete_task, get_task_activity, get_task_summary, set_task_summary

Comments and worklogs (8) — get_task_comments, add_task_comment, update_task_comment, delete_task_comment, get_task_worklogs, add_task_worklog, update_task_worklog, delete_task_worklog

Stages (8) — create_board_stage, materialize_board_backlog_stage, update_board_stage, delete_board_stage, reorder_board_stages, start_board_stage, complete_board_stage, reopen_board_stage

Members and invitations (9) — list_board_members, update_board_member, remove_board_member, list_board_invitations, create_board_invitation, revoke_board_invitation, list_my_invitations, accept_board_invitation, decline_board_invitation

Personal day planner (8) — list_daily_plan_blocks, list_daily_plan_definitions, list_overdue_daily_plan_blocks, create_daily_plan_block, update_daily_plan_block, set_daily_plan_block_status, reorder_daily_plan_blocks, delete_daily_plan_block

Tags (3) — list_board_tags, list_tags, create_board_tag

Core (1) — get_current_user

The server also publishes two prompts (create_task_from_pr and triage_board_backlog) and two schema resources under kelvia://schema/….

Every tool carries MCP annotations — readOnlyHint, destructiveHint, idempotentHint — so a client can auto-approve reads and prompt before a delete. 22 of the 58 tools are read-only.

Toolsets

The full surface costs about 45 KB of JSON schema in every session. Load only the parts a workflow needs:

Toolset

Tools

What it covers

boards

9

Boards, columns, board activity

tasks

12

Tasks, task activity, AI summaries

comments

8

Comments and worklogs

stages

8

Sprints and milestones

members

9

Members, roles, invitations

planner

8

Personal time-blocking day plan

tags

3

Board and workspace tags

get_current_user is always published. Omitting the setting, or naming a toolset that does not exist, publishes everything.

# stdio: environment variable
KELVIA_TOOLSETS=tasks,planner npx kelvia-mcp

# hosted: header (preferred)
X-MCP-Toolsets: tasks,planner

# hosted: query parameter, for clients that cannot set headers
https://mcp.kelvia.app/mcp?toolsets=tasks,planner

tasks,planner publishes 21 tools and about 20 KB of schema instead of 45 KB.

Good first prompts

List my Kelvia boards.
On board "product", show open high-priority tasks and suggest a triage order.
Do not modify anything.
Create a task on board "product" titled "Fix the login redirect", assign high
priority, and show me the created task.
Plan today using my three most urgent assigned tasks. Show the proposed blocks
before creating them.

Security model

  • Remote tokens are accepted only in the Authorization: Bearer … header.

  • OAuth uses authorization-code flow with PKCE and dynamic client registration.

  • OAuth tokens cannot manage account credentials, personal API tokens, agents, or MCP connections.

  • Agent keys are hashed at rest, revocable, optionally expiring, and limited by both key scopes and board roles.

  • Remote sessions appear in the Kelvia profile and can be revoked.

  • Legacy SSE exists for older clients at /sse; it may require a query token because browser EventSource cannot set headers. Prefer /mcp so credentials never enter URLs, browser history, or proxy access logs.

Treat MCP servers as privileged integrations. Review a requested write before approving it, use a dedicated agent key for automation, and grant only the boards and scopes the workflow needs.

Reporting a vulnerability: see SECURITY.md. Data handling for the hosted endpoint is described in the AI and MCP data processing policy, and the privacy policy covers Kelvia as a whole.

Privacy Policy

The MCP Bundle connects to the Kelvia API and sends the requests needed to perform the actions you ask it to take. It does not run a separate analytics or advertising service. Review the Kelvia Privacy Policy and the AI and MCP Data Processing Policy before installing it.

Self-hosting the HTTP endpoint

Setting PORT switches the process from stdio to Streamable HTTP.

docker build -t kelvia-mcp .
docker run --rm -p 8080:8080 \
  -e KELVIA_API_URL=https://api.kelvia.app/api \
  -e MCP_PUBLIC_URL=https://mcp.example.com \
  kelvia-mcp

Then check GET /health, which reports the available transports and toolsets.

Environment variables

Variable

Mode

Purpose

KELVIA_API_TOKEN

stdio

Agent key or personal token

KELVIA_API_URL

both

API base; defaults to https://api.kelvia.app/api

KELVIA_TOOLSETS

both

Comma-separated toolsets; default all

PORT

hosted

Enables HTTP mode and selects the listening port

MCP_PUBLIC_URL

hosted

Public protected-resource origin

MCP_AUTHORIZATION_SERVER

hosted

OAuth authorization-server origin

MCP_ALLOWED_ORIGINS

hosted

Comma-separated CORS allowlist

MCP_RATE_LIMIT

hosted

Requests per token per minute; default 300

MCP_INSTANCE_COUNT

hosted

Number of HTTP instances

MCP_STICKY_SESSIONS

hosted

Required for multi-instance legacy SSE

Streamable HTTP is stateless at the MCP transport layer. Legacy SSE sessions are stored in process memory, so SSE requires one instance or sticky sessions.

Troubleshooting

  • Needs authentication / HTTP 401 — complete OAuth from the client's MCP panel, or verify that the Bearer-token environment variable is available to the client process.

  • HTTP 403 — the key lacks a required scope, the agent lacks the required board role, or the email/account state blocks that operation.

  • Server connects but a board is missing — add the agent identity to that board, or approve OAuth as a user who already has access.

  • Connection closed in stdio mode — run pnpm build, use an absolute path, and confirm Node.js 20+ plus KELVIA_API_TOKEN are present.

  • No tools visible — check claude mcp list, codex mcp list, or Cursor's Tools & MCP panel, then restart/reload the client after changing config.

  • Large task output — use compact list_tasks, filter by board/status, then call get_task for one record instead of requesting detailed lists.

  • Too many tools for the client — narrow the surface with toolsets.

Health and OAuth discovery:

GET https://mcp.kelvia.app/health
GET https://mcp.kelvia.app/.well-known/oauth-protected-resource/mcp
GET https://api.kelvia.app/.well-known/oauth-authorization-server

Development

pnpm install
pnpm run lint
pnpm run typecheck:strict
pnpm run test

pnpm run test builds the package, initializes the stdio server through the official MCP client SDK, and verifies the published tools, annotations, toolsets, prompts, resources, and server instructions.

See CONTRIBUTING.md for how this repository relates to the Kelvia monorepo and what a tool change needs to touch.

License

MIT

Available Tools

58 tools
accept_board_invitationAccept invitationA
Idempotent
Inspect

Accept a pending board invitation sent to the current user. Returns the created board membership.

Inputs: invitation_id (required).

add_task_commentAdd commentAInspect

Post a comment on a task. Returns the created comment with author info.

Inputs: content (required), task_id (required).

add_task_worklogLog timeAInspect

Log time spent on a task. minutes must be > 0 and ≤ 1440 (24 hours). Returns the created worklog entry.

Inputs: minutes (required), task_id (required), comment, worked_at.

archive_boardArchive boardB
DestructiveIdempotent
Inspect

Archive a board by UUID.

Inputs: board_id (required).

complete_board_stageComplete stageA
DestructiveIdempotent
Inspect

Set stage status to COMPLETED (frozen).

Inputs: stage_id (required), board_id, board_slug.

create_boardCreate boardAInspect

Create a new board. Optionally supply an array of column names (defaults to a standard set). Returns the created board with its generated slug.

Inputs: name (required), columns.

create_board_invitationInvite to boardAInspect

Invite a user to board by email with role ADMIN/MEMBER/VIEWER. Requires ADMIN/OWNER.

Inputs: role (required), email (required), board_id, board_slug.

create_board_stageCreate stageAInspect

Create a stage on a board. Requires ADMIN/OWNER role on that board.

Inputs: name (required), status, board_id, board_slug, +1 more.

create_board_tagCreate board tagAInspect

Add a tag to a board's vocabulary. Tags live on the board and are shared by everyone on it. Usually you don't need this: create_task/update_task tag_names create missing tags by themselves.

Inputs: name (required), board_id, board_slug.

create_daily_plan_blockCreate plan blockAInspect

Create a block in the user's personal day-planner (their own time-blocking schedule, not a board task). Title may reference a board task with @boardSlug/N (e.g. @marketing/42) — the app renders it as a clickable link to that task. Returns the created block.

Inputs: title (required), end_time, recurrence, active_from, +2 more.

create_taskCreate taskAInspect

Create a new task on a board. Requires the board slug and a title. Returns the created task with its generated id and number.

Inputs: title (required), board_slug (required), status, tag_ids, +9 more.

decline_board_invitationDecline invitationA
DestructiveIdempotent
Inspect

Decline a pending board invitation sent to the current user.

Inputs: invitation_id (required).

delete_boardDelete boardA
DestructiveIdempotent
Inspect

Delete a board by UUID.

Inputs: board_id (required).

delete_board_stageDelete stageB
DestructiveIdempotent
Inspect

Delete a board stage.

Inputs: stage_id (required), board_id, board_slug.

delete_daily_plan_blockDelete plan blockA
DestructiveIdempotent
Inspect

Remove a day-planner block starting from a given local date onward (soft-delete — earlier occurrences and their completion history are kept).

Inputs: id (required), local_date (required).

delete_taskDelete taskA
DestructiveIdempotent
Inspect

Permanently delete a task by its UUID. Only the task creator or a board OWNER/ADMIN can delete tasks. Returns a confirmation message.

Inputs: id (required).

delete_task_commentDelete commentA
DestructiveIdempotent
Inspect

Delete a comment from a task. You can only delete your own comments.

Inputs: task_id (required), comment_id (required).

delete_task_worklogDelete worklogA
DestructiveIdempotent
Inspect

Delete a worklog entry from a task.

Inputs: task_id (required), worklog_id (required).

get_boardGet boardA
Read-only
Inspect

Get detailed info for a single board by its URL slug (slug is the short identifier in board URLs, e.g. 'my-project'). Includes all columns, stages with their statuses, board config and member count.

Inputs: slug, board_slug.

get_board_activityGet board activityA
Read-only
Inspect

Get the audit trail for a whole board: task/stage/member changes across the board, newest first. Requires ADMIN/OWNER role on that board.

Inputs: to, from, type, limit, +5 more.

get_current_userGet current userA
Read-only
Inspect

Get the profile of the currently authenticated user (id, email, firstName, lastName, avatarUrl).

Inputs: no named parameters.

get_taskGet taskA
Read-only
Inspect

Get full details of a single task by its UUID. Includes all fields: title, description, status, priority, dueDate, assignees, watchers, tags, stage, parent task, subtasks, worklogs (time tracking), and comments count.

Inputs: id (required).

get_task_activityGet task activityA
Read-only
Inspect

Get the audit trail for a task: who changed what and when (status/priority/assignee/field changes, comments, worklogs), newest first.

Inputs: task_id (required).

get_task_by_numberGet task by numberA
Read-only
Inspect

Get a task by its human-friendly number (the #N shown in the UI) within a board. Resolves the number to the task UUID and returns full details (same shape as get_task). Handy when you know the #N but not the UUID.

Inputs: number (required), board_slug (required).

get_task_commentsGet task commentsA
Read-only
Inspect

Get all comments for a task ordered by creation time. Each comment includes id, content, createdAt, updatedAt and the author (user).

Inputs: task_id (required).

get_task_summaryGet task summaryA
Read-only
Inspect

Read a task's summary — the single digest shown in its Summary tab. Returns { summary, summaryUpdatedAt, summaryAuthor }.

Inputs: task_id (required).

get_task_worklogsGet task worklogsA
Read-only
Inspect

Get time-tracking worklogs for a task. Each entry has id, minutes, comment, workedAt, and the author.

Inputs: task_id (required).

list_board_columnsList board columnsA
Read-only
Inspect

Get kanban columns for a board by slug. Returns id and name for each column — use these IDs in create_task and update_task.

Inputs: slug, board_slug.

list_board_invitationsList board invitationsA
Read-only
Inspect

List pending/accepted/declined invitations for a board. Requires ADMIN/OWNER.

Inputs: board_id, board_slug.

list_board_membersList board membersA
Read-only
Inspect

List all members of a board with their roles (OWNER, ADMIN, MEMBER, VIEWER). Use list_boards first to obtain the board id.

Inputs: board_id (required).

list_boardsList boardsA
Read-only
Inspect

List all Kelvia boards accessible to the authenticated user. Returns id, name, slug, isArchived, columns (kanban columns), stages (sprints/milestones), config (custom priorities and statuses), taskCounter, createdAt.

Inputs: no named parameters.

list_board_tagsList board tagsA
Read-only
Inspect

Get the tag vocabulary of a board. Tags belong to the board and are shared by everyone on it — the same name on another board is a different tag. Returns id and name; use the ids in create_task/update_task tag_ids, or just pass tag_names and let the board pick up new ones.

Inputs: board_id, board_slug.

list_calendar_tasksList calendar tasksA
Read-only
Inspect

List tasks with a due date inside a date range, for a calendar view. Unlike list_tasks, this is scoped by due date range rather than status/search filters.

Inputs: to (required), from (required), board_slug.

list_daily_plan_blocksList plan blocksA
Read-only
Inspect

List the user's personal day-planner blocks (their own time-blocking schedule) visible on a given local date, with each block's done/not-done status for that date. Different from list_daily_tasks, which lists board tasks due today — this is the user's private schedule, not board tasks.

Inputs: local_date (required).

list_daily_plan_definitionsList plan definitionsA
Read-only
Inspect

List the user's day-planner block definitions as stored (recurrence rule, scheduled time, active_from) — not resolved against a specific date, unlike list_daily_plan_blocks.

Inputs: no named parameters.

list_daily_tasksList today's tasksA
Read-only
Inspect

List tasks relevant for today (assigned to me and not done, or due today). Optional board filter by slug.

Inputs: date, slug, limit, offset, +2 more.

list_my_invitationsList my invitationsA
Read-only
Inspect

List board invitations sent to the current user (pending/accepted/declined), with the inviting board and role.

Inputs: no named parameters.

list_overdue_daily_plan_blocksList overdue plan blocksA
Read-only
Inspect

List the user's day-planner blocks that were due before the given local date and are still not done.

Inputs: local_date (required).

list_tagsList tagsA
Read-only
Inspect

List tags across every board you can access. Tags belong to boards, so the same name on two boards is two different tags — each item carries its board. For one board use list_board_tags.

Inputs: no named parameters.

list_tasksList tasksA
Read-only
Inspect

List tasks with optional filters. Without any filter returns all tasks the user has access to across every board. By default returns a COMPACT shape to stay within token limits: { board: { id, name, slug, columns } | null, tasks: [{ id, number, title, status, priority, columnId, stageId, tags (names), assignees (count), dueDate }], count }. Pass detailed=true for full task objects (heavy — can exceed limits on large boards) or use get_task / get_task_by_number for one full task.

Inputs: date, slug, limit, today, +10 more.

materialize_board_backlog_stageMaterialize backlog stageBInspect

Create (or fetch, if it already exists) the special backlog stage for a board — holds tasks that aren't part of any active/planned stage. Requires ADMIN/OWNER role on that board.

Inputs: name (required), status, board_id, board_slug.

remove_board_memberRemove memberA
DestructiveIdempotent
Inspect

Remove a member from board. Requires ADMIN/OWNER.

Inputs: target_user_id (required), board_id, board_slug.

reopen_board_stageReopen stageA
Idempotent
Inspect

Reopen stage from COMPLETED to ACTIVE.

Inputs: stage_id (required), board_id, board_slug.

reorder_board_stagesReorder stagesA
Idempotent
Inspect

Reorder stages on a board by passing full ordered list of stage IDs.

Inputs: ordered_stage_ids (required), board_id, board_slug.

reorder_daily_plan_blocksReorder plan blocksA
Idempotent
Inspect

Reorder the day-planner blocks visible on a given local date (drag-and-drop equivalent). Pass ALL block UUIDs visible on that date, in the desired order.

Inputs: local_date (required), ordered_ids (required).

reorder_taskReorder taskA
Idempotent
Inspect

Move/reorder a task inside a column (kanban drag-and-drop equivalent).

Inputs: task_id (required), position (required), column_id (required).

revoke_board_invitationRevoke invitationA
DestructiveIdempotent
Inspect

Revoke an invitation by id. Requires ADMIN/OWNER.

Inputs: invitation_id (required), board_id, board_slug.

set_daily_plan_block_statusSet plan block statusA
Idempotent
Inspect

Mark a day-planner block done or not-done for one specific local date (recurring blocks track completion per-day, not globally).

Inputs: id (required), status (required), local_date (required).

set_task_summarySet task summaryA
Idempotent
Inspect

Write or replace a task's summary: a concise digest of the task's current state and what has been done, shown in the task's Summary tab. Markdown supported. Replaces any previous summary (one per task).

Inputs: summary (required), task_id (required).

start_board_stageStart stageA
Idempotent
Inspect

Set stage status to ACTIVE.

Inputs: stage_id (required), board_id, board_slug.

unarchive_boardUnarchive boardB
Idempotent
Inspect

Unarchive a board by UUID.

Inputs: board_id (required).

update_boardUpdate boardA
Idempotent
Inspect

Update a board's name or column list. Pass only the fields you want to change. Changing columns reorders/renames them. Returns the updated board.

Inputs: board_id (required), name, columns.

update_board_memberChange member roleA
DestructiveIdempotent
Inspect

Update board member role/title. Requires ADMIN/OWNER on that board.

Inputs: target_user_id (required), role, title, board_id, +1 more.

update_board_stageUpdate stageB
Idempotent
Inspect

Rename a board stage.

Inputs: name (required), stage_id (required), board_id, board_slug.

update_daily_plan_blockUpdate plan blockA
Idempotent
Inspect

Update fields of an existing day-planner block. Pass only the fields you want to change. Title may reference a board task with @boardSlug/N. Returns the updated block.

Inputs: id (required), title, end_time, recurrence, +3 more.

update_taskUpdate taskA
Idempotent
Inspect

Update one or more fields of an existing task. Pass only the fields you want to change — all are optional. Returns the updated task.

Inputs: id (required), title, status, tag_ids, +10 more.

update_task_commentUpdate commentA
Idempotent
Inspect

Update an existing task comment.

Inputs: content (required), task_id (required), comment_id (required).

update_task_worklogUpdate worklogA
Idempotent
Inspect

Update an existing worklog entry for a task.

Inputs: minutes (required), task_id (required), worklog_id (required), comment, +1 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.8/5.0

    Scored across 58 tools

    Disambiguation4/5

    While the tool names are largely clear and map to distinct actions, a few sets (list_tasks/list_daily_tasks/list_calendar_tasks; list_board_tags/list_tags) overlap in purpose and rely heavily on descriptions to disambiguate. Overall, an agent can distinguish them with careful reading, but some names are similar enough to risk misselection.

    Naming Consistency5/5

    All tools use the snake_case verb_noun pattern consistently (create_board, update_task, list_board_members, delete_daily_plan_block). Even multi-word resources (daily_plan_blocks, board_invitations) follow the same convention. No mixing of styles or cryptic abbreviations.

    Tool Count2/5

    At 58 tools, the server is excessively large for a typical MCP surface. While the coverage is comprehensive, the sheer number makes it unwieldy for agents to select from, and many tools could be consolidated (e.g., a single 'daily_plan_block' CRUD set). This exceeds the recommended 3-15 range by a wide margin.

    Completeness5/5

    The tool set provides full CRUD coverage for boards, tasks, stages, tags, comments, worklogs, invitations, and daily plan blocks, with additional lifecycle operations (archive, unarchive, reorder, start/complete/reopen). There are no obvious missing operations for the stated project-management domain, and even niche features like task summaries and daily plans are covered.

    Maintenance

    ActivitySlowing
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      D
      maintenance
      An MCP server that provides a database-backed kanban board with 40+ tools for AI agents to track issues, features, todos, epics, and diary entries across projects, including status workflows, relationships, and semantic search.
      45
      86
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      Full-featured MCP server integrating all 71 endpoints of the Weeek API as MCP tools for AI clients, enabling task, project, and workspace management via natural language.
      2
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      MCP server for task management that enables AI agents to read, create, update tasks, and track work sessions, allowing agents and humans to collaborate on the same task board.
      14
      MIT