Taiga MCP Server
The Taiga MCP Server enables AI assistants to fully manage Taiga projects using natural language, operating under your Taiga credentials and permissions.
Project Management
Projects: create, read, update, delete, list, filter by member
Epics: CRUD, list, filter, link/unlink user stories, list related stories
User Stories: CRUD, list, filter, assign/remove from milestones
Tasks: CRUD, list, filter, associate with user stories
Issues: CRUD, list, filter, set classification (type, status, priority, severity)
Milestones/Sprints: CRUD, list, burndown/points statistics
Wiki Pages: CRUD, list, retrieve by slug
Memberships: add, update, remove, list, bulk invite, resend invitations
Comments: add and list on epics, stories, tasks, issues
Attachments: upload (base64), list, delete on supported resources
Collaboration
Voting: upvote/remove vote on epics, stories, tasks, issues
Watching: watch/unwatch epics, stories, tasks, issues, milestones, wiki pages
Search & Utilities
Search: project-scoped text search across epics, stories, tasks, issues, wiki pages
Raw API: raw requests to any
/api/v1/endpoint for webhooks, import/export, etc.Identity resolution: assign users by email or full name without numeric IDs
Verbosity: control response size (minimal/standard/full)
Safe operations: automatic handling of concurrency, rate-limiting, and errors; respects your Taiga permissions
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Taiga MCP Server Show me all open bugs in the Website project."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Taiga MCP Server
Connect Claude, Cursor, Windsurf, or any other MCP-compatible AI assistant to your Taiga project management tool — read and update epics, user stories, tasks, issues, sprints, comments, and wiki pages just by chatting, in plain English. No coding required to use it.
In plain words: MCP (Model Context Protocol) is a standard that lets an AI assistant safely use outside tools — like reading your files or browsing the web. This package is that "tool" for Taiga: it's the bridge that lets your AI assistant see and change things in your Taiga account when you ask it to.
Package on npm: @madebyclowd/taiga-mcp-server
Not an official Taiga product. This is an independent, open-source integration.
Table of contents
Related MCP server: Taiga MCP Server
What can I actually do with this?
Once it's connected, you can ask your AI assistant things like:
"Show me all open bugs in the Website project."
"Create a task called 'Fix login button' under the current sprint."
"Move user story #482 to the QA column."
"Summarize what changed on epic #12 this week."
"Search the wiki for our deployment steps."
You don't type any code or API calls yourself — you just ask, in normal sentences, and the assistant does the rest.
Behind the scenes, the assistant does this by calling this server, which talks to Taiga's real API using your own Taiga login. It only does what your Taiga account is already allowed to do — it can't see or change anything you don't already have permission for in Taiga itself.
It supports:
Projects, epics, user stories, tasks, issues, sprints (milestones), wiki pages, comments (including edit/delete), attachments (including download), project members, voting/watching, ref lookup (
#436→ the right item), batch create, and search. If it's in Taiga, there's a good chance this covers it.Assign people by email or full name instead of hunting down a numeric user id — the server figures out who you mean from the project's member list.
Every response tells the AI assistant whether more results are waiting (paging) and lets it ask for a shorter or fuller version of the data (a
verbositysetting:minimal/standard/full). In plain terms: asking "list my backlog" won't dump a wall of raw data into your conversation and eat up the assistant's memory of what you've been talking about — it gets just enough to answer you.Cheap filter-id lookups (
user_story_filters_data,task_filters_data,issue_filters_data) instead of paging through a full list just to find a valid status or tag id.Each tool is clearly labeled as read-only, safe-to-repeat, or something that changes data — so your AI assistant (and you) can tell at a glance what's harmless to run and what deserves a second look before confirming.
A fallback "raw request" tool for the rare Taiga API endpoint that doesn't have a dedicated tool yet (webhooks, import/export, and similar admin-level features).
Before you start
You need:
A Taiga account — either on Taiga Cloud or a self-hosted Taiga instance.
Node.js version 22.11 or newer, or version 24 or newer.
An AI assistant that supports MCP — Claude Desktop, Claude Code, Cursor, Windsurf, or any other MCP-compatible client.
You do not need to install or run anything Taiga-related yourself — this connects to your existing Taiga account over the internet (or your self-hosted instance's URL).
Install
You don't need to install this by hand. Your AI assistant will download and run it automatically the first time it's used, via npx. If you'd rather install it yourself:
# Run it once, without installing anything permanently
npx -y @madebyclowd/taiga-mcp-serverOr install it globally, using whichever package manager you already use — you only need one of these:
pnpm add -g @madebyclowd/taiga-mcp-server
# or
npm install -g @madebyclowd/taiga-mcp-serverSet it up with Claude Desktop, Claude Code, Cursor, or Windsurf
All of these tools use the same kind of config file, usually a JSON file with an mcpServers section. Add this to yours:
Option A: using a Taiga access token (recommended)
This is the safer option — your password is never stored anywhere.
Log into Taiga in your browser.
Get your auth token (in Taiga Cloud, this is available via your account settings or the API; for self-hosted Taiga, ask your admin how tokens are issued).
Add this to your config:
{
"mcpServers": {
"taiga": {
"command": "npx",
"args": ["-y", "@madebyclowd/taiga-mcp-server"],
"env": {
"TAIGA_BASE_URL": "https://api.taiga.io",
"TAIGA_TOKEN": "your-taiga-auth-token"
}
}
}
}Option B: using your username and password
{
"mcpServers": {
"taiga": {
"command": "npx",
"args": ["-y", "@madebyclowd/taiga-mcp-server"],
"env": {
"TAIGA_BASE_URL": "https://api.taiga.io",
"TAIGA_USERNAME": "your-username",
"TAIGA_PASSWORD": "your-password"
}
}
}
}Using self-hosted Taiga? Just change TAIGA_BASE_URL to your own instance's URL, for example https://taiga.mycompany.com.
After saving the config, restart your AI assistant (or reload its MCP connections). It should now show Taiga tools as available.
Running it as a shared HTTP server instead
The setup above (called "stdio") runs a private copy of the server just for you, on your own computer. If you instead want to run one shared server that a team can connect to over the network, use the HTTP mode.
The important difference: in HTTP mode, nobody's Taiga login is stored on the server. Each person connecting sends their own Taiga token with each request, so everyone keeps their own Taiga permissions and audit trail — nobody has to share one account.
# Start the HTTP server — same package, a different command it exposes
npx -y --package=@madebyclowd/taiga-mcp-server -- taiga-mcp-server-httpEach client connects by sending their Taiga token in a standard HTTP header:
POST /mcp HTTP/1.1
Host: your-server:3000
Content-Type: application/json
Authorization: Bearer <your-taiga-auth-token>If you're exposing this server on the internet (not just on your own machine or local network), read the HTTP_ALLOWED_ORIGINS note in the settings table below — the default is permissive on purpose for easy local/team use, and you should lock it down for a public deployment.
All settings (environment variables)
Used by both modes
Setting | Required? | What it does | Default |
| Yes | The Taiga API address to connect to. |
|
| No | How much the server logs ( |
|
| No |
| unset (fallback allowed) |
Only for the normal (stdio) mode
Setting | Required? | What it does |
| One of these three is required | Your Taiga access token. Preferred over username/password. |
| Required if you're not using a token | Your Taiga username. |
| Required if you're not using a token | Your Taiga password. |
Only for HTTP server mode
In HTTP mode, the server itself doesn't hold any Taiga login — each connecting client sends its own token, so none of the settings below are about credentials.
Setting | Required? | What it does | Default |
| No | Which network port the server listens on. |
|
| No | Comma-separated list of websites allowed to connect from a browser (CORS). If unset, any website is allowed — fine for local/team use, but set this explicitly if you're exposing the server publicly. | unset (any site allowed) |
| No | How long an idle connection stays open before it's automatically closed, in milliseconds. |
|
| No | The most connections the server will hold open at once, to keep memory use bounded. |
|
What's covered, and how it handles problems
Plain description of what happens behind the scenes, so you know what to expect:
It uses your own Taiga permissions. If you can't see or edit something in Taiga's own web app, this server can't either — it's making the same API calls your browser would.
Your password/token is never written to disk or logged. It's only kept in memory while the server is running.
If two people edit the same item at the same time, Taiga would normally reject the second save. This server automatically re-fetches the latest version and retries the save once instead of just failing.
If Taiga temporarily rate-limits requests, the server waits and retries automatically instead of giving up right away.
Errors are returned in a structured way (which field was wrong, and why) instead of a generic "something went wrong" — this helps the AI assistant actually understand and fix the problem instead of guessing.
Tested against the real Taiga API, not just simulated responses — the automated test suite includes tests that run against an actual Taiga project, in addition to the usual offline tests.
Released with npm provenance — a signed record proving the published package was built from this exact GitHub repository, not modified or uploaded from somewhere else.
Breaking change in 1.0.0
Every list-shaped tool (*_list, comment_list, attachment_list, epic_related_user_stories, search) now returns { items, pagination } instead of a bare array. If you have code parsing one of these responses directly as an array, read .items instead. pagination is { count, current_page, has_next }. This is the point at which the tool surface's response shapes are considered stable — it's been tested carefully, including live against the real Taiga API, but hasn't had real-world use by others yet, so if you hit a problem, please report it.
Frequently asked questions
What is Taiga? Taiga is a project management tool, similar to Jira or Linear — used for tracking epics, user stories, tasks, bugs, and sprints.
What is MCP / Model Context Protocol? It's a standard that lets AI assistants (like Claude) connect to external tools and data sources in a consistent way, instead of every integration being custom-built. This package implements that standard for Taiga.
How do I connect Claude (or Cursor, Windsurf) to Taiga? Add this package to your assistant's MCP config with your Taiga token — see Set it up above. It works the same way for any MCP-compatible client, not just Claude.
Is this made by the Taiga team? No. This is an independent, open-source project, not affiliated with or endorsed by Taiga/Kaleidos.
Do I need to run my own server? No, for normal personal use. Your AI assistant starts and stops this server automatically in the background. You only need to run it yourself as a standalone server if you're setting it up for a team (see HTTP mode).
Does this work with self-hosted Taiga, or only Taiga Cloud?
Both. Just point TAIGA_BASE_URL at your own instance.
Is it safe to give this my Taiga password? You don't have to — a Taiga access token (Option A above) is the recommended way, and your password never gets involved at all. If you do use username/password, it's only kept in memory, never written to disk or logged.
Can it do things I'm not allowed to do in Taiga? No. It uses your own Taiga account and is limited to the exact same permissions you already have.
Contributing / running the tests
# Install dependencies
pnpm install
# Build
pnpm build
# Lint, format check, type-check
pnpm lint
pnpm format
pnpm typecheck
# Run the offline test suite
pnpm test
# Check dependencies for known security issues
pnpm audit
# Run the live test suite against a real Taiga project (see docs/testing.md)
pnpm test:integrationSee docs/testing.md for how to set up the live-test project.
Security
See SECURITY.md for how to privately report a security problem.
License
MIT.
Available Tools
70 toolsattachment_deleteDelete AttachmentADestructive
Delete an attachment by id. This cannot be undone. Requires confirmation: elicitation-capable clients are prompted interactively; others must call again with confirm: true after reviewing the preview returned by the first call.
Inputs: id (required), resource (required), confirm.
attachment_downloadDownload AttachmentARead-only
Download an attachment's file contents as base64, along with its filename, content type, size, and sha1. Rejects files larger than 10485760 bytes before downloading.
Inputs: id (required), resource (required).
attachment_listList AttachmentsARead-only
List attachments on an epic, user story, task, issue, or wiki page. Response is { items, pagination }.
Inputs: resource (required), object_id (required), page, page_size, +1 more.
attachment_uploadUpload AttachmentA
Upload a file attachment to an epic, user story, task, issue, or wiki page. File contents are passed as base64.
Inputs: project (required), resource (required), file_name (required), object_id (required), +3 more.
batch_create_issuesBatch Create IssuesA
Create up to 20 issues in one call. Each item is created independently — a bad item doesn't fail the others. Returns a structured result with per-item success/failure, not a native Taiga bulk-create (which can't carry per-item fields).
Inputs: items (required), project (required).
batch_create_tasksBatch Create TasksA
Create up to 20 tasks in one call, each under its own parent user story. Each item is created independently — a bad item doesn't fail the others. Returns a structured result with per-item success/failure, not a native Taiga bulk-create (which can't carry per-item fields).
Inputs: items (required), project (required).
batch_create_user_storiesBatch Create User StoriesA
Create up to 20 user stories in one call. Each item is created independently — a bad item doesn't fail the others. Returns a structured result with per-item success/failure, not a native Taiga bulk-create (which can't carry per-item fields).
Inputs: items (required), project (required).
comment_addAdd CommentA
Add a comment to an epic, user story, task, or issue. Goes through the same optimistic-concurrency path as a normal update.
Inputs: id (required), comment (required), resource (required).
comment_deleteDelete CommentADestructive
Delete a comment from an epic, user story, task, or issue. This cannot be undone. Requires confirmation: elicitation-capable clients are prompted interactively; others must call again with confirm: true after reviewing the preview returned by the first call.
Inputs: id (required), resource (required), comment_id (required), confirm.
comment_editEdit CommentAIdempotent
Edit the text of an existing comment on an epic, user story, task, or issue. Not gated — editing isn't destructive.
Inputs: id (required), comment (required), resource (required), comment_id (required).
comment_listList CommentsARead-only
List the comment history for an epic, user story, task, or issue. Includes plain field-change history entries too — filter on a non-empty comment field for comments only. Response is { items, pagination }.
Inputs: id (required), resource (required), page, page_size, +1 more.
epic_createCreate EpicA
Create a new epic. Note: if the project's Epics module isn't enabled (is_epics_activated), the epic is still created via the API but stays invisible in Taiga's web UI (no nav item, in-app links 404) until the module is enabled — use project_update to enable it.
Inputs: project (required), subject (required), tags, color, +5 more.
epic_deleteDelete EpicADestructive
Delete a epic by id. This cannot be undone. Requires confirmation: elicitation-capable clients are prompted interactively; others must call again with confirm: true after reviewing the preview returned by the first call.
Inputs: id (required), confirm.
epic_getGet EpicARead-only
Get a single epic by id.
Inputs: id (required), verbosity.
epic_link_user_storyLink User Story to EpicAIdempotent
Link an existing user story to an epic.
Inputs: id (required), user_story (required).
epic_listList EpicsARead-only
List epics, optionally filtered by the given query parameters. Response is { items, pagination } — pagination has { count, current_page, has_next } read from Taiga. Default page_size is 30.
Inputs: project (required), q, page, status, +3 more.
epic_unlink_user_storyUnlink User Story from EpicAIdempotent
Unlink a user story from an epic.
Inputs: id (required), user_story (required).
epic_updateUpdate EpicAIdempotent
Update an existing epic (partial patch — only include the fields you want to change). Taiga's optimistic-concurrency version field is handled automatically; do not pass it.
Inputs: id (required), tags, color, status, +5 more.
issue_createCreate IssueC
Create a new issue.
Inputs: type (required), project (required), subject (required), priority (required), +7 more.
issue_deleteDelete IssueADestructive
Delete a issue by id. This cannot be undone. Requires confirmation: elicitation-capable clients are prompted interactively; others must call again with confirm: true after reviewing the preview returned by the first call.
Inputs: id (required), confirm.
issue_filters_dataIssue Filter OptionsARead-only
Get the valid filter values (types, statuses, priorities, severities, tags, assigned users, roles) for issues in a project, each with a live item count — cheaper than a full issue_list call just to discover ids.
Inputs: project (required).
issue_getGet IssueARead-only
Get a single issue by id.
Inputs: id (required), verbosity.
issue_listList IssuesARead-only
List issues, optionally filtered by the given query parameters. Response is { items, pagination } — pagination has { count, current_page, has_next } read from Taiga. Default page_size is 30. Use issue_filters_data to discover valid type/status/priority/severity/tags/assigned_to ids cheaply instead of paging through results.
Inputs: project (required), q, page, type, +6 more.
issue_set_classificationA
Set an issue's type/status/priority/severity in one call (only the fields provided are changed). Convenience wrapper over issue_update for this common triage action.
Inputs: id (required), type, status, priority, +1 more.
issue_updateUpdate IssueAIdempotent
Update an existing issue (partial patch — only include the fields you want to change). Taiga's optimistic-concurrency version field is handled automatically; do not pass it.
Inputs: id (required), tags, type, status, +7 more.
membership_bulk_createBulk Invite Project MembersA
Invite multiple members to a project in one call. Each entry needs a role id and either a username or an email — this will send real invitation emails for entries that don't match an existing user.
Inputs: project_id (required), bulk_memberships (required).
membership_createCreate Project MemberC
Create a new membership.
Inputs: role (required), project (required), email, username.
membership_deleteDelete Project MemberADestructive
Delete a membership by id. This cannot be undone. Requires confirmation: elicitation-capable clients are prompted interactively; others must call again with confirm: true after reviewing the preview returned by the first call.
Inputs: id (required), confirm.
membership_getGet Project MemberARead-only
Get a single membership by id.
Inputs: id (required), verbosity.
membership_listList Project MembersARead-only
List memberships, optionally filtered by the given query parameters. Response is { items, pagination } — pagination has { count, current_page, has_next } read from Taiga. Default page_size is 30.
Inputs: project (required), page, page_size, verbosity.
membership_resend_invitationResend InvitationA
Resend a pending project invitation email.
Inputs: id (required).
membership_updateUpdate Project MemberAIdempotent
Update an existing membership (partial patch — only include the fields you want to change). Taiga's optimistic-concurrency version field is handled automatically; do not pass it.
Inputs: id (required), role, is_admin.
milestone_createCreate MilestoneC
Create a new milestone.
Inputs: name (required), project (required), estimated_start (required), estimated_finish (required).
milestone_deleteDelete MilestoneADestructive
Delete a milestone by id. This cannot be undone. Requires confirmation: elicitation-capable clients are prompted interactively; others must call again with confirm: true after reviewing the preview returned by the first call.
Inputs: id (required), confirm.
milestone_getGet MilestoneARead-only
Get a single milestone by id.
Inputs: id (required), verbosity.
milestone_listList MilestonesARead-only
List milestones, optionally filtered by the given query parameters. Response is { items, pagination } — pagination has { count, current_page, has_next } read from Taiga. Default page_size is 30.
Inputs: project (required), page, page_size, verbosity.
milestone_statsA
Get burndown/points stats for a milestone (sprint): total and completed points, user stories, tasks, and per-day breakdown.
Inputs: id (required).
milestone_updateUpdate MilestoneAIdempotent
Update an existing milestone (partial patch — only include the fields you want to change). Taiga's optimistic-concurrency version field is handled automatically; do not pass it.
Inputs: id (required), name, closed, estimated_start, +1 more.
project_createCreate ProjectD
Create a new project.
Inputs: name (required), description (required), is_private.
project_deleteDelete ProjectADestructive
Delete a project by id. This cannot be undone. Requires confirmation: elicitation-capable clients are prompted interactively; others must call again with confirm: true after reviewing the preview returned by the first call.
Inputs: id (required), confirm.
project_getGet ProjectARead-only
Get a single project by id.
Inputs: id (required), verbosity.
project_listList ProjectsARead-only
List projects, optionally filtered by the given query parameters. Response is { items, pagination } — pagination has { count, current_page, has_next } read from Taiga. Default page_size is 30.
Inputs: q, page, member, page_size, +1 more.
project_updateUpdate ProjectAIdempotent
Update an existing project (partial patch — only include the fields you want to change). Taiga's optimistic-concurrency version field is handled automatically; do not pass it.
Inputs: id (required), name, is_private, description, +5 more.
ref_resolveResolve RefARead-only
Resolve a project-scoped ref (e.g. "#436" or 436) to its type (issue, user_story, task, or epic) and numeric id, without fetching full details.
Inputs: ref (required), project (required).
searchSearchARead-only
Project-scoped text search across epics, user stories, tasks, issues, and wiki pages. Returns id/title matches grouped by type. Response is { items: {epics, userstories, tasks, wikipages, issues}, pagination }.
Inputs: text (required), project (required).
taiga_raw_requestRaw Taiga API RequestA
Escape hatch: make a raw request to any /api/v1/ endpoint on the configured Taiga instance, for functionality not covered by a dedicated tool (importers, webhooks, application tokens, notify policies, project templates, export/import, etc.). Prefer a dedicated tool when one exists.
Inputs: path (required), method (required), body, query.
task_createCreate TaskC
Create a new task.
Inputs: project (required), subject (required), user_story (required), tags, +5 more.
task_deleteDelete TaskADestructive
Delete a task by id. This cannot be undone. Requires confirmation: elicitation-capable clients are prompted interactively; others must call again with confirm: true after reviewing the preview returned by the first call.
Inputs: id (required), confirm.
task_filters_dataTask Filter OptionsARead-only
Get the valid filter values (statuses, tags, assigned users, roles) for tasks in a project, each with a live item count — cheaper than a full task_list call just to discover ids.
Inputs: project (required).
task_getGet TaskARead-only
Get a single task by id.
Inputs: id (required), verbosity.
task_listList TasksARead-only
List tasks, optionally filtered by the given query parameters. Response is { items, pagination } — pagination has { count, current_page, has_next } read from Taiga. Default page_size is 30. Use task_filters_data to discover valid status/tags/assigned_to ids cheaply instead of paging through results.
Inputs: project (required), page, status, milestone, +3 more.
task_updateUpdate TaskAIdempotent
Update an existing task (partial patch — only include the fields you want to change). Taiga's optimistic-concurrency version field is handled automatically; do not pass it.
Inputs: id (required), tags, status, subject, +5 more.
user_story_assign_milestoneA
Move a user story into a milestone/sprint (or out of one, by omitting milestone). Convenience wrapper over user_story_update.
Inputs: id (required), milestone.
user_story_createCreate User StoryC
Create a new user_story.
Inputs: project (required), subject (required), tags, points, +5 more.
user_story_deleteDelete User StoryADestructive
Delete a user_story by id. This cannot be undone. Requires confirmation: elicitation-capable clients are prompted interactively; others must call again with confirm: true after reviewing the preview returned by the first call.
Inputs: id (required), confirm.
user_story_filters_dataUser Story Filter OptionsARead-only
Get the valid filter values (statuses, tags, assigned users, epics, roles) for user stories in a project, each with a live item count — cheaper than a full user_story_list call just to discover ids.
Inputs: project (required).
user_story_getGet User StoryARead-only
Get a single user_story by id.
Inputs: id (required), verbosity.
user_story_listList User StoriesARead-only
List user_storys, optionally filtered by the given query parameters. Response is { items, pagination } — pagination has { count, current_page, has_next } read from Taiga. Default page_size is 30. Use user_story_filters_data to discover valid status/tags/assigned_to/epic ids cheaply instead of paging through results.
Inputs: project (required), q, epic, page, +4 more.
user_story_updateUpdate User StoryAIdempotent
Update an existing user_story (partial patch — only include the fields you want to change). Taiga's optimistic-concurrency version field is handled automatically; do not pass it.
Inputs: id (required), tags, points, status, +5 more.
vote_addUpvoteAIdempotent
Upvote an epic, user story, task, or issue. Milestones and wiki pages don't support voting.
Inputs: id (required), resource (required).
vote_removeRemove VoteAIdempotent
Remove your vote from an epic, user story, task, or issue.
Inputs: id (required), resource (required).
watch_addWatchAIdempotent
Watch an epic, user story, task, issue, milestone, or wiki page for update notifications.
Inputs: id (required), resource (required).
watch_removeUnwatchAIdempotent
Stop watching an epic, user story, task, issue, milestone, or wiki page.
Inputs: id (required), resource (required).
wiki_page_createCreate Wiki PageC
Create a new wiki_page.
Inputs: slug (required), content (required), project (required).
wiki_page_deleteDelete Wiki PageADestructive
Delete a wiki_page by id. This cannot be undone. Requires confirmation: elicitation-capable clients are prompted interactively; others must call again with confirm: true after reviewing the preview returned by the first call.
Inputs: id (required), confirm.
wiki_page_getGet Wiki PageARead-only
Get a single wiki_page by id.
Inputs: id (required), verbosity.
wiki_page_get_by_slugA
Get a wiki page by its project-scoped slug instead of its numeric id.
Inputs: slug (required), project (required).
wiki_page_listList Wiki PagesARead-only
List wiki_pages, optionally filtered by the given query parameters. Response is { items, pagination } — pagination has { count, current_page, has_next } read from Taiga. Default page_size is 30.
Inputs: project (required), page, page_size, verbosity.
wiki_page_updateUpdate Wiki PageAIdempotent
Update an existing wiki_page (partial patch — only include the fields you want to change). Taiga's optimistic-concurrency version field is handled automatically; do not pass it.
Inputs: id (required), slug, content.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 70 tools
Every tool targets a distinct resource and action, even the convenience wrappers (user_story_assign_milestone, issue_set_classification) are clearly specialized and documented. The only near-overlap (single vs bulk create) is explicitly distinguished.
The overwhelming majority follow a clear `<resource>_<action>` snake_case pattern (e.g., task_get, project_create, milestone_delete). However, a few deviate: `search`, `ref_resolve`, `taiga_raw_request`, and the `batch_create_*`/`*_filters_data` tools, mixing verb-first and modifier-first ordering.
70 tools is excessive for an agent to choose from, even for a full-featured project management API. While each tool has a purpose, the server could have consolidated CRUD operations (e.g., a generic `list_<type>`) to reduce clutter.
CRUD is covered for all main entities (projects, epics, user stories, tasks, issues, milestones, wiki pages, memberships) plus comments, attachments, votes, watches, search, and reference resolution. Some niche Taiga features (import/export, webhooks) are only reachable via the raw-request escape hatch, but the core domain is well covered.
Maintenance
Related MCP Connectors
Open your team's project from the AI you use: read and write its brief, documents, tasks and notes.
Connects AI assistants to TrackingTime for querying time entries, projects, tasks, customers, and team data using natural language.
Manage Orangescrum projects, tasks, users, sprints, test cases, releases, and risks from AI tools.
Manage projects, tasks, time tracking, and team collaboration through natural language.
Related MCP Servers
- AlicenseBqualityDmaintenanceA protocol bridge that connects AI systems to Taiga project management platform, enabling AI tools to create and manage projects, epics, user stories, tasks, issues, and sprints.9438MIT
- AlicenseNot gradedqualityDmaintenanceEnables seamless integration between Large Language Models and Taiga project management platform, allowing users to manage projects, user stories, tasks, and team collaboration through natural language commands.4GPL 3.0
- AlicenseDqualityDmaintenanceEnables natural language interaction with Taiga project management systems, allowing management of projects, sprints, user stories, tasks, and issues through conversational AI.4679 npm7ISC
- AlicenseCqualityDmaintenanceEnables natural language interaction with Taiga project management tool to list projects, view details, and create user stories.69ISC