@illodev/taiga-mcp
Full-featured MCP server for Taiga project management, enabling AI agents to manage projects, epics, user stories, tasks, issues, sprints, wiki pages, memberships, and roles via Taiga API v1.
README
Taiga MCP Server
Full-featured MCP (Model Context Protocol) server for Taiga project management. Provides comprehensive access to Taiga's API v1, enabling AI agents to manage projects, epics, user stories, tasks, issues, sprints, wiki pages, memberships, roles, and more.
Features
Covers all Taiga API v1 endpoints:
- Projects — CRUD, stats, tags, likes, watching
- Epics — CRUD, bulk create, related user stories, voting, watching, attachments
- User Stories — CRUD, bulk operations, ordering, voting, watching, attachments
- Tasks — CRUD, bulk create, voting, watching, attachments
- Issues — CRUD, bulk create, voting, watching, attachments
- Milestones/Sprints — CRUD, stats, watching
- Wiki — Pages & links CRUD, watching, attachments
- Memberships — CRUD, bulk invite
- Roles — CRUD with permissions
- Users — List, get, me, stats, contacts
- Statuses — US/Task/Issue statuses, types, priorities, severities, points
- Custom Attributes — Definitions & values for epics, user stories, tasks, issues
- History & Comments — Change history, create/delete comments
- Search — Global project search
- Timeline — User & project timeline
- Resolver — Slug/ref to ID resolution
- Webhooks — CRUD, test, logs
- Export/Import — Project export & import
Setup
Environment Variables
| Variable | Description |
|---|---|
TAIGA_URL |
Taiga instance URL (e.g. https://taiga.example.com) |
TAIGA_USERNAME |
Taiga username |
TAIGA_PASSWORD |
Taiga password |
MCP Client Configuration (recommended)
The easiest way to use this server is via npx — no installation required:
{
"mcpServers": {
"taiga": {
"command": "npx",
"args": ["-y", "@illodev/taiga-mcp"],
"env": {
"TAIGA_URL": "https://taiga.example.com",
"TAIGA_USERNAME": "your-user",
"TAIGA_PASSWORD": "your-pass"
}
}
}
}
VS Code / GitHub Copilot — add the entry above to your
mcp.json.
Claude Desktop — add it undermcpServersinclaude_desktop_config.json.
Docker Compose
cp .env.example .env
# Edit .env with your Taiga credentials
docker compose up --build
Local Development
pnpm install
pnpm run dev
Build
pnpm run build
pnpm start
Agent Customizations
This project includes ready-to-use GitHub Copilot customizations under .github/ so your AI agents can work effectively with the Taiga MCP tools.
.github/
├── agents/ # Custom agents (10)
│ ├── taiga-project-manager.agent.md # Orchestrator — delegates to sub-agents
│ ├── taiga-user-stories.agent.md # User story CRUD, backlog, story points
│ ├── taiga-tasks.agent.md # Task CRUD, statuses, comments
│ ├── taiga-issues.agent.md # Bug triage & issue classification
│ ├── taiga-epics.agent.md # Epic CRUD, story-to-epic linking
│ ├── taiga-sprints.agent.md # Sprint lifecycle & burndown
│ ├── taiga-wiki.agent.md # Wiki pages, links, history
│ ├── taiga-team.agent.md # Members, roles, permissions
│ ├── taiga-reporter.agent.md # Project reports & analytics (read-only)
│ └── taiga-project-setup.agent.md # Project config, webhooks, export/import
├── instructions/ # Context-aware guidelines
│ ├── taiga-mcp-usage.instructions.md # Tool naming, ID resolution, common patterns
│ ├── taiga-workflows.instructions.md # Scrum/Kanban recipes, feature flows
│ └── taiga-orchestration.instructions.md # Agent delegation & coordination
└── skills/ # On-demand workflow skills
├── sprint-planning/SKILL.md # Create & manage sprints
├── backlog-grooming/SKILL.md # Refine stories, epics, and points
├── issue-triage/SKILL.md # Classify and prioritize issues
├── project-setup/SKILL.md # Configure a new project from scratch
├── project-reporting/SKILL.md # Generate stats and reports
├── team-management/SKILL.md # Manage members, roles, permissions
└── wiki-documentation/SKILL.md # Create and organize wiki pages
Custom Agents
| Agent | Role | Invoke |
|---|---|---|
| Taiga Project Manager | Orchestrator — delegates to specialized agents, resolves context | @Taiga Project Manager |
| Taiga User Stories | User story CRUD, backlog/kanban ordering, story points, comments | @Taiga User Stories |
| Taiga Tasks | Task CRUD, task statuses, comments, custom attributes | @Taiga Tasks |
| Taiga Issues | Bug triage, issue classification, severity/priority management | @Taiga Issues |
| Taiga Epics | Epic CRUD, story-to-epic linking, epic custom attributes | @Taiga Epics |
| Taiga Sprints | Sprint lifecycle, burndown stats, milestone management | @Taiga Sprints |
| Taiga Wiki | Wiki page CRUD, navigation links, comments, history | @Taiga Wiki |
| Taiga Team | Member invitations, role management, user profiles | @Taiga Team |
| Taiga Reporter | Project reports, burndown analysis, team activity summaries (read-only) | @Taiga Reporter |
| Taiga Project Setup | Project creation, status/workflow config, webhooks, export/import | @Taiga Project Setup |
Skills (slash commands)
| Skill | Description |
|---|---|
/sprint-planning |
Plan sprints, assign stories, track burndown |
/backlog-grooming |
Create epics, refine stories, set points, order backlog |
/issue-triage |
Create and classify issues with priority/severity |
/project-setup |
Set up a new project with statuses, roles, tags, and custom attributes |
/project-reporting |
Generate sprint, project, and team reports |
/team-management |
Invite members, assign roles, manage permissions |
/wiki-documentation |
Create and organize wiki pages and navigation |
Expanded Documentation
For detailed guides and examples, see the docs/ folder:
- Getting Started — Installation, configuration, and first steps
- Agent Architecture — Hub-and-spoke delegation, agent roles, and chaining
- Usage Examples — Practical examples for every agent domain
- Advanced Workflows — Multi-domain recipes: feature dev, sprint planning, bug lifecycle, project bootstrap
Instructions
Loaded automatically when relevant:
- taiga-mcp-usage — Tool naming conventions, ID resolution patterns, error handling
- taiga-workflows — Ready-made recipes for Scrum sprints, Kanban boards, feature development, bug resolution
- taiga-orchestration — Agent delegation patterns and multi-domain workflow coordination
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.