Click on "Install 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 List all my Taiga projects"
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.
An MCP (Model Context Protocol) server that allows you to interact with Taiga using natural language. This server enables you to list your projects and create user stories within your chosen project.
List all your Taiga projects
Get detailed information about a specific project
Create user stories within a project
List user stories in a project
Related MCP server: backlog-mcp-server
Node.js (v14 or higher)
npm
A Taiga account
Clone this repository:
git clone <repository-url>
cd mcpTAIGAInstall dependencies:
npm installConfigure your Taiga credentials:
Edit the .env file and add your Taiga credentials:
TAIGA_API_URL=https://api.taiga.io/api/v1
TAIGA_USERNAME=your_username
TAIGA_PASSWORD=your_password
#OPENAI_API_KEY=your_openai_api_keyStart the MCP server:
npm startThe server will start and listen for MCP requests via standard input/output.
If you don't use Claude Desktop, Cursor, Windsurf or any client to use the MCP server, you can setup the OPENAI_API_KEY in .env file and execute:
node openaiClient.jsYou can connect to the MCP server using any MCP client, such as the MCP Inspector or by using the MCP client SDK.
The server provides the following tools:
authenticate - Authenticate with Taiga
listProjects - List all your Taiga projects
getProject - Get detailed information about a specific project
createUserStory - Create a new user story in a project
listUserStories - List all user stories in a project
More coming soon...
Configuration example:
"taiga-mcp": {
"command": "node",
"args": ["C:\\path\\to\\mcpTAIGA\\src\\index.js"]
}With WSL:
"taiga-mcp": {
"command": "wsl.exe",
"args": [
"bash",
"-c",
"cd /home/user/mcpTAIGA && /usr/bin/node src/index.js"
]
}Here are some example natural language prompts you can use with an LLM that supports MCP:
"List all my Taiga projects"
"Show me details about project X"
"Create a new user story in project Y with title 'Implement login feature'"
"Show me all user stories in project Z"
ISC
| Name | Required | Description | Default |
|---|---|---|---|
| password | No | ||
| username | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| tags | No | Array of tags | |
| status | No | Status name (e.g., "New", "In progress") | |
| subject | Yes | Task title/subject | |
| description | No | Task description | |
| projectIdentifier | Yes | Project ID or slug | |
| userStoryIdentifier | Yes | User story ID or reference number |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| tags | No | Array of tags | |
| status | No | Status name (e.g., "New", "In progress") | |
| subject | Yes | User story title/subject | |
| description | No | User story description | |
| projectIdentifier | Yes | Project ID or slug |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| projectIdentifier | Yes | Project ID or slug |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| projectIdentifier | Yes | Project ID or slug |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0authenticatecreateTaskcreateUserStorygetProjectlistProjectslistUserStoriesScored across 6 tools
Each tool targets a distinct resource and action: authentication, project listing vs. single project retrieval, and creating user stories vs. tasks. No two tools overlap in purpose.
All tool names follow a consistent verbNoun camelCase pattern (e.g., listProjects, createUserStory). The only slight exception is 'authenticate', which is a single verb, but it still fits the style.
With six tools, the server is well-scoped for a focused Taiga integration. Each tool covers a distinct core operation without unnecessary bloat.
The server covers authentication, listing/reading projects, and creating/list user stories plus creating tasks. Missing update, delete, and single-item retrieval for user stories and tasks, which limits full lifecycle coverage.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Manage projects, tasks, time tracking, and team collaboration through natural language.
Create and manage MeisterTask projects, tasks, and notes from your AI assistant.
Task manager your agent can fully operate: boards, tasks, sprints, roles, worklogs, day planner.
Track stories, organize sprints, and manage project workflows across your team
