What dependencies or runtime are required?
Node.js and either `npx` (for quick start) or a local clone with `pnpm` installed for building.
@AnthonyUtt
Basic information
Basic MCP server for interacting with Vikunja to-do app
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"vikunja": {
"command": "npx",
"args": [
"-y",
"vikunja-mcp"
],
"env": {
"VIKUNJA_API_BASE": "https://app.vikunja.cloud",
"VIKUNJA_API_TOKEN": ""
}
}
}
}List all projects
Get a specific project by ID
Create a new project
Update an existing project
Delete a project by ID
List all tasks across all projects
List all tasks for a specific project
Get a specific task by ID
Create a new task in a project
Update an existing task by ID
Delete a specific task by ID. This action cannot be undone, so use with caution.
Create a relation between two tasks
Delete a relation between two tasks
Get the comments for a specific task
Create a comment for a specific task
Update a comment for a specific task
Delete a comment for a specific task
List all attachments for a specific task
Attach a file to a task
Get a specific attachment for a task
Delete a specific attachment for a task
vikunja-mcp is a basic Model Context Protocol server for Vikunja, a task management platform. It enables AI assistants like Claude to interact with Vikunja to manage projects and tasks.
Install it via npx or build locally, then configure your MCP client with the vikunja-mcp command and environment variables VIKUNJA_API_BASE and VIKUNJA_API_TOKEN. For example, add a "vikunja" entry under mcpServers in your Claude configuration.
Node.js and either `npx` (for quick start) or a local clone with `pnpm` installed for building.
You provide a Vikunja API token via the `VIKUNJA_API_TOKEN` environment variable. The token must have appropriate permissions for the operations you intend to use.
It runs as a subprocess via `stdio` – the command and arguments are specified in the client’s MCP server configuration.
Only the `title`, `description`, and `done` fields are supported when adding a task.
All data resides in your Vikunja instance, which is accessed via the `VIKUNJA_API_BASE` URL you configure. The server does not store anything locally.

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
🚀 The fast, Pythonic way to build MCP servers and clients.
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct

Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3
Open-source MCP to use Blender with any LLM
Comments