Another Planka

Bridges MCP clients with Planka to read workspace data and perform write actions via the Planka REST API.

python

GitHub Stars

python

Language

4 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "roelven-another-planka-mcp": {
      "command": "python",
      "args": [
        "planka_mcp.py"
      ],
      "env": {
        "PLANKA_EMAIL": "user@example.com",
        "PLANKA_BASE_URL": "https://your-planka-instance.com",
        "PLANKA_PASSWORD": "your-password",
        "PLANKA_API_TOKEN": "<token>"
      }
    }
  }
}

Another Planka MCP Server provides a lightweight bridge between MCP clients and your self-hosted Planka instance. It exposes workspace data such as projects, boards, lists, cards, tasks, and labels, and enables write operations like creating or updating cards through MCP tools. This lets AI chat clients read your Planka data and perform actions securely within your access permissions.

How to use

You connect an MCP client to your Planka instance to read data and perform actions such as creating or updating cards, moving cards between lists, and retrieving detailed card information. Use the MCP client to issue high-level requests like listing all cards in a board, finding specific cards by keywords, or creating a new card with subtasks. The MCP server enforces the same permissions as your Planka user.

How to install

Prerequisites you need before installation.

Step-by-step commands to set up the server locally.

Additional setup and configuration

Configure access to your Planka instance and enable MCP protocol compatibility. You can authenticate with a JWT access token or fallback to Planka login credentials. The MCP server runs alongside your Planka API and uses the same permissions rules as your Planka user.

Explicit MCP configuration for Claude Desktop shows how to start the local MCP server process and pass environment variables. Use the following configuration in your Claude Desktop client to connect to your local MCP server.

{
  "mcpServers": {
    "planka": {
      "command": "/absolute/path/to/venv/bin/python",
      "args": ["mcp_server.py"],
      "env": {
        "PLANKA_BASE_URL": "https://your.domain",
        "PLANKA_API_TOKEN": "<token>"
      }
    }
  }
}

Security & permissions

The MCP server accesses only what your authenticated Planka user can access. Use a token rather than email/password whenever possible, and expose your Planka instance over HTTPS if it is accessible externally. Consider using a dedicated Planka service user with restricted permissions to limit access scope.

Troubleshooting & FAQ

401 Unauthorized errors usually indicate an invalid or expired token or misconfigured environment variables. If a client cannot connect, verify the Python path, firewall rules, and execution permissions. If no boards or cards are returned, confirm that your Planka user has access to the workspace.

Notes & running locally

Development and test guidance are available, including how to run tests in a Python environment and how to perform MCP protocol inspection with dedicated tooling. You can start the MCP server in stdio mode to ensure better compatibility with MCP clients.

# Start the standard Planka MCP server (direct MCP protocol)
python mcp_server.py

Available tools

planka_get_workspace

Read workspace structure to retrieve boards, lists, users, and labels.

planka_list_cards

List cards with detail levels and filters.

planka_find_and_get_card

Search for a specific card and fetch its details.

planka_create_card

Create a new card with title, description, labels, and subtasks.

planka_update_card

Update an existing card, including its title, description, labels, and subtasks.

Built by

VeilStrat

AI signals for GTM teams