Tana MCP Server

Tana workspace nodes, fields, and structures via the Tana Input API.

Data last scanned today · Reviewed today

3512 tools★ 40TypeScriptMIT

Overview

This MCP server provides a direct bridge to the Tana Input API, allowing AI agents to generate, format, and organize content within your workspace. It features 12 specific tools for node creation, ranging from simple text and checkboxes to structured hierarchies and file attachments, alongside support for schema definition via supertags and fields. Beyond basic node manipulation, the server includes four predefined prompt templates for tasks, projects, meeting notes, and knowledge entries. These facilitate complex interactions with Tana by automating document structures, while built-in resources provide documentation and usage examples directly to your assistant.

Our verdict

This server carries a high risk level with a security score of 35/100. It is a community-maintained project that has not undergone editorial review, and the authentication and read-only mechanisms remain unverified. Due to these factors, this tool should only be used in non-critical environments where potential misconfigurations of the Tana Input API do not impact sensitive data.

Four prompt templates for structured workflow automation
Twelve granular tools for node and schema manipulation
Lightweight codebase with only four direct dependencies
Detailed README documentation for configuration and usage

Security mechanisms like OAuth remain unreviewed
Limited community presence with only two contributors
Lack of an official vendor maintenance track

Setup

Claude Desktop

{
  "mcpServers": {
    "tana-mcp": {
      "args": [
        "-y",
        "tana-mcp"
      ],
      "command": "npx"
    }
  }
}

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows), then restart Claude Desktop. Some servers require API keys or tokens as environment variables — check the project's README and add an "env" object if needed.

No read-only mode — running this grants full read/write access.
No built-in authentication — anyone with access to this config can invoke every tool it exposes.

Tools

Tool	Description	Risk
create_plain_node	Create simple text nodes with optional supertags	medium
create_formatted_node	Create nodes with rich formatting and inline references	medium
create_reference_node	Create references to existing nodes	medium
create_date_node	Create date nodes (supports various ISO 8601 formats)	medium
create_url_node	Create URL/link nodes	medium
create_checkbox_node	Create checkbox/task nodes	medium
create_file_node	Create file attachment nodes (base64 encoded)	medium
create_node_structure	Create complex nested node hierarchies	medium
create_supertag	Define new supertags in your schema	medium
create_field	Define new fields in your schema	medium

Compatibility

Client	Local	Docker	Remote	Read-only
Windsurf
ChatGPT
Claude Desktop
Cursor
VS Code

Frequently asked questions

›What prerequisites are needed to use the Tana MCP server?

You need a Tana workspace with API access enabled, a Tana API token generated from your workspace settings, and an MCP-compatible client like Claude Desktop, Claude Code, or Raycast.

›How do I obtain a Tana API token?

Navigate to the Settings icon in your Tana workspace, select 'API tokens', and click 'Create new token' to generate and copy your unique identifier.

›What is the TANA_DEFAULT_TARGET environment variable used for?

It is an optional configuration setting that defines the default destination for nodes created via the server, such as your Tana inbox.

›Can I use this server to modify existing nodes in Tana?

Yes, you can rename existing plain nodes using the set_node_name tool or add field values to existing nodes using the add_field_value tool.

›Does the server support creating complex data structures?

Yes, the server includes tools to create nested node hierarchies, define new supertags and fields, and create formatted nodes with inline references.