Tana MCP Server
Tana MCP 服务器
连接到Tana 的输入 API 的模型上下文协议 (MCP)服务器,允许大型语言模型 (LLM) 和其他 MCP 客户端在 Tana 工作区中创建和操作数据。
特征
该 MCP 服务器完全实现了 Tana 输入 API 的所有功能:
Available Tools
11 toolscreate_checkbox_nodeD
Inputs: name (required), checked (required), targetNodeId, description, +1 more.
create_date_nodeD
Inputs: date (required), targetNodeId, description, supertags.
create_fieldD
Inputs: name (required), targetNodeId, description.
create_field_nodeD
Inputs: attributeId (required), targetNodeId, children.
create_file_nodeD
Inputs: fileData (required), filename (required), contentType (required), targetNodeId, +2 more.
create_node_structureD
Inputs: node (required), targetNodeId.
create_plain_nodeD
Inputs: name (required), targetNodeId, description, supertags.
create_reference_nodeD
Inputs: referenceId (required), targetNodeId.
create_supertagD
Inputs: name (required), targetNodeId, description.
create_url_nodeD
Inputs: url (required), targetNodeId, description, supertags.
set_node_nameD
Inputs: nodeId (required), newName (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 11 tools
The tools have overlapping purposes with unclear boundaries, as multiple 'create_' tools (e.g., create_checkbox_node, create_plain_node, create_file_node) seem to create different node types without clear distinctions in their descriptions. While they target different node types, the lack of descriptions makes it ambiguous when to use one over another, especially for similar-sounding tools like create_field and create_field_node.
The tool names follow a highly consistent verb_noun pattern throughout, with all tools using 'create_' or 'set_' prefixes followed by descriptive nouns (e.g., create_checkbox_node, set_node_name). There are no deviations in naming conventions, making the set predictable and readable.
With 11 tools, the count is reasonable for a server focused on node creation and management in Tana. It is well-scoped, though slightly on the higher side, as each tool appears to serve a specific node type or action, earning its place without being excessive.
The tool surface is significantly incomplete for node management, as it only includes creation and naming tools (e.g., create_* and set_node_name) with no obvious operations for reading, updating, or deleting nodes. This lack of CRUD coverage will likely cause agent failures when trying to perform full lifecycle management.
Maintenance
Related MCP Connectors
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
MCP server for generating rough-draft project plans from natural-language prompts.
One MCP server for the services your AI needs: memory, files, Microsoft 365, kanban and more.
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceA Model Context Protocol (MCP) server implementation that enables AI assistants to interact with Anytype's API through natural language, allowing users to manage their knowledge base through conversation.77,112 npm545MIT
- AlicenseNot gradedqualityAmaintenanceAn MCP server that connects AI assistants to Super Productivity for managing tasks, projects, and tags. Supports quick capture, batch triage, and full planning sessions through natural language.407 npm139MIT
- AlicenseAqualityDmaintenanceA Model Context Protocol (MCP) server that connects AI assistants to your TickTick tasks, enabling task management through natural language.81MIT
- FlicenseNot gradedqualityDmaintenanceAn MCP server that provides an AI LLM orchestrator supporting multiple providers (LM Studio, Ollama, OpenAI, generic) plus SQLite-backed memory, kanban, and todo databases for persistent task and knowledge management.-