Skip to main content
The SuperDoc MCP server lets AI agents open, read, edit, and save .docx files. It exposes the same operations as the Document API through the Model Context Protocol: the open standard for connecting AI tools to agents.

How it works

Your MCP client spawns the server as a local subprocess and talks to it over stdio. The server embeds the SuperDoc document engine — the same engine the browser editor uses — and manages documents as in-memory sessions: superdoc_open loads a file and returns a session_id, every tool call targets that session, and nothing touches disk until superdoc_save. A typical conversation, end to end: Everything runs locally — SuperDoc never uploads your files. The AI agent you connect still sends document content to its own model provider as tool results.

Setup

Install once. Your MCP client spawns the server automatically on each conversation.

Tools

The server registers one of two tool surfaces, selected by the MCP_PRESET environment variable. All tools except superdoc_open take a session_id from superdoc_open. To use the core surface, add the env to your client config:

Lifecycle

Intent tools

These are the legacy preset’s tools (the default surface). With MCP_PRESET=core the server registers superdoc_inspect and superdoc_perform_action instead — see the core preset reference for its 40 actions, selectors, and receipts.
Multi-action tools use an action argument to select the underlying operation. superdoc_search is a single-action tool and does not require action.
  • How to use: workflow patterns, targeting, and common operations
  • Debugging: inspect and troubleshoot MCP tool calls
  • LLM Tools: build custom LLM integrations with the SDK
  • CLI: edit documents from the terminal