hedgedoc-mcp-server
Enables creating, reading, and managing HedgeDoc 1.x notes and Mermaid diagrams from AI agents via the MCP protocol.
README
HedgeDoc MCP Server
MCP server for HedgeDoc 1.x — the open-source collaborative markdown editor. Create notes and Mermaid diagrams from OpenCode and other MCP-compatible AI agents.
Note: This is built for HedgeDoc 1.x (formerly CodiMD). It uses the HedgeDoc 1.x API, which differs from HedgeDoc 2.
Tools
| Tool | Description |
|---|---|
hedgedoc_create_blank |
Create a blank note with the instance's default template |
hedgedoc_create |
Create a new note with a random ID |
hedgedoc_create_with_alias |
Create a new note with a custom URL alias (requires FreeURL mode) |
hedgedoc_create_diagram |
Create a note with a Mermaid diagram |
hedgedoc_read |
Read the raw markdown content of a note |
hedgedoc_info |
Get note metadata (title, description, timestamps, viewcount) |
hedgedoc_list_revisions |
List all available revisions of a note |
hedgedoc_get_revision |
Get the full content of a specific revision |
hedgedoc_publish_url |
Get the published (read-only) URL of a note |
hedgedoc_slide_url |
Get the slide presentation URL of a note |
hedgedoc_status |
Get the current status of the HedgeDoc instance |
Usage
export HEDGEDOC_URL="https://hedgedoc.your-instance.com"
uvx hedgedoc-mcp-server stdio
HedgeDoc 1.x does not use API tokens for note operations. Authentication is handled via session cookies (browser) or instance configuration (see Production Ready guide).
OpenCode config
{
"mcp": {
"hedgedoc": {
"type": "local",
"enabled": true,
"command": ["uvx", "hedgedoc-mcp-server", "stdio"],
"environment": {
"HEDGEDOC_URL": "https://hedgedoc.your-instance.com"
}
}
}
}
Requirements
| Requirement | Notes |
|---|---|
| HedgeDoc 1.x instance | Tested on 1.x. Not compatible with HedgeDoc 2. |
| Python 3.11+ | |
uv (recommended) |
Or pip install hedgedoc-mcp-server |
API Endpoints Used
This server uses the following HedgeDoc 1.x API endpoints:
| Method | Endpoint | Used by |
|---|---|---|
GET |
/new |
Create a blank note |
POST |
/new |
Create a note (random ID) |
POST |
/new/{alias} |
Create a note (custom alias) |
GET |
/{id}/download |
Read raw markdown |
GET |
/{id}/info |
Read metadata |
GET |
/{id}/revision |
List revisions |
GET |
/{id}/revision/{rev} |
Get specific revision |
GET |
/{id}/publish |
Published URL |
GET |
/{id}/slide |
Slide URL |
GET |
/status |
Instance status |
For more details, see the official API docs.
Instance Configuration
Your HedgeDoc administrator may need to configure these settings:
| Setting | Impact | Docs |
|---|---|---|
CMD_ALLOW_ANONYMOUS=true |
Allows note creation without login | Users and Privileges |
CMD_ALLOW_FREEURL=true |
Enables custom URL aliases | Users and Privileges |
CMD_RATE_LIMIT_NEW_NOTES=20 |
Max new notes per 5 minutes (default: 20) | Web Security |
CMD_DOCUMENT_MAX_LENGTH=100000 |
Max note length in chars (default: 100k) | HedgeDoc basics |
CMD_DISABLE_NOTE_CREATION=false |
If true, no notes can be created | Users and Privileges |
Development
git clone https://github.com/Jyzus/kaymer-hedgedoc-mcp
cd kaymer-hedgedoc-mcp
uv venv && uv pip install -e .
HEDGEDOC_URL="https://hedgedoc.your-instance.com" uv run hedgedoc-mcp-server
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.