growi
A Model Context Protocol (MCP) server that connects AI models to GROWI wiki content. Enables LLMs to search and retrieve information from your organization's knowledge base for accurate, context-aware responses.
claude mcp add --transport stdio growilabs-growi-mcp-server npx @growi/mcp-server \ --env GROWI_APP_NAME_1="main" \ --env GROWI_BASE_URL_1="https://your-growi-instance.com" \ --env GROWI_API_TOKEN_1="your_growi_api_token"
How to use
This MCP server connects AI models to your GROWI wiki content, enabling the model to search pages, retrieve full page data, manage pages and tags, handle comments, and work with share links and revisions across one or more GROWI apps. By configuring separate app blocks, you can connect to multiple GROWI instances and route prompts to the appropriate data source. Once running, you can invoke the available tools (such as searchPages, getPage, createPage, updatePage, getTagList, createShareLink, and more) through your MCP consumer to perform context-aware queries against your GROWI knowledge base. The server exposes a catalog of capabilities that allow LLMs to interact with content, metadata, and collaboration features in your GROWI deployments.
How to install
Prerequisites:
- Node.js 18 or higher
- pnpm (recommended)
- A GROWI instance (for development and testing)
-
Clone the MCP server repository (or install via npm if published):
- git clone https://github.com/growilabs/growi-mcp-server.git
- cd growi-mcp-server
-
Install dependencies:
- pnpm install
-
Set up environment variables:
- Copy the example env file and edit it with your GROWI connection details
cp .env.example .env.local
Edit .env.local to enter GROWI connection information
- Copy the example env file and edit it with your GROWI connection details
cp .env.example .env.local
-
Build (if you plan to run the built output):
- pnpm build
-
Run the MCP server using the recommended approach (npx for development with the package):
- pnpm dev:cli # Test with MCP CLI
- pnpm dev:inspect # Develop with MCP Inspector
If you prefer running from a built output, ensure you point to the built index.js and use node to start the server as shown in the configuration examples.
Additional notes
Notes and tips:
- The MCP server supports multiple GROWI app configurations. Use numbered environment variables like GROWI_APP_NAME_1, GROWI_BASE_URL_1, GROWI_API_TOKEN_1 for the first app, and increment the suffix for additional apps (2, 3, ...).
- If GROWI_DEFAULT_APP_NAME is omitted, the first configured app becomes the default.
- Absolute paths to the built output must be used when running a prebuilt server (see Node-based configuration examples).
- Ensure your GROWI instance is reachable from the environment where the MCP server runs and that the API token has the necessary permissions.
- When testing across environments (production, staging, development), provide distinct GROWI_APP_NAME_N values and corresponding tokens to avoid conflicts.
- If you encounter connectivity issues, verify network settings and that the GROWI_BASE_URL is correct and publicly reachable if needed.
Related MCP Servers
iterm
A Model Context Protocol server that executes commands in the current iTerm session - useful for REPL and CLI assistance
mcp
Octopus Deploy Official MCP Server
furi
CLI & API for MCP management
editor
MCP Server for Phaser Editor
DoorDash
MCP server from JordanDalton/DoorDash-MCP-Server
mcp
MCP сервер для автоматического создания и развертывания приложений в Timeweb Cloud