Content
# Tool List
**One-line config, ready to use.** Let AI assistants read your knowledge bases directly.
## Client Compatibility
| Client | Status | Notes |
|:---:|:---:|:---|
| ✅ Codex | **Verified** | — |
| ✅ WorkBuddy | **Verified** | — |
| ⚠️ LobeHub | **May not work** | Known compatibility issues |
> Your client not listed? Feel free to open an issue with your experience!
## Usage
### Method 1: npx (Recommended, No Installation)
Open your AI client config (Claude Desktop / Cursor, etc.), paste this JSON:
```json
{
"mcpServers": {
"cherrystudio-knowledgebase": {
"command": "npx",
"args": ["-y", "cherrystudio-knowledgebase-mcp"],
"env": {
"CHERRYSTUDIO_API_BASE_URL": "http://127.0.0.1:23333",
"CHERRYSTUDIO_API_KEY": "your-api-key-here"
}
}
}
}
```
**Just replace `your-api-key-here` with your real API Key**, save and restart your client.
> Get API Key: Open settings, find and copy the API key.
### Method 2: Clone and Run Locally
```bash
git clone https://github.com/Prism-Future/cherrystudio-knowledgebase-mcp.git
cd cherrystudio-knowledgebase-mcp
npm install
npm run build
```
Then configure with local path:
```json
{
"mcpServers": {
"cherrystudio-knowledgebase": {
"command": "node",
"args": ["path/to/cherrystudio-knowledgebase-mcp/dist/index.js"],
"env": {
"CHERRYSTUDIO_API_BASE_URL": "http://127.0.0.1:23333",
"CHERRYSTUDIO_API_KEY": "your-api-key-here"
}
}
}
}
```
### Method 3: JSON Config File
If you don't want to put the API Key in the client config, create a standalone JSON config file:
```bash
# Create config file
echo '{"cherryStudioApiKey":"your-api-key-here"}' > config.json
```
Then the client config doesn't need `env`:
```json
{
"mcpServers": {
"cherrystudio-knowledgebase": {
"command": "npx",
"args": ["-y", "cherrystudio-knowledgebase-mcp"]
}
}
}
```
Config file can be placed at (priority from high to low):
1. `config.json` in project root
2. `~/.config/cherrystudio-kb-mcp/config.json`
See `config.example.json` for full example.
## Prerequisites
- Node.js 18+
- Cherry Studio（Running）
- Cherry Studio API enabled and you have the API Key
## Features
| Tool | Function |
|---|---|
| `listKnowledgeBases` | List all knowledge bases |
| `searchKnowledgeBases` | Search knowledge bases |
| `getKnowledgeBase` | Get knowledge base details |
| `getMcpServers` | List configured MCP servers |
## FAQ
**Q: Where to get the API Key?**
A: Find and copy the API key in settings.
**Q: What is the API address?**
A: Default is `http://127.0.0.1:23333`, make sure Cherry Studio is running.
**Q: Which clients are supported?**
A: Any MCP-compatible client: Claude Desktop, Cursor, Codex, etc.
## Development
```bash
npm install # Install dependencies
npm run dev # Development mode
npm run build # Build
npm run test # Test
```
## Project Info
- **Author**: [Prism-Future](https://github.com/Prism-Future)
- **License**: MIT
- **Tech Stack**: TypeScript, Node.js, MCP SDK, Zod, Axios
## Links
- [Official Site](https://docs.cherryai.com.cn/)
- [MCP Protocol Docs](https://modelcontextprotocol.io/)
- [Claude Desktop](https://claude.ai/)
- [Issues](https://github.com/Prism-Future/cherrystudio-knowledgebase-mcp/issues)
