dolphindb-mcp-server

## 🧱 Installation [](https://archestra.ai/mcp-catalog/tradercjz__dolphindb-mcp-server) ### ✅ Method 1: Using `uvx` (Recommended) Install and run via `uvx`: ```bash uvx install dolphindb-mcp-server ``` After installation, run directly: ```bash uvx dolphindb-mcp-server ``` > 📌 **Note**: The `uvx` installation method requires building and uploading to Universe via `uv.pack`. If you have not uploaded yet, please refer to the `uv` documentation for packaging and publishing. ### ✅ Method 2: Install from PyPI ```bash pip install dolphindb-mcp-server ``` Run after installation: ```bash dolphindb-mcp-server ``` ### ✅ Method 3: Local Build & Installation ```bash git clone https://github.com/your-org/dolphindb-mcp-server.git cd dolphindb-mcp-server # Create and activate virtual environment python -m venv .venv source .venv/bin/activate # Build and install pip install build python -m build pip install dist/*.whl ``` Run after installation: ```bash dolphindb-mcp-server ``` ## 🧪 Test Run After running, you can directly use the tool, for example: ```bash dolphindb-mcp-server ``` Or (if installed via `uvx`): ```bash uvx dolphindb-mcp-server ``` --- ## 🚀 Usage 1. **Configure Environment Variables (Optional)** You can configure DolphinDB connection information through the `.env` file or system environment variables: ```env DDB_HOST=127.0.0.1 DDB_PORT=8848 DDB_USER=admin DDB_PASSWD=123456 ``` If not set, the system will use the default values. 2. **Start the Service** ```bash dolphindb-mcp-server ``` This command starts the MCP plugin service for external calls. 3. **FastMCP Agent Usage Example** After starting, your tool will expose the following function interfaces through FastMCP: * `list_dbs()` * `list_tbs(dbName: str)` * `query_table_diskusage(database: str, tableName: str)` * `query_dolphindb(script: str)` It can be accessed through the MCP front-end interface or by connecting to the LLM toolchain.