About dolphindb-mcp-server
dolphindb-mcp-server exposes DolphinDB operations to MCP clients and LLM toolchains. Its tools list databases and tables, inspect table disk usage, and execute DolphinDB scripts.
Key features
- 01List databases
- 02List tables in a database
- 03Query table disk usage
- 04Run DolphinDB scripts
Use cases
- 01Browse DolphinDB databases and tables
- 02Check a table’s disk usage
- 03Run DolphinDB queries through a toolchain
MCP support
When started, it exposes tools for listing databases and tables, checking disk usage, and executing scripts to MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project README🧱 安装方式
✅ 方法一:使用 uvx(推荐)
通过 uvx 安装并运行:
uvx install dolphindb-mcp-server
安装完成后,直接运行:
uvx dolphindb-mcp-server
📌 注意:
uvx安装方式需要通过uv.pack构建并上传到 Universe。如果你尚未上传,请参考uv文档进行打包与发布。
✅ 方法二:从 PyPI 安装
pip install dolphindb-mcp-server
安装后运行:
dolphindb-mcp-server
✅ 方法三:本地构建 & 安装
git clone https://github.com/your-org/dolphindb-mcp-server.git
cd dolphindb-mcp-server
# 创建并激活虚拟环境
python -m venv .venv
source .venv/bin/activate
# 构建并安装
pip install build
python -m build
pip install dist/*.whl
安装后运行:
dolphindb-mcp-server
🧪 测试运行
运行后你可以直接使用工具,例如:
dolphindb-mcp-server
或(如果是 uvx 安装):
uvx dolphindb-mcp-server
好的,这是转换后的 Markdown 版本:
好的,这是转换后的 Markdown 版本:
🚀 使用方法
-
配置环境变量(可选)
你可以通过
.env文件或系统环境变量配置 DolphinDB 的连接信息:DDB_HOST=127.0.0.1 DDB_PORT=8848 DDB_USER=admin DDB_PASSWD=123456也可以不设置,系统将使用默认值。
-
启动服务
dolphindb-mcp-server该命令会启动 MCP 插件服务,供外部调用。
-
FastMCP Agent 使用示例
启动后,你的工具将通过 FastMCP 对外暴露以下函数接口:
list_dbs()list_tbs(dbName: str)query_table_diskusage(database: str, tableName: str)query_dolphindb(script: str)
可通过 MCP 前端界面或对接 LLM 工具链来进行访问。
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.