Skip to main content
Glama
deenesjakoruzh

MCP Server for Apache Gravitino

Official
by datastrato
GitHub
Python
Apache 2.0
19
OverviewInspectNewEndpointsSchemaRelated ServersReviewsScore
Need Help?View Source CodeReport Issue

Apache Gravitino 的 MCP 服务器（孵化中）

Python 版本

提供 Gravitino API 的 MCP 服务器 - 用于 Apache Gravitino（孵化）服务的 FastMCP 集成。

特征

  • Gravitino API 与 FastMCP 集成

  • 易于使用的元数据管理界面

  • 支持目录/模式/表元数据、标签和用户角色信息

安装

从配置

{ "mcpServers": { "Gravitino": { "command": "uv", "args": [ "--directory", "/Users/user/workspace/mcp-server-gravitino", "run", "--with", "fastmcp", "--with", "httpx", "--with", "mcp-server-gravitino", "python", "-m", "mcp_server_gravitino.server" ], "env": { "GRAVITINO_URI": "http://localhost:8090", "GRAVITINO_USERNAME": "admin", "GRAVITINO_PASSWORD": "admin", "GRAVITINO_METALAKE": "metalake_demo" } } } }

环境变量

授权

mcp-server-gravitino 提供令牌认证和基本认证：

令牌认证

GRAVITINO_URI=http://localhost:8090 GRAVITINO_JWT_TOKEN=<YOUR GRAVITINO JWT TOKEN>

基本身份验证

GRAVITINO_URI=http://localhost:8090 GRAVITINO_USERNAME=<YOUR GRAVITINO USERNAME> GRAVITINO_PASSWORD=<YOUR GRAVITINO PASSWORD>

工具清单

mcp-server-gravitino 不提供 Gravitino 中可用的所有 API。

表格工具

  • get_list_of_catalogs ：获取包含基本信息的目录列表

  • get_list_of_schemas ：获取包含基本信息的模式列表

  • get_list_of_tables ：获取包含基本信息的表的分页列表

  • get_table_by_fqn ：通过完全限定名称获取详细的表信息

  • get_table_columns_by_fqn ：通过完全限定名称获取表列信息

标签工具

  • get_list_of_tags ：获取包含基本信息的标签列表

  • associate_tag_to_table ：将标签关联到表

  • associate_tag_to_column标签到列

  • list_objects_by_tag ：获取与标签关联的对象列表

用户角色工具

  • get_list_of_roles ：获取包含基本信息的角色列表

  • get_list_of_users ：获取用户列表及基本信息

  • grant_role_to_user ：授予用户角色

  • revoke_role_from_user ：撤销用户的角色

每个工具都返回具有相关字段的优化响应，以确保与模型上下文限制兼容，同时提供必要的元数据信息。

执照

该项目是采用 Apache 许可证版本 2.0 许可的开源软件。

This server cannot be installed

-
security - not tested
A
license - permissive license
-
quality - not tested

How are these scores calculated?

remote-capable server

The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.

FastMCP 集成服务器提供对 Apache Gravitino 元数据管理 API 的访问，允许用户通过结构化界面管理目录/模式/表元数据、标签和用户角色信息。

  1. 特征
    1. 安装
      1. 从配置
    2. 环境变量
      1. 授权
    3. 工具清单
      1. 表格工具
      2. 标签工具
      3. 用户角色工具
    4. 执照

      Related MCP Servers

      • MyAIServ MCP Server

        eagurin
        -
        security
        A
        license
        -
        quality
        A high-performance FastAPI server supporting Model Context Protocol (MCP) for seamless integration with Large Language Models, featuring REST, GraphQL, and WebSocket APIs, along with real-time monitoring and vector search capabilities.
        Last updated -
        9
        MIT License

      • IMF Data MCP Server

        c-cf
        A
        security
        A
        license
        A
        quality
        The server integrates with the free IMF data API and provides various features to facilitate data retrieval and analysis. The server is built using the FastMCP framework and offers the following functionalities:
        Last updated -
        10
        3
        Apache 2.0

      • Python MySQL MCP

        hoonzinope
        -
        security
        F
        license
        -
        quality
        A FastMCP-based server that enables interaction with MySQL databases, supporting client-server communication for querying and analyzing MySQL data.
        Last updated -

      • Data Labeling MCP Server

        ag2-mcp-servers
        -
        security
        F
        license
        -
        quality
        An MCP Server that enables interaction with Google's Data Labeling API, allowing users to manage datasets, annotations, and labeling tasks through natural language commands.
        Last updated -

      View all related MCP servers

      New MCP Servers

      MCP directory API

      We provide all the information about MCP servers via our MCP API.

      curl -X GET 'https://glama.ai/api/mcp/v1/servers/datastrato/mcp-server-gravitino'

      If you have feedback or need assistance with the MCP directory API, please join our Discord server