Skip to main content
Glama
Sign In
RootData MCP Server

RootData MCP Server

by jincai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

RootData MCP Server

Introduction

这是一个基于 Model Context Protocol (MCP) 的服务器，用于集成 RootData API，提供加密货币和区块链项目的数据查询功能。

它允许 Claude 和其他 AI 助手通过 MCP 接口直接获取项目信息、机构详情和搜索结果。

Related MCP server: Flow MCP Server

Available Tools

本服务器提供以下 MCP 工具：

  • search: 根据关键词搜索项目/VC/人物的简要信息

  • get_project: 根据项目 ID 获取项目的详细信息

  • get_organization: 根据机构 ID 获取风投机构的详细信息

Setup

Prerequisites

  • Python 3.10 或更高版本

  • uv 包管理器（推荐）

Installation

  1. 克隆此仓库：

git clone https://github.com/jincai/rootdata-mcp-server
cd rootdata-mcp-server

  1. 如果你还没有安装 uv，可以安装它：

# macOS/Linux
curl -LsSf https://astral.sh/uv/install.sh | sh

# Windows
curl -LsSf https://astral.sh/uv/install.ps1 | powershell

  1. 安装依赖：

# 创建虚拟环境并激活
uv venv
source .venv/bin/activate  # Windows 上: .venv\Scripts\activate

# 安装依赖
uv add "mcp[cli]" httpx python-dotenv

  1. 设置环境变量：

# 创建 .env 文件存储 API 密钥
cp .env.example .env

# 在 .env 文件中设置 API 密钥
ROOTDATA_API_KEY=your-rootdata-api-key

  1. 运行服务器：

uv run server.py

Connecting to Claude Desktop

  1. 安装 Claude Desktop（如果你还没有安装）

  2. 创建或编辑 Claude Desktop 配置文件：

# macOS
mkdir -p ~/Library/Application\ Support/Claude/
nano ~/Library/Application\ Support/Claude/claude_desktop_config.json

  1. 添加以下配置：

{
  "mcpServers": {
    "rootdata": {
      "command": "/path/to/uv",
      "args": [
        "--directory",
        "/absolute/path/to/rootdata-mcp-server",
        "run",
        "server.py"
      ]
    }
  }
}

将 /path/to/uv 替换为 which uv 的结果，将 /absolute/path/to/rootdata-mcp-server 替换为此项目的绝对路径。

  1. 重启 Claude Desktop

  2. 现在你应该能在 Claude Desktop 的工具菜单（锤子图标）中看到 RootData 工具

  3. 尝试向 Claude 提问，例如：

    • "搜索以太坊相关的项目"

    • "获取项目 ID 为 12 的详细信息"

    • "查询机构 ID 为 219 的风投机构信息"

License

MIT

Available Tools

3 tools
get_organizationC

Obtain VC details according to VC ID.

Args:
    org_id: Organization ID
    include_team: Whether to include team member information, default is false.
    include_investments: Whether it includes investment project information, default is false.

Inputs: org_id (required), include_team, include_investments. Returns: result

get_projectB

Obtain project details according to the project ID.

Args:
    project_id: The unique identifier for the project.
    include_team: Whether to include team member information, default is false.
    include_investors: Whether to include investor information, default is false.

Inputs: project_id (required), include_team, include_investors. Returns: result

searchB

Search for Project/VC/People brief information according to keywords.

Args:
    query: Search keywords, which can be project/institution names, tokens, or other related terms.

Inputs: query (required). Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    B3.3/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: get_organization retrieves VC details, get_project retrieves project details, and search performs keyword-based searches across multiple entity types. There is no overlap in functionality, and an agent can easily differentiate between them based on their specific objectives.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern: get_organization, get_project, and search. The naming is uniform, using snake_case throughout, with clear and predictable verbs that accurately describe each tool's action.

    Tool Count3/5

    With only 3 tools, the server feels thin for a data-focused domain like VC and project details. While the tools cover basic retrieval and search, the scope suggests that additional operations (e.g., listing, filtering, or updating) might be expected, making the count borderline for comprehensive coverage.

    Completeness3/5

    The server provides read operations (get and search) but lacks create, update, or delete tools, which are typical for data management. This creates notable gaps in lifecycle coverage, as agents cannot modify or add data, limiting the server to query-only functionality.

    Resources

    Related MCP Connectors

    Related MCP Servers

    • MCP Expert Server

      crazyrabbitLTC
      A
      license
      Not graded
      quality
      D
      maintenance
      A Model Context Protocol server utilizing Claude AI for generating intelligent queries and offering documentation assistance based on API documentation analysis.
      15 npm
      3
      MIT

    • Flow MCP Server

      lmcmz
      A
      license
      Not graded
      quality
      D
      maintenance
      A Model Context Protocol server that enables AI assistants to access Flow blockchain data and perform operations such as checking balances, resolving domains, executing scripts, and submitting transactions.
      1
      MIT
    • Blockscout MCP Server

      Blockscout MCP Serverofficial

      blockscout
      F
      license
      A
      quality
      C
      maintenance
      A server that exposes blockchain data (balances, tokens, NFTs, contract metadata) via the Model Context Protocol, enabling AI agents and tools to access and analyze blockchain information contextually.
      18
      46
      -

    Appeared in Searches