SuperDB MCP Server

SuperDB MCP Server

Enables AI assistants to execute SuperSQL queries on data files and SuperDB databases without shell escaping issues. Supports querying, schema inspection, database pool management, and provides LSP features for code completion and documentation.

Category
访问服务器

README

SuperDB MCP Server

An MCP (Model Context Protocol) server for SuperDB that enables AI assistants to better compose SuperSQL queries, optionally backed by an LSP.

About

SuperDB is the successor to zq from Brim Data. As of Jan 2026, it is still in pre-release with limited public documentation, so LLMs have little knowledge of its syntax. This MCP server provides the context AI assistants need to write correct queries.

Installation

Add to your Claude Code settings (~/.claude/settings.json) or project .mcp.json:

{
  "mcpServers": {
    "superdb": {
      "command": "npx",
      "args": ["-y", "superdb-mcp"]
    }
  }
}

Or install globally:

npm install -g superdb-mcp
{
  "mcpServers": {
    "superdb": {
      "command": "superdb-mcp"
    }
  }
}

From Source

git clone https://github.com/chrismo/superdb-mcp.git
cd superdb-mcp
npm install
npm run build
{
  "mcpServers": {
    "superdb": {
      "command": "node",
      "args": ["/path/to/superdb-mcp/dist/index.js"]
    }
  }
}

Tools

Query Tools

super_query

Execute a SuperSQL query on data files.

query: string         # Required: The SuperSQL query
files?: string[]      # File paths to query
data?: string         # Inline data (alternative to files)
format?: string       # Output: json (default), sup, csv, table
inputFormat?: string  # Force input format

super_validate

Validate query syntax without executing.

query: string         # The query to validate

super_schema

Inspect types in a data file by sampling records.

file: string          # Path to data file
sample?: number       # Records to sample (default: 5)

Database Tools

super_db_list

List all pools in a SuperDB database.

lake?: string         # Lake path (default: ~/.super)

super_db_query

Query data from a database pool.

query: string         # The SuperSQL query
pool?: string         # Pool name
lake?: string         # Lake path
format?: string       # Output format

super_db_load

Load data into a pool.

pool: string          # Pool name
files?: string[]      # Files to load
data?: string         # Inline data
lake?: string         # Lake path

super_db_create_pool

Create a new pool.

name: string          # Pool name
orderBy?: string      # Sort key
lake?: string         # Lake path

Info Tools

super_info

Get SuperDB version info, environment configuration, LSP availability, and installation instructions.

compare_to?: string   # Optional path to another super binary to compare

super_lsp_status

Check if the SuperDB LSP is installed and get installation instructions if not.

# No parameters - returns availability status and setup instructions

super_help

Get SuperDB documentation (bundled expert guide or migration docs).

topic: string         # "expert", "upgrade", "upgrade-guide", or "migration"

super_test_compat

Test a query against multiple SuperDB versions to detect breaking changes.

query: string         # The query to test
versions: string[]    # Paths to different super binaries

LSP Tools

Require SUPERDB_LSP_PATH environment variable to be set.

super_complete

Get code completions for a SuperSQL query at a cursor position.

query: string         # The query text
line: number          # Line number (0-based)
character: number     # Character offset (0-based)

super_docs

Get documentation for a symbol at a position in a query.

query: string         # The query text
line: number          # Line number (0-based)
character: number     # Character offset (0-based)

Example Usage

With the MCP server configured, Claude can execute queries like:

super_query({
  query: "where status == 'active' | aggregate count() by category",
  files: ["data.json"]
})

No shell escaping needed - the query string is passed directly.

Requirements

  • Node.js 18+
  • super binary in PATH:

Versioning

SuperDB is in active pre-release development without official versioned releases. The only official builds are via Homebrew cask, identified by git SHA rather than version numbers.

To manage this, this repo uses pseudo-versions in the format 0.YMMDD (last digit of year + month + day). For example, 0.51231 represents a build from 2025-12-31. See asdf-superdb for more details on the versioning scheme.

This MCP server versions to match the bundled documentation:

  • 0.51231.0 - initial release with docs for SuperDB pseudo-version 0.51231
  • 0.51231.1, .2, etc. - MCP-only patches (no doc changes)

The super_info tool reports both your runtime version and the bundled docs version, warning if they differ.

License

BSD 3-Clause License

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选