jq MCP Server
Enables AI models to execute jq expressions against JSON files and return the results as text.
README
jq MCP Server
This project is an MCP (Model Context Protocol) server for AI models that allows executing jq expressions against JSON files.
What it does
The server exposes a tool that runs a jq filter on a JSON file and returns the result as text. It accepts the jq expression and the absolute path to the JSON file, and it handles execution errors.
Requirements
- Node.js
- npm, pnpm (recommended) or any compatible Node.js package manager
Installation
- Install the dependencies with:
npm install
- Or with pnpm:
pnpm install
For security reasons, the pnpm package manager is recommended. You can configure it with the following command before installing any dependencies:
pnpm config set minimum-release-age 1440 --global
This adds a layer of security against supply chain attacks.
If you use pnpm run pnpm approve-builds, select node-jq with <space> key and press <Enter>. Finally press y and press <Enter> to confirm.
- Or install dependencies with your favorite Node.js package manager.
Usage with MCP clients
This server is intended to be started by MCP-compatible clients; you do not need to run node main.js manually. Properly configured clients will start the server when needed. Below are example client configurations (replace /path/to/... with the correct path on your system).
- Continue (VSCode extension) — example
config.yaml:
mcpServers:
- name: jq MCP server
command: npx
args:
- -y
- node
- /path/to/mcp_servers/jq/main.js
env: {}
- Claude (desktop) — example
claude_desktop_config.json:
{
"mcpServers": {
"jq": {
"command": "npx",
"args": ["-y", "node", "/path/to/mcp_servers/jq/main.js"]
}
}
}
- GitHub Copilot (VSCode). Press Ctrl+Shift+P (Windows or Linux) or Cmd+Shift+P (Mac) to open the Command Palette. Execute the MCP: Open User Configuration command. This creates a clean
mcp.jsonin your global user profile directory. Edit themcp.jsonfile and place the following:
{
"servers": {
"jq": {
"command": "npx",
"args": ["-y", "node", "/path/to/mcp_servers/jq/main.js"]
}
}
}
- Generic MCP client (command line):
# A client can launch the server this way if it must be started manually
npx -y node /path/to/mcp_servers/jq/main.js
Tool exposed
The server exposes the following MCP tool:
execute-jq-expression- Parameters:
filter: the jq expression to evaluatefilePath: the absolute path to the JSON file
- Parameters:
Example
If the JSON file contains:
{
"name": "Ada",
"skills": ["jq", "JSON"]
}
You can use a filter such as:
.name
or:
.skills[]
Notes:
- Check the documentation of the MCP client you use for the exact configuration key names; the examples above are common templates.
- When chatting with the AI, make sure to provide the absolute path of JSON file and the jq expression.
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。