bruno-mcp

bruno-mcp

MCP server that executes requests from Bruno API collections via the Bruno CLI tool, enabling API request execution and collection management.

Category
访问服务器

README

Bruno MCP

MCP server for Bruno API collections that executes requests via the Bruno CLI tool.

Prerequisites

1. Install Bruno CLI

The Bruno CLI tool (bru) must be installed and available in your PATH.

  1. Install Bruno CLI using npm
npm install -g @usebruno/cli
  1. Verify installation:
    bru --version
    

2. Install uv (recommended)

uv is the recommended way to install and run bruno-mcp. It includes uvx, which handles package installation and execution automatically.

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

Setup

MCP Configuration (uvx)

Configure the MCP server by adding an entry to your IDE. For Cursor, create or edit the configuration file at ~/.cursor/mcp.json:

{
  "mcpServers": {
    "bruno-mcp": {
      "command": "uvx",
      "args": ["bruno-mcp"],
      "env": {
        "BRUNO_COLLECTION_PATH": "/path/to/your/bruno/collection"
      }
    }
  }
}

The only configuration required is BRUNO_COLLECTION_PATH, which should point to your Bruno collection directory. To load multiple collections, separate paths with : (Unix/Mac) or ; (Windows), e.g. BRUNO_COLLECTION_PATH="/path/to/collection1:/path/to/collection2".

Alternative: Run Server Manually

If you prefer not to use uvx, you can clone the repository and run the server directly:

git clone https://github.com/jackmulligan-ire/bruno-mcp.git
cd bruno-mcp
uv sync

Then configure your MCP client with the full paths:

{
  "mcpServers": {
    "bruno-mcp": {
      "command": "/path/to/bruno-mcp/.venv/bin/python",
      "args": ["-m", "bruno_mcp"],
      "cwd": "/path/to/bruno-mcp",
      "env": {
        "BRUNO_COLLECTION_PATH": "/path/to/your/bruno/collection",
        "PYTHONPATH": "/path/to/bruno-mcp/src"
      }
    }
  }
}

After updating the configuration file, enable the server in your IDE's MCP settings.

Usage Notes

Multiple Collections

When BRUNO_COLLECTION_PATH contains multiple paths (separated by : on Unix/Mac or ; on Windows), the server loads all collections at startup. The first path is the initial active collection. Use the list_collections tool or bruno://collections resource to see available collections, and set_active_collection to switch which collection tools operate on.

Variable Overrides

The run_request_by_id tool accepts a variable_overrides parameter that maps to the Bruno CLI's --env-var flag. This allows you to substitute {{variable}} placeholders in your .bru files at runtime.

Important limitation: --env-var can only override variables that are already defined in a Bruno environment. It cannot introduce new variables, or replace the values of pre-request and post-request variables. If a variable is not defined in any environment, the override will be silently ignored and the placeholder will resolve to an empty string.

To use variable overrides:

  1. Define the variable in a Bruno environment file (even as an empty string):
    vars {
      postId:
    }
    
  2. Pass variable_overrides when calling the tool. For example, if you have a .bru file with the URL https://api.example.com/posts/{{postId}} and an environment called dev that defines postId, you would call:
    • variable_overrides: {"postId": "42"}

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