MCP.so
Sign In

mcp2brave

@mcp2everything

Repository

About mcp2brave

一个MCP服务器，基于Brave API让你的Claude Cline以及Langchain实现网络搜索功能。An MCP server that use Brave API allows your Claude Cline and Langchain to implement network search functions.

#mcp2brave#mcp-server#brave-api

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp2brave": {
      "command": "uv",
      "args": [
        "venv"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is mcp2brave?

mcp2brave is an MCP (Model Context Protocol) server that uses the Brave API to perform web searches. It is designed for developers who want to integrate Brave search capabilities into MCP‑compatible AI tools such as Claude, Cline, or Continue.

How to use mcp2brave?

Install the server using UV and set your Brave API key in the .env file. To use it as a Claude extension, run fastmcp install mcp2brave.py. For development or manual configuration (e.g. with Cline or Continue), add the provided JSON block to your MCP server configuration file. Two tools are exposed: search_web(query) and search_web_info(query).

Key features of mcp2brave

  • Integrates Brave API via the MCP protocol
  • Provides two search tools: search_web and search_web_info
  • Easy installation as a Claude extension using fastmcp
  • Supports development mode with the MCP inspector (localhost:5173)
  • Requires only Python 3.11+, UV, and a Brave API key
  • Can be manually integrated with Cline, Continue, or Claude

Use cases of mcp2brave

  • Enable Claude to perform real‑time web searches through Brave
  • Add web search capability to any MCP‑compatible AI assistant
  • Test and debug search tools locally with the MCP inspector
  • Customize search behaviour using a Chinese‑described tool variant

FAQ from mcp2brave

What are the system requirements?

Python 3.11+, the UV package manager, and a valid Brave API key.

How do I obtain a Brave API key?

The README does not specify how to get one; it must be set as the Brave_API_KEY environment variable.

What tools does mcp2brave provide?

Two tools: search_web(query) – standard Brave search – and search_web_info(query), which is the same but with a Chinese description.

Can I use mcp2brave without Claude?

Yes. It can be manually added to any MCP client (e.g., Cline, Continue) by inserting the JSON configuration into the client’s MCP server settings file.

Are there any known limitations?

The virtual environment must be active before running commands. If encoding issues arise, ensure the system uses UTF‑8 encoding.

Frequently asked questions

What are the system requirements?

Python 3.11+, the UV package manager, and a valid Brave API key.

How do I obtain a Brave API key?

The README does not specify how to get one; it must be set as the `Brave_API_KEY` environment variable.

What tools does mcp2brave provide?

Two tools: `search_web(query)` – standard Brave search – and `search_web_info(query)`, which is the same but with a Chinese description.

Can I use mcp2brave without Claude?

Yes. It can be manually added to any MCP client (e.g., Cline, Continue) by inserting the JSON configuration into the client’s MCP server settings file.

Are there any known limitations?

The virtual environment must be active before running commands. If encoding issues arise, ensure the system uses UTF‑8 encoding.

Comments

Basic information

Category

AI & Agents

Transports

stdio

Author

mcp2everything

More AI & Agents MCP servers

1MCP - One MCP Server for All

1mcp-app

A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.

468

Shell and Coding agent for Claude and other mcp clients

rusiaaman

Shell and coding agent on mcp clients

666

Open Multi-Agent Canvas

CopilotKit

The open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research

507

欢迎来到 智言平台

Shy2593666979

AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。

797

Model Context Protocol for Unreal Engine

chongdashu

Enable AI assistant clients like Cursor, Windsurf and Claude Desktop to control Unreal Engine through natural language using the Model Context Protocol (MCP).

2.0K