mcpField
M
mcp-server-brave-search

mcp-server-brave-search

Local
github.com/zed-extensionsSearch28Updated 19w ago

About mcp-server-brave-search

mcp-server-brave-search is a Zed extension that wraps the official Brave Search MCP server. It suits Zed users who want Brave search from within the editor and requires a Brave Search API key.

Key features

  1. 01Wraps the official Brave Search MCP server package
  2. 02Configured through Zed context_servers settings
  3. 03Uses a brave_api_key setting for authentication

Use cases

  1. 01Giving the AI assistant in Zed web search access
  2. 02Looking up current documentation during coding sessions

MCP support

The extension registers the Brave Search MCP server in Zed, so Zed's AI features can call its search tools.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

mcp-server-brave-search

Zed extension that wraps the official Brave Search MCP server: @brave/brave-search-mcp-server. See the upstream project for features and usage details: brave/brave-search-mcp-server.

Configuration

This MCP server requires an API key.

  1. Sign up for a Brave Search API account
  2. Choose a plan (Free tier available with 1,000 queries/month)
  3. Generate your API key from the developer dashboard

In your Zed settings:

{
    "context_servers": {
        "mcp-server-brave-search": {
          "settings": {
              "brave_api_key": "YOUR_API_KEY"
          }
        }
    }
}

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.