Provides web search capabilities using the Brave Search API, allowing AI agents to perform searches and retrieve results.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP Brave Search Server search the web for 'MCP Protocol Specification'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
đ English | Deutsch
A Model Context Protocol (MCP) server that provides web search capabilities via the Brave Search API.
Node.js (version 18 or higher)
Brave Search API Key (free from Brave)
Related MCP server: Brave Search MCP Server
Install dependencies:
npm installGet a Brave API Key:
Go to Brave Search API
Sign up for a free API key
Copy the API key
Windows (PowerShell):
[System.Environment]::SetEnvironmentVariable('BRAVE_API_KEY', 'your-api-key-here', 'User')Or add it to ~/.config/mcp/mcp.json (see below).
Create or edit the file ~/.config/mcp/mcp.json (on Windows: %USERPROFILE%\.config\mcp\mcp.json):
{
"mcpServers": {
"brave-search": {
"command": "node",
"args": ["C:\\Users\\endre\\WebstormProjects\\MCP-Server\\index.js"],
"env": {
"BRAVE_API_KEY": "your-brave-api-key-here"
}
}
}
}Important: Adjust the path in args to match your actual project path.
If you want to make the server globally available, you can add a bin field to package.json and link it with npm link.
The server provides the following tool:
brave_searchPerforms a web search using the Brave Search API.
Parameters:
query (string, required): The search query
count (number, optional): Number of results (default: 10, maximum: 20)
Example:
Search the web for "MCP Protocol Specification"Free: Generous free tier quota
Privacy: No tracking IDs or user profiling
Modern: Current web indexes
Additional Features: News results are automatically displayed
You can manually test the server:
# First, set the environment variable
$env:BRAVE_API_KEY="your-api-key"
# Start the server
npm startMake sure you have configured the API key as described above.
Check the Copilot plugin logs
Ensure the path in mcp.json is correct
Test if Node.js is available: node --version
Verify that your API key is valid
Make sure you haven't exceeded your quota
Check the Brave Search API rate limits
MIT
Performs a web search using the Brave Search API. Returns relevant websites, snippets, and URLs. Optionally displays news results.
| Name | Required | Description | Default |
|---|---|---|---|
| count | No | Number of results to return (Default: 10, Maximum: 20) | |
| query | Yes | The search query |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description carries the full burden. It states the tool returns websites, snippets, and URLs, and mentions an optional news display. However, it does not disclose rate limits, the external Brave API dependency, or how the optional news results are controlledâwhich is not reflected in the schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two succinct sentences with no wasted words. It front-loads the primary action and includes return types, making it easy to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
As a simple 2-parameter search tool, the description gives the essential purpose and return types but has gaps: 'Optionally displays news results' is ambiguous and not backed by any parameter, and there is no mention of error conditions or result structure. The absence of an output schema makes these omissions more noticeable.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%: both 'query' and 'count' are fully described in the schema. The description adds no parameter-specific details beyond what the schema already provides, so the baseline of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the tool's function: 'Performs a web search using the Brave Search API' and lists the outputs ('relevant websites, snippets, and URLs'). This is a specific verb+resource pair that leaves no ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use when a web search is needed, but there are no explicit when-to-use vs. alternatives because no sibling tools are listed. It lacks exclusions or context about when this tool is preferred over other methods.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Only one tool exists, so there is no possibility of confusing it with another. The tool's purpose is clear and distinct.
The single tool name 'internet_search' follows a clear verb_noun pattern, which is consistent and predictable even though there is only one tool.
The server has only one tool, which feels thin for a typical server, but given the narrow scope of performing web searches, it is borderline acceptable rather than excessive.
The domain is web search, and the single tool fully covers that domain by performing searches and returning results. There are no obvious missing operations for the stated purpose.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Visit https://brave.com/search/api/ for a free API key. Search the web, local businesses, images,âŚ
Provides AI assistants with access to Seltz's powerful Web Search capabilities.
Web search, news, page retrieval, sitemaps, and trending topics through Search1API.
Search Google straight from your AI agent. Web results, images, videos, news, products, scholarly ar
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/enbock/MCP-Server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
