Skip to main content
Glama
kwp-lab

Brave Search With Proxy

brave_web_search

Search the web for general queries, news, articles, and online content using Brave Search API with pagination and filtering options.

Instructions

Performs a web search using the Brave Search API, ideal for general queries, news, articles, and online content. Use this for broad information gathering, recent events, or when you need diverse web sources. Supports pagination, content filtering, and freshness controls. Maximum 20 results per request, with offset for pagination.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesSearch query (max 400 chars, 50 words)
countNoNumber of results (1-20, default 10)
offsetNoPagination offset (max 9, default 0)

Implementation Reference

  • Core implementation of the brave_web_search tool: performs API call to Brave Search, handles response, extracts and formats web search results.
    async function performWebSearch(query: string, count: number = 10, offset: number = 0) {
      checkRateLimit();
      const url = new URL('https://api.search.brave.com/res/v1/web/search');
      url.searchParams.set('q', query);
      url.searchParams.set('count', Math.min(count, 20).toString()); // API limit
      url.searchParams.set('offset', offset.toString());
    
      const response = await fetch(url, {
        headers: {
          'Accept': 'application/json',
          'Accept-Encoding': 'gzip',
          'X-Subscription-Token': BRAVE_API_KEY
        }
      });
    
      if (!response.ok) {
        throw new Error(`Brave API error: ${response.status} ${response.statusText}\n${await response.text()}`);
      }
    
      const data = await response.json() as BraveWeb;
    
      // Extract just web results
      const results = (data.web?.results || []).map(result => ({
        title: result.title || '',
        description: result.description || '',
        url: result.url || ''
      }));
    
      return results.map(r =>
        `Title: ${r.title}\nDescription: ${r.description}\nURL: ${r.url}`
      ).join('\n\n');
    }
  • MCP CallTool handler case for brave_web_search: validates arguments and calls performWebSearch.
    case "brave_web_search": {
      if (!isBraveWebSearchArgs(args)) {
        throw new Error("Invalid arguments for brave_web_search");
      }
      const { query, count = 10 } = args;
      const results = await performWebSearch(query, count);
      return {
        content: [{ type: "text", text: results }],
        isError: false,
      };
    }
  • Tool schema definition for brave_web_search, including name, description, and JSON schema for inputs.
    const WEB_SEARCH_TOOL: Tool = {
      name: "brave_web_search",
      description:
        "Performs a web search using the Brave Search API, ideal for general queries, news, articles, and online content. " +
        "Use this for broad information gathering, recent events, or when you need diverse web sources. " +
        "Supports pagination, content filtering, and freshness controls. " +
        "Maximum 20 results per request, with offset for pagination. ",
      inputSchema: {
        type: "object",
        properties: {
          query: {
            type: "string",
            description: "Search query (max 400 chars, 50 words)"
          },
          count: {
            type: "number",
            description: "Number of results (1-20, default 10)",
            default: 10
          },
          offset: {
            type: "number",
            description: "Pagination offset (max 9, default 0)",
            default: 0
          },
        },
        required: ["query"],
      },
    };
  • Type guard function for validating brave_web_search arguments.
    function isBraveWebSearchArgs(args: unknown): args is { query: string; count?: number } {
      return (
        typeof args === "object" &&
        args !== null &&
        "query" in args &&
        typeof (args as { query: string }).query === "string"
      );
    }
  • index.ts:318-320 (registration)
    Registers brave_web_search (via WEB_SEARCH_TOOL) in the MCP listTools handler.
    server.setRequestHandler(ListToolsRequestSchema, async () => ({
      tools: [WEB_SEARCH_TOOL, LOCAL_SEARCH_TOOL],
    }));
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively adds context beyond the input schema by stating 'Maximum 20 results per request, with offset for pagination', which clarifies limits and pagination behavior. It also mentions 'Supports pagination, content filtering, and freshness controls', providing useful operational details. However, it lacks information on rate limits, authentication needs, or error handling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized and front-loaded, with the first sentence stating the core purpose. Each subsequent sentence adds specific value: ideal use cases, features like pagination and filtering, and operational limits. There is no wasted text, and the structure efficiently conveys essential information in a compact form.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (3 parameters, no output schema, no annotations), the description is largely complete. It covers purpose, usage guidelines, behavioral traits, and operational limits. However, without an output schema, it does not explain return values or result format, and it lacks details on error handling or authentication, leaving some gaps for a tool with no annotations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, so the schema already documents all parameters (query, count, offset) with details like max chars, ranges, and defaults. The description adds marginal value by implying usage of these parameters for 'pagination' and 'freshness controls', but does not provide additional syntax or format details beyond what the schema provides, meeting the baseline for high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool 'performs a web search using the Brave Search API', specifying both the action ('performs a web search') and resource ('Brave Search API'). It distinguishes from the sibling tool 'brave_local_search' by emphasizing 'general queries, news, articles, and online content' for broad information gathering, which implies a contrast with local search functionality.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use this tool: 'ideal for general queries, news, articles, and online content' and 'for broad information gathering, recent events, or when you need diverse web sources'. However, it does not explicitly state when not to use it or name alternatives beyond the implied sibling tool, missing explicit exclusions or comparisons.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/kwp-lab/mcp-brave-search'

If you have feedback or need assistance with the MCP directory API, please join our Discord server