Skip to main content
Glama
Decodo

Decodo MCP Server

google_search

Read-only

Scrape Google Search results and automatically parse them. Customize by geolocation, locale, and JavaScript rendering.

Instructions

Scrape Google Search results with automatic parsing

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesSearch query
geoNoGeolocation of the desired request, expressed as a country name
localeNoLocale of the desired request
jsRenderNoShould the request be opened in a headless browser, false by default

Implementation Reference

  • The handler that executes the Google Search tool logic: builds params with target='google_search', calls sapiClient.scrape(), transforms the response by removing high-char-count fields, and returns text content.
    async (scrapingParams: ScrapingMCPParams, extra: ProgressExtra) => {
      const params = {
        ...scrapingParams,
        target: SCRAPER_API_TARGETS.GOOGLE_SEARCH,
        parse: true,
      } satisfies ScraperAPIParams;
    
      const { data } = await sapiClient.scrape<object>({ auth, scrapingParams: params, extra });
    
      const { data: text } = this.transformResponse({ data });
    
      return {
        content: [
          {
            type: 'text',
            text,
          },
        ],
      };
    }
  • Input schema for the google_search tool: requires 'query' (string), and optional 'geo', 'locale', 'jsRender' using shared Zod types.
    inputSchema: {
      query: z.string().describe('Search query'),
      geo: zodGeo,
      locale: zodLocale,
      jsRender: zodJsRender,
    },
  • Registration of the google_search tool with the MCP server, including description, annotations (readOnlyHint, openWorldHint), input schema, and the handler callback.
    register = ({ server, sapiClient, auth }: ToolRegistrationArgs) => {
      server.registerTool(
        'google_search',
        {
          description: 'Scrape Google Search results with automatic parsing',
          inputSchema: {
            query: z.string().describe('Search query'),
            geo: zodGeo,
            locale: zodLocale,
            jsRender: zodJsRender,
          },
          annotations: {
            readOnlyHint: true,
            openWorldHint: true,
          },
        },
        async (scrapingParams: ScrapingMCPParams, extra: ProgressExtra) => {
          const params = {
            ...scrapingParams,
            target: SCRAPER_API_TARGETS.GOOGLE_SEARCH,
            parse: true,
          } satisfies ScraperAPIParams;
    
          const { data } = await sapiClient.scrape<object>({ auth, scrapingParams: params, extra });
    
          const { data: text } = this.transformResponse({ data });
    
          return {
            content: [
              {
                type: 'text',
                text,
              },
            ],
          };
        }
      );
    };
  • Helper method that strips high-character-count fields (images, image_data, factoids, etc.) from the response to reduce payload size, then stringifies the result.
    transformResponse = ({ data }: { data: object }) => {
      for (const fieldToRemove of GoogleSearchTool.FIELDS_WITH_HIGH_CHAR_COUNT) {
        data = removeKeyFromNestedObject({ obj: data, keyToRemove: fieldToRemove });
      }
    
      return { data: JSON.stringify(data) };
    };
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the description adds limited value beyond stating 'automatic parsing'. It does not disclose rate limits, result structure, or whether it returns raw HTML vs. structured data.

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

Conciseness4/5

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

One efficient sentence with no wasted words, though it could be slightly expanded to include usage guidance without losing conciseness.

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

Completeness2/5

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

Lacks detail on output format (no output schema) and does not explain what 'scrape' and 'automatic parsing' entail. For a tool with multiple sibling search tools, agents need more context to judge appropriateness.

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?

Schema description coverage is 100% for all 4 parameters, so the description does not add additional meaning beyond what the schema already provides.

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?

Clearly states it scrapes Google Search results with automatic parsing, distinguishing it from sibling tools like bing_search through the explicit mention of Google.

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

Usage Guidelines2/5

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

No guidance on when to use this tool versus alternatives such as bing_search, google_ads, or google_lens. The description does not provide context or exclusions.

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

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/Decodo/mcp-server'

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