Skip to main content
Glama
ravinwebsurgeon

DataForSEO MCP Server

dataforseo_labs_google_keyword_suggestions

Generate long-tail keyword suggestions based on seed keywords, providing search volume, CPC, competition data, and trends for SEO research and content planning.

Instructions

The Keyword Suggestions provides search queries that include the specified seed keyword.

The algorithm is based on the full-text search for the specified keyword and therefore returns only those search terms that contain the keyword you set in the POST array with additional words before, after, or within the specified key phrase. Returned keyword suggestions can contain the words from the specified key phrase in a sequence different from the one you specify.

As a result, you will get a list of long-tail keywords with each keyword in the list matching the specified search term.

Along with each suggested keyword, you will get its search volume rate for the last month, search volume trend for the previous 12 months, as well as current cost-per-click and competition values. Moreover, this endpoint supplies minimum, maximum and average values of daily impressions, clicks and CPC for each result.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keywordYestarget keyword
location_nameNofull name of the location required field only in format "Country" (not "City" or "Region") example: 'United Kingdom', 'United States', 'Canada'United States
language_codeNolanguage code required field example: enen
limitNoMaximum number of keywords to return
offsetNooffset in the results array of returned keywords optional field default value: 0 if you specify the 10 value, the first ten keywords in the results array will be omitted and the data will be provided for the successive keywords
filtersNoyou can add several filters at once (8 filters maximum) you should set a logical operator and, or between the conditions the following operators are supported: regex, not_regex, <, <=, >, >=, =, <>, in, not_in, match, not_match, ilike, not_ilike, like, not_like you can use the % operator with like and not_like, as well as ilike and not_ilike to match any string of zero or more characters merge operator must be a string and connect two other arrays, availible values: or, and. example: ["keyword_info.search_volume",">",0] [["keyword_info.search_volume","in",[0,1000]], "and", ["keyword_info.competition_level","=","LOW"]][["keyword_info.search_volume",">",100], "and", [["keyword_info.cpc","<",0.5], "or", ["keyword_info.high_top_of_page_bid","<=",0.5]]]
order_byNoresults sorting rules optional field you can use the same values as in the filters array to sort the results possible sorting types: asc – results will be sorted in the ascending order desc – results will be sorted in the descending order a comma is used as a separator example: ["keyword_info.competition,desc"] default rule: ["keyword_info.search_volume,desc"] note that you can set no more than three sorting rules in a single request you should use a comma to separate several sorting rules example: ["keyword_info.search_volume,desc","keyword_info.cpc,desc"]
include_clickstream_dataNoInclude or exclude data from clickstream-based metrics in the result

Implementation Reference

  • The handle() method that implements the tool's core logic: constructs and sends a POST request to DataForSEO Labs API for Google keyword suggestions, handles response and errors.
    async handle(params: any): Promise<any> {
      try {
        const response = await this.client.makeRequest('/v3/dataforseo_labs/google/keyword_suggestions/live', 'POST', [{
          keyword: params.keyword,
          location_name: params.location_name,
          language_code: params.language_code,
          limit: params.limit,
          offset: params.offset,
          filters: this.formatFilters(params.filters),
          order_by: this.formatOrderBy(params.order_by),
          include_clickstream_data: params.include_clickstream_data
        }]);
        return this.validateAndFormatResponse(response);
      } catch (error) {
        return this.formatErrorResponse(error);
      }
    }
  • Input schema defined using Zod in getParams(), including parameters like keyword, location_name, language_code, filters, etc.
      getParams(): z.ZodRawShape {
        return {
          keyword: z.string().describe(`target keyword`),
          location_name: z.string().default("United States").describe(`full name of the location
    required field
    in format "Country"
    example:
    United Kingdom`),
          language_code: z.string().default("en").describe(
            `language code
            required field
            example:
            en`),
          limit: z.number().min(1).max(1000).default(10).optional().describe("Maximum number of keywords to return"),
          offset: z.number().min(0).optional().describe(
            `offset in the results array of returned keywords
            optional field
            default value: 0
            if you specify the 10 value, the first ten keywords in the results array will be omitted and the data will be provided for the successive keywords`
          ),
          filters: z.array(
            z.union([
              z.array(z.union([z.string(), z.number(), z.boolean()])).length(3),
              z.enum(["and", "or"])
            ])
          ).max(8).optional().describe(
            `you can add several filters at once (8 filters maximum)
            you should set a logical operator and, or between the conditions
            the following operators are supported:
            regex, not_regex, <, <=, >, >=, =, <>, in, not_in, match, not_match, ilike, not_ilike, like, not_like
            you can use the % operator with like and not_like, as well as ilike and not_ilike to match any string of zero or more characters
            merge operator must be a string and connect two other arrays, availible values: or, and.
            example:
          ["keyword_info.search_volume",">",0]
    [["keyword_info.search_volume","in",[0,1000]],
    "and",
    ["keyword_info.competition_level","=","LOW"]][["keyword_info.search_volume",">",100],
    "and",
    [["keyword_info.cpc","<",0.5],
    "or",
    ["keyword_info.high_top_of_page_bid","<=",0.5]]]`
          ),
          order_by: z.array(z.string()).optional().describe(
            `results sorting rules
    optional field
    you can use the same values as in the filters array to sort the results
    possible sorting types:
    asc – results will be sorted in the ascending order
    desc – results will be sorted in the descending order
    a comma is used as a separator
    example:
    ["keyword_info.competition,desc"]
    default rule:
    ["keyword_info.search_volume,desc"]
    note that you can set no more than three sorting rules in a single request
    you should use a comma to separate several sorting rules
    example:
    ["keyword_info.search_volume,desc","keyword_info.cpc,desc"]`
          ),
          include_clickstream_data: z.boolean().optional().default(false).describe(
            `Include or exclude data from clickstream-based metrics in the result`)
        };
      }
  • The tool is instantiated as new GoogleKeywordsSuggestionsTool and registered in the getTools() method of DataForSEOLabsApi module, mapping its name to description, params, and handler.
    getTools(): Record<string, ToolDefinition> {
      const tools = [
        new GoogleRankedKeywordsTool(this.dataForSEOClient),
        new GoogleDomainCompetitorsTool(this.dataForSEOClient),
        new GoogleDomainRankOverviewTool(this.dataForSEOClient),
        new GoogleKeywordsIdeasTool(this.dataForSEOClient),
        new GoogleRelatedKeywordsTool(this.dataForSEOClient),
        new GoogleKeywordsSuggestionsTool(this.dataForSEOClient),
        new GoogleHistoricalSERP(this.dataForSEOClient),
        new GoogleSERPCompetitorsTool(this.dataForSEOClient),
        new GoogleBulkKeywordDifficultyTool(this.dataForSEOClient),
        new GoogleSubdomainsTool(this.dataForSEOClient),
        new GoogleKeywordOverviewTool(this.dataForSEOClient),
        new GoogleTopSearchesTool(this.dataForSEOClient),
        new GoogleSearchIntentTool(this.dataForSEOClient),
        new GoogleKeywordsForSiteTool(this.dataForSEOClient),
        new GoogleDomainIntersectionsTool(this.dataForSEOClient),
        new GoogleHistoricalDomainRankOverviewTool(this.dataForSEOClient),
        new GooglePageIntersectionsTool(this.dataForSEOClient),
        new GoogleBulkTrafficEstimationTool(this.dataForSEOClient),
        new DataForSeoLabsFilterTool(this.dataForSEOClient),
        new GoogleHistoricalKeywordDataTool(this.dataForSEOClient),
        // Add more tools here
      ];
    
      return tools.reduce((acc, tool) => ({
        ...acc,
        [tool.getName()]: {
          description: tool.getDescription(),
          params: tool.getParams(),
          handler: (params: any) => tool.handle(params),
        },
      }), {});
    }
  • Helper mapping in TOOL_TO_FILTER_MAP for using filters with this tool in the labs-available-filters tool.
    'dataforseo_labs_google_keyword_suggestions': 'keyword_suggestions.google',
Behavior3/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. It does well by detailing what data is returned (search volume, trends, CPC, competition, impressions, clicks) and explaining the algorithm's matching behavior (keywords can contain seed with additional words in different sequences). However, it lacks critical behavioral information: no mention of rate limits, authentication requirements, potential costs, error conditions, or pagination behavior (despite having offset/limit parameters). For a tool with 8 parameters and no annotations, this leaves significant gaps.

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

Conciseness3/5

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

The description is moderately concise but could be better structured. It uses 5 sentences to explain the tool's function, algorithm, and returned data. While each sentence adds value, the information isn't optimally front-loaded - the key purpose is clear in the first sentence, but important behavioral details are scattered. Some redundancy exists (e.g., 'returns only those search terms' and 'each keyword in the list matching' convey similar ideas). It's neither excessively verbose nor perfectly efficient.

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

Completeness3/5

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

Given the tool's complexity (8 parameters, no output schema, no annotations), the description is moderately complete. It covers the core functionality and return data well, but misses important contextual elements: no output format description, no error handling information, no rate limit or authentication context, and no guidance on when to use this versus sibling tools. For a data retrieval tool with filtering capabilities and no output schema, the description should provide more complete operational context.

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%, so the schema already documents all 8 parameters thoroughly. The description adds minimal parameter semantics beyond the schema - it mentions the 'seed keyword' (mapping to 'keyword' parameter) and implies filtering capabilities through the algorithm description, but doesn't provide additional context about parameter interactions or usage patterns. With high schema coverage, the baseline of 3 is appropriate as the description doesn't significantly enhance parameter understanding.

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

Purpose4/5

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

The description clearly states the tool's purpose: 'provides search queries that include the specified seed keyword' and 'returns only those search terms that contain the keyword you set'. It specifies the verb ('provides', 'returns') and resource ('search queries', 'keyword suggestions'), making it clear this is a keyword suggestion generator. However, it doesn't explicitly differentiate from sibling tools like 'dataforseo_labs_google_keyword_ideas' or 'dataforseo_labs_google_related_keywords', which likely serve similar purposes.

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?

The description provides minimal usage guidance. It mentions the algorithm is 'based on full-text search' and returns 'long-tail keywords', but offers no explicit when-to-use instructions, no prerequisites, and no comparison to alternative tools. With many sibling tools available for keyword analysis, the agent receives no help in selecting this specific tool over others in the same domain.

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/ravinwebsurgeon/seo-mcp'

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