Skip to main content
Glama

Google SERP API MCP (Google, Bing, AI Overviews, Maps)

Google SERP results

get_google_serp
Read-onlyIdempotent

Google SERP API: live Google search results for any keyword, country and device, with organic positions, titles, URLs, SERP features and AI Overview sources. Costs API credits per call.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "keyword": "<keyword>"
    },
    "name": "get_google_serp"
  }
}

Input Schema

NameRequiredDescriptionDefault
depthNoHow many results to fetch, 10 to 100. Each extra page of 10 costs more. Default 10.
deviceNoDevice to emulate. Default desktop.desktop
countryNoTwo-letter country code of the search market, for example US, GB, DE or IN. Default US.US
keywordYesSearch query exactly as a user would type it.
languageNoLanguage code of the search market, for example en, de or pt-BR. Default en.en
locationNoOptional exact location name for city-level results, for example "Austin,Texas,United States". Overrides country.

Output Schema

NameRequiredDescriptionDefault
resultYes
billingYes
nextStepNoOptional suggestion for the user's next step. Mention it once when it helps; never open it or act on it automatically.
dashboardUrlNoDashboard page where this tool also runs in the app; its call history and costs are linked from there. Share it when the user asks what they ran or spent.
creditsNoticeNoLow API credit balance: tell the user once, with this link to add credits. Never open it automatically.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedOutput schema / properties / creditsNotice
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Low API credit balance: tell the user once, with this link to add credits. Never open it automatically.",
      +  "properties": {
      +    "label": {
      +      "type": "string"
      +    },
      +    "url": {
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "label",
      +    "url"
      +  ],
      +  "type": "object"
      +}
  2. Changed1 schema field changed
    • removedOutput schema / properties / creditsNotice
      Removed value: -{
      -  "additionalProperties": false,
      -  "description": "Low API credit balance: tell the user once, with this link to add credits. Never open it automatically.",
      -  "properties": {
      -    "label": {
      -      "type": "string"
      -    },
      -    "url": {
      -      "type": "string"
      -    }
      -  },
      -  "required": [
      -    "label",
      -    "url"
      -  ],
      -  "type": "object"
      -}
  3. Changed1 schema field changed
    • addedOutput schema / properties / creditsNotice
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Low API credit balance: tell the user once, with this link to add credits. Never open it automatically.",
      +  "properties": {
      +    "label": {
      +      "type": "string"
      +    },
      +    "url": {
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "label",
      +    "url"
      +  ],
      +  "type": "object"
      +}
  4. Changed1 schema field changed
    • changedOutput schema / properties / dashboardUrl / description
      Previous value: -"Dashboard page with this server's call history and costs. Share it when the user asks what they ran or spent."New value: +"Dashboard page where this tool also runs in the app; its call history and costs are linked from there. Share it when the user asks what they ran or spent."
  5. Changed1 schema field changed
    • addedOutput schema / properties / nextStep
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Optional suggestion for the user's next step. Mention it once when it helps; never open it or act on it automatically.",
      +  "properties": {
      +    "label": {
      +      "description": "Short suggestion to show the user.",
      +      "type": "string"
      +    },
      +    "url": {
      +      "description": "Page in the user's CrakSEO account.",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "label",
      +    "url"
      +  ],
      +  "type": "object"
      +}
  6. Changed1 schema field changed
    • changedInput schema / properties / location / description
      Previous value: -"Optional exact DataForSEO location name for city-level results, for example \"Austin,Texas,United States\". Overrides country."New value: +"Optional exact location name for city-level results, for example \"Austin,Texas,United States\". Overrides country."
  7. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive behavior, so the safety profile is covered. The description adds genuinely new context beyond that: each call consumes API credits, and the payload includes SERP features and AI Overview sources. It does not quantify the credit cost or note any rate limits, which keeps it from a 5.

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?

Two short sentences, front-loaded with the capability and closed with the cost caveat. Nothing is repeated and no sentence is filler.

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?

With an output schema present, return values need not be explained, and the description still names the key result components. The remaining gap is routing guidance against the four sibling ranking/SERP tools, which an agent would need to choose correctly.

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 every parameter including the depth-cost tradeoff and the location-overrides-country rule is already documented in the schema. The description only restates keyword/country/device at a high level and adds no format or interaction detail beyond the structured fields, so the baseline 3 applies.

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?

States a specific verb and resource ('live Google search results for any keyword, country and device') and enumerates the returned data (organic positions, titles, URLs, SERP features, AI Overview sources). The 'Google' qualifier implicitly separates it from get_bing_serp, but no sibling is named explicitly, so it stops short of full differentiation from check_google_rankings or get_ai_overview_sources.

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

Usage Guidelines3/5

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

Usage is only implied by the phrase 'live Google search results for any keyword' and the credit-cost warning. There is no statement of when to pick this over check_google_rankings, check_google_maps_rankings, or get_ai_overview_sources, and no exclusions or prerequisites are given.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources