SerpKite

Google Search

search

Read-onlyIdempotent

Search Google. Returns organic results, answer box, knowledge graph, People-also-ask and related searches as Markdown. 1 credit.

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": {
      "q": "<q>"
    },
    "name": "search"
  }
}

Input Schema

Name	Required	Description
`q`	Yes	Search query
`num`	No	Results (depth >10 costs up to 7 credits)
`page`	No
`time`	No	Restrict to recent results
`engine`	No	google (default), auto (fall back to other engines when Google is unavailable), consensus (several engines in parallel, merged and ranked by agreement; costs the sum of the engines that answered), or brave, bing, yahoo, duckduckgo, wikipedia, yandex (Yandex web search, strongest for Russian and CIS queries); a comma-separated list also works
`country`	No	Country code, e.g. us, de, ru
`end_date`	No	Only results published on or before this date (YYYY-MM-DD)
`language`	No	Language code, e.g. en, ru (Russian). Does not change country
`location`	No	City-level location, e.g. "Austin, Texas, United States"
`highlights`	No	With include_content: return the 3 passages most relevant to q per page instead of the whole page (free)
`start_date`	No	Only results published on or after this date (YYYY-MM-DD)
`boost_domains`	No	Move results from these sources to the top, keeping the rest: a domain (example.com, subdomains match), a path prefix (github.com/org) or a TLD (.gov)
`include_answer`	No	Also write a short cited answer over the results (+2 credits, +4 with include_content; free if it fails)
`exclude_domains`	No	Drop results from these sources: a domain (example.com, subdomains match), a path prefix (github.com/org) or a TLD (.gov)
`include_content`	No	Also fetch the top N result pages as Markdown (+1 credit each)
`include_domains`	No	Only results from these sources: a domain (example.com, subdomains match), a path prefix (github.com/org) or a TLD (.gov)

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 29, 2026

changedInput schema / properties / country / description

Previous value: -"Country code, e.g. us, de, ru. Uses shared proxy routes"New value: +"Country code, e.g. us, de, ru"

Changed1 schema field changedOct 24, 2026

addedInput schema / properties / include_answer

Added value: +{
+  "description": "Also write a short cited answer over the results (+2 credits, +4 with include_content; free if it fails)",
+  "type": "boolean"
+}

Changed1 schema field changedOct 23, 2026

changedInput schema / properties / engine / description

Previous value: -"google (default), auto (fall back to other engines when Google is unavailable), consensus (several engines in parallel, merged and ranked by agreement; costs the sum of the engines that answered), or brave, bing, yahoo, duckduckgo, wikipedia; a comma-separated list also works"New value: +"google (default), auto (fall back to other engines when Google is unavailable), consensus (several engines in parallel, merged and ranked by agreement; costs the sum of the engines that answered), or brave, bing, yahoo, duckduckgo, wikipedia, yandex (Yandex web search, strongest for Russian and CIS queries); a comma-separated list also works"

First observedOct 9, 2026

TDQS

A3.5/5.0

Behavior4/5

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

Annotations already declare read-only, open-world, idempotent, and non-destructive behavior. The description adds useful context beyond annotations by specifying the return format (Markdown with organic results, answer box, etc.) and the base credit cost.

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 two tight sentences with no wasted words, front-loading the core action and return format. Every clause earns its place.

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?

The tool has 16 parameters and many sibling tools, but the description covers only basic output content and cost. With no output schema and high schema coverage for parameters, the description is adequate but leaves a clear gap around when to use this tool versus alternatives.

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 94%, so the schema itself documents nearly all parameters, including cost impacts and filtering options. The description adds no parameter-level meaning beyond what is already in the schema, which is the baseline 3 case.

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 states a specific verb and resource ('Search Google') and enumerates the result types returned. It is clear what the tool does, but it does not differentiate itself from siblings such as answer, news, or ai_mode.

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 no guidance on when to use this tool versus the many sibling search tools. It also omits any exclusions or conditions that would help an agent choose correctly.

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

All SerpKite tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.