AgentSEO MCP Server

AgentSEO AI Overview Extract

agentseo_ai_overview_extract

Destructive

Extract AI Overview insights for a target keyword, including optional domain checks against sampled candidates. Use it to analyze AI search visibility by keyword, language, and location.

Instructions

Extract AI Overview insights for a target keyword. Uses AgentSEO credits; repeating the call can create new charged work.

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": "agentseo_ai_overview_extract"
  }
}

Input Schema

Name	Required	Description	Default
`sync`	No	Request a bounded wait for completion when true. The API can still return a pending job; retain its job ID and poll agentseo_job_status instead of repeating this charged call. False returns a queued job without waiting. Type: Boolean. Default: true.
`keyword`	Yes	Search keyword or phrase to analyze for this workflow. Type: String. Required.
`language`	No	Supported search language code, for example en for English. Type: String. Default: "en".	en
`location`	No	Supported geographic search-market name, for example United States; this is not a coordinate pair. Type: String. Default: "United States".	United States
`target_domain`	No	Your hostname, for example example.com, to check against sampled AI Overview candidate domains; this is not official citation attribution. Type: String. Optional; no client default.

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedv0.1.5Nov 5, 2026

changedInput schema / properties / keyword / description

Previous value: -"Target keyword"New value: +"Search keyword or phrase to analyze for this workflow. Type: String. Required."

addedInput schema / properties / language / description

Added value: +"Supported search language code, for example en for English. Type: String. Default: \"en\"."

addedInput schema / properties / location / description

Added value: +"Supported geographic search-market name, for example United States; this is not a coordinate pair. Type: String. Default: \"United States\"."

addedInput schema / properties / sync / description

Added value: +"Request a bounded wait for completion when true. The API can still return a pending job; retain its job ID and poll agentseo_job_status instead of repeating this charged call. False returns a queued job without waiting. Type: Boolean. Default: true."

addedInput schema / properties / target_domain / description

Added value: +"Your hostname, for example example.com, to check against sampled AI Overview candidate domains; this is not official citation attribution. Type: String. Optional; no client default."

First observedv0.1.4Nov 4, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations already flag destructiveHint=true, idempotentHint=false, and openWorldHint=true; the description adds genuinely new behavioral context by disclosing credit consumption and that repeated invocations can spawn new charged work. This is consistent with the non-idempotent, destructive annotations rather than contradicting them, though it does not say what an extraction costs or how large the charge is.

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?

Two sentences, front-loaded with the action and followed by the cost caveat, with no filler. The second sentence is slightly vague ("can create new charged work") but still earns its place as a repeat-call warning.

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?

For a five-parameter, charged, non-idempotent extraction with no output schema, the description covers purpose and billing risk but leaves the agent to work out how this differs from the AI-visibility and SERP siblings and how to handle a pending job. The essential calling information exists, but the tool-selection context is thin given the crowd of related tools.

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 all five parameters (including sync, language, location, target_domain) are already fully documented in the schema. The description adds only the phrase "target keyword," which conveys nothing the keyword property does not already state, 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?

The description states a specific verb and resource ("Extract AI Overview insights") scoped to a "target keyword," which is enough to distinguish it from siblings like agentseo_analyze_serp or agentseo_search. It stops short of naming those alternatives, so the agent must infer the boundary from their names alone.

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?

There is no explicit when-to-use or when-not-to-use guidance against the many similar SERP/content siblings. The only quasi-guidance is a cost caution about repeating the call, which implies the tool is a one-shot charged extraction but does not say what to do instead (the schema's sync parameter, not the description, points to agentseo_job_status).

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

Deploy Server