AgentSEO MCP Server

AgentSEO Search

agentseo_search

Destructive

Run Google searches with optional include or exclude domain filters to gather SERP results, and avoid repeating charged calls by polling the returned job ID when pending.

Instructions

Perform a Google search with optional domain filters. 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": {
      "query": "<query>"
    },
    "name": "agentseo_search"
  }
}

Input Schema

Name	Required	Description
`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.
`limit`	No	Maximum number of search results to return; larger result sets may consume more credits. Type: Safe integer. Minimum: 1. Maximum: 50. Default: 10.
`query`	Yes	Google search query to run; provide the words or phrase to search for. Type: String. Required.
`exclude_domains`	No	Exclude these hostnames from search results, for example example.com. Type: Array. Optional; no client default.
`include_domains`	No	Restrict search results to these hostnames, for example example.com; omit for no inclusion filter. Type: Array. Optional; no client default.

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedv0.1.5Nov 5, 2026

addedInput schema / properties / exclude_domains / description

Added value: +"Exclude these hostnames from search results, for example example.com. Type: Array. Optional; no client default."

addedInput schema / properties / exclude_domains / items / description

Added value: +"One hostname to exclude from the search results, for example example.com. Type: String. Required."

addedInput schema / properties / include_domains / description

Added value: +"Restrict search results to these hostnames, for example example.com; omit for no inclusion filter. Type: Array. Optional; no client default."

addedInput schema / properties / include_domains / items / description

Added value: +"One allowed hostname for search inclusion, for example example.com. Type: String. Required."

addedInput schema / properties / limit / description

Added value: +"Maximum number of search results to return; larger result sets may consume more credits. Type: Safe integer. Minimum: 1. Maximum: 50. Default: 10."

changedInput schema / properties / query / description

Previous value: -"The search query"New value: +"Google search query to run; provide the words or phrase to search for. Type: String. Required."

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."

First observedv0.1.4Nov 4, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already flag readOnlyHint=false, destructiveHint=true and idempotentHint=false, but the description adds the concrete reason: the call consumes AgentSEO credits and duplicates create new charged work. That is meaningful cost/retry context beyond the structured fields, though it stops short of explaining what the job/polling flow looks like (which the schema covers).

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 tight sentences: purpose first, cost/retry caution second. Nothing is wasted and the most decision-relevant constraint is front-loaded.

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?

For a search tool with full schema coverage, no output schema, and rich annotations, the description supplies the two things the schema cannot: what it does and that calls are billed and non-idempotent. It leaves the pending-job polling detail to the schema, which handles it explicitly.

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 are already documented with types, defaults, bounds and hostname examples. The description only echoes "optional domain filters" and adds no syntax or semantics beyond the schema, making the baseline 3 appropriate.

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 ("Perform a Google search") and notes the optional domain filters that shape results. It does not distinguish itself from adjacent siblings like agentseo_analyze_serp or agentseo_ai_overview_extract, which also touch SERP data, so an agent gets a clear purpose but no explicit sibling differentiation.

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?

The warning that "repeating the call can create new charged work" implies a usage posture (don't re-run, reuse results), but it never names when to choose this tool over the many other SERP/keyword siblings. Guidance is implied rather than stated.

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

Deploy Server