AgentSEO MCP Server

AgentSEO Content Keyword Map

agentseo_content_keyword_map

Destructive

Maps supplied keywords to supplied pages and flags missing pages or cannibalization risks, helping identify keyword coverage gaps and conflicting page targeting.

Instructions

Map supplied keywords to supplied pages and flag missing pages or cannibalization risks. 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": {
      "keywords": "<keywords>",
      "pages": "<pages>"
    },
    "name": "agentseo_content_keyword_map"
  }
}

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.
`pages`	Yes	Supplied page records to compare; URLs identify the records and are not instructions to publish changes. Type: Array. Minimum: 1 items. Maximum: 100 items. Required.
`target`	No	Your target brand, domain or URL used to scope this workflow; supply the entity you want assessed. Type: String. Optional; no client default.
`keywords`	Yes	Search phrases to evaluate or associate with the supplied page. Type: Array. Minimum: 1 items. Maximum: 250 items. Required.
`max_mappings`	No	Maximum number of keyword-to-page mappings to include in the result. Type: Safe integer. Minimum: 1. Maximum: 250. Default: 250.

Schema Changelog

Changes observed during successful MCP inspections.

Changed15 schema fields changedv0.1.5Nov 5, 2026

addedInput schema / properties / keywords / description

Added value: +"Search phrases to evaluate or associate with the supplied page. Type: Array. Minimum: 1 items. Maximum: 250 items. Required."

addedInput schema / properties / keywords / items / description

Added value: +"One search keyword or phrase, not a comma-separated list. Type: String. Minimum: 1 characters. Required."

addedInput schema / properties / max_mappings / description

Added value: +"Maximum number of keyword-to-page mappings to include in the result. Type: Safe integer. Minimum: 1. Maximum: 250. Default: 250."

addedInput schema / properties / pages / description

Added value: +"Supplied page records to compare; URLs identify the records and are not instructions to publish changes. Type: Array. Minimum: 1 items. Maximum: 100 items. Required."

addedInput schema / properties / pages / items / description

Added value: +"One supplied page record used in this comparison. Type: Object. Required."

addedInput schema / properties / pages / items / properties / current_keywords / description

Added value: +"Keywords currently assigned to or targeted by this supplied page. Type: Array. Maximum: 30 items. Default: []."

addedInput schema / properties / pages / items / properties / current_keywords / items / description

Added value: +"One keyword currently assigned to this supplied page. Type: String. Minimum: 1 characters. Required."

addedInput schema / properties / pages / items / properties / description / description

Added value: +"Short summary of this supplied page; this is input evidence, not a request to generate a meta description. Type: String. Maximum: 500 characters. Optional; no client default."

addedInput schema / properties / pages / items / properties / headings / description

Added value: +"Existing page headings as plain-text strings, in reading order when available. Type: Array. Maximum: 30 items. Default: []."

addedInput schema / properties / pages / items / properties / headings / items / description

Added value: +"One existing page heading as plain text. Type: String. Minimum: 1 characters. Required."

addedInput schema / properties / pages / items / properties / page_type / description

Added value: +"Page format or classification for this record; select one of the accepted values. Type: String. Accepted values: \"unknown\", \"homepage\", \"blog_post\", \"landing_page\", \"product\", \"software\", \"local_business\", \"comparison_page\", \"guide\", \"docs\". Default: \"unknown\"."

addedInput schema / properties / pages / items / properties / title / description

Added value: +"Title of the supplied page or work item, used as its human-readable label. Type: String. Minimum: 1 characters. Maximum: 180 characters. Required."

addedInput schema / properties / pages / items / properties / url / description

Added value: +"Absolute URL identifying this supplied page for keyword mapping; the page content is supplied in the other record fields. Type: String. Format: absolute URL. 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."

changedInput schema / properties / target / description

Previous value: -"Optional target brand, domain, or product"New value: +"Your target brand, domain or URL used to scope this workflow; supply the entity you want assessed. Type: String. Optional; no client default."

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 declare destructiveHint=true and idempotentHint=false, and the description reinforces that with concrete cost context: AgentSEO credits are consumed and a repeat call can generate new charged work. That is real added value beyond the annotations, though it does not explain why the operation is flagged destructive (nothing on the site appears to be mutated) or give any rate/quota details.

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 sentences, the capability front-loaded and the cost caveat second; nothing is wasted and there is no redundant restatement of the title.

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 five-parameter charged tool with a rich schema but no output schema, the description establishes what comes back at a high level (mappings, missing pages, cannibalization) and warns about repeat charges. It could say more about the shape of results and about what 'destructive' means here, but an agent has enough to invoke it 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% and the schema itself spells out each field, its type, limits and defaults, including the sync/job-status guidance. The description adds no field-level meaning beyond restating that keywords and pages must be supplied, 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 uses a specific verb plus two resources ('map supplied keywords to supplied pages') and names the two outputs it produces: missing-page flags and cannibalization risks. It is clear on its own, but it never names a sibling such as agentseo_content_cannibalization or agentseo_content_gap, so the agent must infer the boundary itself.

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: the caller is expected to already hold a keyword list and page corpus, and the description warns that repeating the call creates new charged work. It gives no explicit when-to-use versus when-to-prefer conditions relative to the many sibling content/gap tools.

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

Deploy Server