Skip to main content
Glama
AgentSEO MCP Server

AgentSEO MCP Server

AgentSEO Page Intersection

agentseo_page_intersection
Destructive

Compares ranking keywords across up to five pages to reveal shared terms or competitor keywords missing from your pages, so you can find content gaps and prioritize SEO opportunities.

Instructions

Compare ranking pages to find shared page keywords or competitor-page keywords excluded from your pages. 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": {
      "pages": "<pages>"
    },
    "name": "agentseo_page_intersection"
  }
}

Input Schema

NameRequiredDescriptionDefault
syncNoRequest 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.
limitNoMaximum number of keyword intersection records to return. Type: Safe integer. Minimum: 5. Maximum: 100. Default: 25.
pagesYesAbsolute page URLs whose ranking keywords should be compared; these are URLs, not supplied page objects. Type: Array. Minimum: 1 items. Maximum: 5 items. Required.
offsetNoZero-based result offset measured in rows; use with limit for pagination. Type: Safe integer. Minimum: 0. Maximum: 20000. Default: 0.
sort_byNoMetric used to order returned results; choose one of this tool’s accepted enum values. Type: String. Accepted values: "opportunity", "search_volume", "traffic_gap", "rank", "cpc". Default: "opportunity".opportunity
languageNoSupported search language code, for example en for English. Type: String. Default: "en".en
locationNoSupported geographic search-market name, for example United States; this is not a coordinate pair. Type: String. Default: "United States".United States
max_rankNoWorst organic search position to include, where 1 means first. Type: Safe integer. Minimum: 1. Maximum: 100. Default: 30.
item_typesNoSearch-result categories to include in the page intersection analysis. Type: Array. Minimum: 1 items. Maximum: 4 items. Default: ["organic","featured_snippet"].
exclude_pagesNoAbsolute page URLs to exclude from the keyword intersection comparison. Type: Array. Maximum: 5 items. Default: [].
location_codeNoNumeric provider location identifier for the search market; the service validates support alongside the location name. Type: Safe integer. Must be greater than 0. Optional; no client default.
ignore_synonymsNoAsk the provider not to expand keyword matching to synonyms when true. Type: Boolean. Default: true.
include_serp_infoNoInclude provider search-result context in the returned records when true. Type: Boolean. Default: false.
intersection_modeNoWhether matches must cover every supplied target (all) or a supported subset (partial). Type: String. Accepted values: "union", "intersect". Default: "union".union
min_search_volumeNoMinimum estimated monthly keyword searches to include; zero disables this lower-bound filter. Type: Safe integer. Minimum: 0. Maximum: 10000000. Default: 0.
include_subdomainsNoInclude links or ranking data for subdomains of the target when true. Type: Boolean. Default: true.
include_clickstream_dataNoRequest available provider clickstream-derived estimates when true; these are not your own analytics measurements. Type: Boolean. Default: false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed20 schema fields changedv0.1.5
    • addedInput schema / properties / exclude_pages / description
      Added value: +"Absolute page URLs to exclude from the keyword intersection comparison. Type: Array. Maximum: 5 items. Default: []."
    • addedInput schema / properties / exclude_pages / items / description
      Added value: +"One absolute page URL to exclude from the keyword intersection. Type: String. Format: absolute URL. Required."
    • addedInput schema / properties / ignore_synonyms / description
      Added value: +"Ask the provider not to expand keyword matching to synonyms when true. Type: Boolean. Default: true."
    • addedInput schema / properties / include_clickstream_data / description
      Added value: +"Request available provider clickstream-derived estimates when true; these are not your own analytics measurements. Type: Boolean. Default: false."
    • addedInput schema / properties / include_serp_info / description
      Added value: +"Include provider search-result context in the returned records when true. Type: Boolean. Default: false."
    • addedInput schema / properties / include_subdomains / description
      Added value: +"Include links or ranking data for subdomains of the target when true. Type: Boolean. Default: true."
    • addedInput schema / properties / intersection_mode / description
      Added value: +"Whether matches must cover every supplied target (all) or a supported subset (partial). Type: String. Accepted values: \"union\", \"intersect\". Default: \"union\"."
    • addedInput schema / properties / item_types / description
      Added value: +"Search-result categories to include in the page intersection analysis. Type: Array. Minimum: 1 items. Maximum: 4 items. Default: [\"organic\",\"featured_snippet\"]."
    • addedInput schema / properties / item_types / items / description
      Added value: +"One search-result category to include in the comparison. Type: String. Accepted values: \"organic\", \"paid\", \"featured_snippet\", \"local_pack\". Required."
    • addedInput schema / properties / language / description
      Added value: +"Supported search language code, for example en for English. Type: String. Default: \"en\"."
    • addedInput schema / properties / limit / description
      Added value: +"Maximum number of keyword intersection records to return. Type: Safe integer. Minimum: 5. Maximum: 100. Default: 25."
    • 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 / location_code / description
      Added value: +"Numeric provider location identifier for the search market; the service validates support alongside the location name. Type: Safe integer. Must be greater than 0. Optional; no client default."
    • addedInput schema / properties / max_rank / description
      Added value: +"Worst organic search position to include, where 1 means first. Type: Safe integer. Minimum: 1. Maximum: 100. Default: 30."
    • addedInput schema / properties / min_search_volume / description
      Added value: +"Minimum estimated monthly keyword searches to include; zero disables this lower-bound filter. Type: Safe integer. Minimum: 0. Maximum: 10000000. Default: 0."
    • addedInput schema / properties / offset / description
      Added value: +"Zero-based result offset measured in rows; use with limit for pagination. Type: Safe integer. Minimum: 0. Maximum: 20000. Default: 0."
    • addedInput schema / properties / pages / description
      Added value: +"Absolute page URLs whose ranking keywords should be compared; these are URLs, not supplied page objects. Type: Array. Minimum: 1 items. Maximum: 5 items. Required."
    • addedInput schema / properties / pages / items / description
      Added value: +"One absolute page URL whose ranking keywords should be compared. Type: String. Format: absolute URL. Required."
    • addedInput schema / properties / sort_by / description
      Added value: +"Metric used to order returned results; choose one of this tool’s accepted enum values. Type: String. Accepted values: \"opportunity\", \"search_volume\", \"traffic_gap\", \"rank\", \"cpc\". Default: \"opportunity\"."
    • 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."
  2. First observedv0.1.4

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true; the description adds genuinely new context by stating that calls consume AgentSEO credits and that repeating a call can spawn additional charged work. It does not explain what 'destructive' means in practice (billing only, or data effects) nor mention polling, though the sync parameter schema covers that.

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, no filler: the first states what the comparison produces and the second front-loads the cost/idempotency warning. Nothing is repeated from the schema and nothing could be cut without losing information.

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 17-parameter, credit-charged, open-world tool with no output schema, the description is thin: it never says what a result record contains or how pagination/limits shape output, leaving the agent to reconstruct the return shape from parameter names. The cost warning is a valuable addition, but the definition is only minimally sufficient for a tool of this complexity.

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 17 parameters are already documented in detail, including enums, defaults and bounds. The description adds no meaning beyond that — it does not clarify intersection_mode semantics or how exclude_pages interacts with pages — 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 gives a concrete verb and resource: compare ranking pages to surface shared keywords or keywords a competitor page ranks for that yours do not. That is clearly distinct from domain-level or backlink intersections among the siblings, but it never names those alternatives, so the agent must infer the boundary from the description 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?

Usage is only implied: the agent learns the tool is for page-vs-page keyword comparison and that it costs credits, but there is no statement of when to prefer agentseo_domain_intersection or agentseo_content_gap, nor any prerequisite or exclusion guidance. The credit warning functions as a caution, not as routing guidance.

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