AgentSEO MCP Server

AgentSEO Content Cannibalization

agentseo_content_cannibalization

Destructive

Detect overlapping SEO pages and get safe consolidation, differentiation, canonical, and internal-link recommendations to resolve keyword cannibalization.

Instructions

Detect overlapping SEO pages and recommend safe consolidation, differentiation, canonical, and internal-link fixes. 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_content_cannibalization"
  }
}

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.
`pages`	Yes	Supplied page records to compare; URLs identify the records and are not instructions to publish changes. Type: Array. Minimum: 2 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.
`sensitivity`	No	Conservative, balanced or aggressive threshold preset for flagging page overlap. Type: String. Accepted values: "conservative", "balanced", "aggressive". Default: "balanced".	balanced
`focus_keywords`	No	Optional keyword phrases to emphasize when comparing the supplied pages. Type: Array. Maximum: 250 items. Default: [].

Schema Changelog

Changes observed during successful MCP inspections.

Changed25 schema fields changedv0.1.5Nov 5, 2026

addedInput schema / properties / focus_keywords / description

Added value: +"Optional keyword phrases to emphasize when comparing the supplied pages. Type: Array. Maximum: 250 items. Default: []."

addedInput schema / properties / focus_keywords / items / description

Added value: +"One keyword phrase to emphasize in the page comparison. Type: String. Minimum: 1 characters. Maximum: 120 characters. Required."

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: 2 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 / avg_position / description

Added value: +"Supplied mean organic search position, where 1 is best; not an authority score. Type: Number. Minimum: 1. Maximum: 100. Optional; no client default."

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

Added value: +"Count of backlinks reported for this supplied page. Type: Number. Minimum: 0. Optional; no client default."

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

Added value: +"Absolute canonical URL reported for this supplied page. Type: String. Format: absolute URL. Optional; no client default."

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

Added value: +"Count of search clicks in your supplied reporting window; use the same window across compared records. Type: Number. Minimum: 0. Optional; no client default."

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 / impressions / description

Added value: +"Count of search impressions in your supplied reporting window; use the same window across compared records. Type: Number. Minimum: 0. Optional; no client default."

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

Added value: +"Whether this supplied page is considered indexable according to your crawl evidence. Type: Boolean. Default: true."

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

Added value: +"Supplied page update date or timestamp; use YYYY-MM-DD or ISO 8601 when available. Type: String. Maximum: 40 characters. Optional; no client default."

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 / primary_keyword / description

Added value: +"Main keyword phrase assigned to this supplied page. Type: String. Minimum: 1 characters. Maximum: 120 characters. Optional; no client default."

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

Added value: +"Search queries known to rank for this page from your supplied evidence. Type: Array. Maximum: 100 items. Default: []."

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

Added value: +"One search query known to rank for this page. Type: String. Minimum: 1 characters. Maximum: 120 characters. Required."

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

Added value: +"Additional keyword phrases this supplied page is intended to target. Type: Array. Maximum: 50 items. Default: []."

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

Added value: +"One keyword phrase this supplied page is intended to target. Type: String. Minimum: 1 characters. Maximum: 120 characters. Required."

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 overlap analysis; no page fetch is requested by this record. Type: String. Format: absolute URL. Required."

addedInput schema / properties / sensitivity / description

Added value: +"Conservative, balanced or aggressive threshold preset for flagging page overlap. Type: String. Accepted values: \"conservative\", \"balanced\", \"aggressive\". Default: \"balanced\"."

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 / description

Added 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

A3.7/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=false; the description earns credit for adding the concrete consequence beyond them — AgentSEO credits are consumed and a repeat call creates new charged work. There is a mild tension in that "recommend ... fixes" reads as advisory output while destructiveHint is true, but the credit-billing note plausibly explains the destructive flag, so this is not a contradiction.

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 short sentences with zero padding: capability first, cost/retry caveat second. Every clause carries information an agent would otherwise lack.

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 charged, non-idempotent analysis over 2–100 page records with no output schema, the description says nothing about what comes back (overlap clusters? per-pair verdicts? fix types per page) or how results should be interpreted. The credit and repeat-charge warnings are valuable, but the return shape and the meaning of "safe consolidation" are left unspecified.

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 the schema already documents pages, target, sensitivity, focus_keywords, and sync in detail. The description adds no parameter-level meaning (not even what "sensitivity" thresholds do differently), 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?

"Detect overlapping SEO pages and recommend safe consolidation, differentiation, canonical, and internal-link fixes" gives a specific verb (detect), a specific resource (overlapping pages), and enumerates the remedy types returned. It is clearly distinct from siblings like agentseo_content_gap or agentseo_content_internal_links, though it never names an alternative to route against.

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 implied by the topic (use when pages compete for the same queries) and the credit/repeat warning implies a retry policy, but there is no explicit when-to-use versus agentseo_content_gap, agentseo_content_refresh_brief, or agentseo_content_action_plan. The exclusion guidance lives only in the schema's sync parameter description (poll agentseo_job_status instead of repeating).

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

Deploy Server