Skip to main content
Glama
AgentSEO MCP Server

AgentSEO MCP Server

AgentSEO Backlinks Anchors

agentseo_backlinks_anchors
Destructive

Analyze backlink anchor text groups to classify branded, commercial, generic, URL, risky, broken, and lost patterns, helping identify link-profile issues before planning outreach or cleanup.

Instructions

Analyze backlink anchor text groups and classify branded, commercial, generic, URL, risky, broken, or lost anchor patterns. 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": {
      "target": "<target>"
    },
    "name": "agentseo_backlinks_anchors"
  }
}

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 aggregated anchor-text records to return. Type: Safe integer. Minimum: 1. Maximum: 100. Default: 25.
offsetNoZero-based result offset measured in rows; use with limit for pagination. Type: Safe integer. Minimum: 0. Maximum: 20000. Default: 0.
targetYesTarget domain, subdomain or absolute page URL to analyze; use a hostname or URL, not a business name. Type: String. Minimum: 1 characters. Required.
sort_byNoMetric used to order returned results; choose one of this tool’s accepted enum values. Type: String. Accepted values: "backlinks", "rank", "referring_domains", "spam_score", "broken_backlinks". Default: "backlinks".backlinks
rank_scaleNoRequested provider authority-score scale: one_hundred is 0-100; one_thousand is 0-1000. Individual filter input bounds still apply. Type: String. Accepted values: "one_hundred", "one_thousand". Default: "one_hundred".one_hundred
anchor_filterNoText filter to match backlink anchor text. Type: String. Minimum: 1 characters. Maximum: 80 characters. Optional; no client default.
dofollow_onlyNoRestrict results to followed backlinks when true; false does not apply that filter. Type: Boolean. Default: false.
min_backlinksNoMinimum backlink count for an aggregate record to be included. Type: Safe integer. Minimum: 1. Maximum: 10000000. Optional; no client default.
include_subdomainsNoInclude links or ranking data for subdomains of the target when true. Type: Boolean. Default: true.
internal_list_limitNoMaximum embedded sample rows per aggregate record; this does not cap the aggregate backlink totals. Type: Safe integer. Minimum: 1. Maximum: 100. Default: 10.
backlinks_status_typeNoBacklink lifecycle filter: live links only, lost links only, or all supported links. Type: String. Accepted values: "live", "all", "lost". Default: "live".live
min_referring_domainsNoMinimum count of distinct referring domains for a record to be included. Type: Safe integer. Minimum: 1. Maximum: 10000000. Optional; no client default.
include_indirect_linksNoInclude backlinks that reach the target through supported indirect/redirect link relationships when true. Type: Boolean. Default: true.
exclude_internal_backlinksNoExclude links originating within the target’s own site when true. Type: Boolean. Default: true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed15 schema fields changedv0.1.5
    • addedInput schema / properties / anchor_filter / description
      Added value: +"Text filter to match backlink anchor text. Type: String. Minimum: 1 characters. Maximum: 80 characters. Optional; no client default."
    • addedInput schema / properties / backlinks_status_type / description
      Added value: +"Backlink lifecycle filter: live links only, lost links only, or all supported links. Type: String. Accepted values: \"live\", \"all\", \"lost\". Default: \"live\"."
    • addedInput schema / properties / dofollow_only / description
      Added value: +"Restrict results to followed backlinks when true; false does not apply that filter. Type: Boolean. Default: false."
    • addedInput schema / properties / exclude_internal_backlinks / description
      Added value: +"Exclude links originating within the target’s own site when true. Type: Boolean. Default: true."
    • addedInput schema / properties / include_indirect_links / description
      Added value: +"Include backlinks that reach the target through supported indirect/redirect link relationships when true. Type: Boolean. Default: true."
    • 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 / internal_list_limit / description
      Added value: +"Maximum embedded sample rows per aggregate record; this does not cap the aggregate backlink totals. Type: Safe integer. Minimum: 1. Maximum: 100. Default: 10."
    • addedInput schema / properties / limit / description
      Added value: +"Maximum number of aggregated anchor-text records to return. Type: Safe integer. Minimum: 1. Maximum: 100. Default: 25."
    • addedInput schema / properties / min_backlinks / description
      Added value: +"Minimum backlink count for an aggregate record to be included. Type: Safe integer. Minimum: 1. Maximum: 10000000. Optional; no client default."
    • addedInput schema / properties / min_referring_domains / description
      Added value: +"Minimum count of distinct referring domains for a record to be included. Type: Safe integer. Minimum: 1. Maximum: 10000000. Optional; no client default."
    • 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 / rank_scale / description
      Added value: +"Requested provider authority-score scale: one_hundred is 0-100; one_thousand is 0-1000. Individual filter input bounds still apply. Type: String. Accepted values: \"one_hundred\", \"one_thousand\". Default: \"one_hundred\"."
    • 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: \"backlinks\", \"rank\", \"referring_domains\", \"spam_score\", \"broken_backlinks\". Default: \"backlinks\"."
    • 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: +"Target domain, subdomain or absolute page URL to analyze; use a hostname or URL, not a business name. Type: String. Minimum: 1 characters. Required."
  2. First observedv0.1.4

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, idempotentHint=false and openWorldHint=true; the description reinforces this rather than contradicting it by warning that repeating the call can create new charged work. It adds genuine context the annotations cannot convey (credit consumption, cost risk on retry), but it does not explain what is actually mutated, expected latency, or result shape.

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, no filler: the capability statement is front-loaded and the cost warning follows. Every clause carries information an agent needs.

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 15-parameter, no-output-schema tool, the description covers purpose, the classification output concept, and the cost/retry hazard, while the schema handles pagination, filtering and async job handling in detail. The main residual gap is that it never sketches what the returned anchor groups look like, though that is partially offset by the explicit classification list.

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 every one of the 15 parameters carries its own type, bounds, enum values and default, including the sync/job-polling caveat and internal_list_limit semantics. The description adds no parameter-level meaning beyond that, so the baseline of 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 names a specific verb and resource ('Analyze backlink anchor text groups') and enumerates the classification buckets (branded, commercial, generic, URL, risky, broken, lost), which is concrete enough to separate it from list-oriented siblings like agentseo_backlinks_list or agentseo_backlinks_summary. It does not explicitly name an alternative sibling, so it stops short of a 5.

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 second sentence tells the agent this consumes AgentSEO credits and that repeating the call can create new charged work, which is real usage guidance about cost. However, it never states when to pick this tool over the many adjacent backlink tools (summary, list, referring_domains, competitors), so the choice remains inferred from the name and description.

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