Skip to main content
Glama
Sign In

SEO Skill

by dev.seoskill
OverviewDiscussionsAdmin

Keyword, competitor, backlink and AI answer data

seo_research
Read-only

Data from the person’s own DataForSEO or Ahrefs account, which costs them credits. It uses the key the person saved on their seoskill.dev account (or on this machine for the CLI). Actions: provider is optional: without it the call uses the saved key, DataForSEO when both are saved. The target is a domain (the whole site), a path ending in / such as example.com/blog/ (every URL under it), or one page; scope overrides that. keyword_metrics (keywords: volume, difficulty, CPC), keyword_ideas (up to 5 seed keywords: searches that contain each seed, by volume), ranked_keywords (target: keywords a site, subfolder or page ranks for, with the provider's traffic total for the whole target), top_pages (target: the pages with the most estimated organic traffic), serp (keywords, up to 5: the ranking pages, each with its domain's authority: DataForSEO domain_rank 0 to 100, Ahrefs domain_rating; depth sets results per keyword, default 20; rows run position by position across the keywords), serp_overlap (2 to 10 keywords: for each pair, how many of their top 10 pages and sites are the same, to decide one page or several; results without a real page are counted, not compared), competitors (target: domains that share keywords), backlinks (target: referring domains), pages_by_backlinks (target: the pages with the most referring domains), link_gap (target and 2 to 5 competitors: referring domains that link to two or more competitors and not the target, highest authority first, from each site's top 1,000 referring domains; costs one backlinks call per site), ai_answers (DataForSEO only; target: the site. Without keywords it takes the site’s top 10 chat-style and long questions from Search Console’s AI-shaped queries itself. With up to 10 questions in keywords it asks those instead, and the target can be any domain, such as a competitor's. Each answer row also lists the other sites it cites, and the notes rank them. Answers come from DataForSEO's queue: answers not ready after about 40 seconds are returned as tasks, already paid for; call again with the same target and those tasks to read them at no cost. It asks ChatGPT search, Google AI Mode and Google AI Overviews each one and says whether the answer cites or mentions the site. DataForSEO’s queue prices are about $0.0072 a question across the three engines, so about $0.07 a run: tell the person before running it). Rows with a domain, and the target, get a free Ahrefs domain_rating column. Numbers are provider estimates, not Search Console data.

Input Schema

NameRequiredDescriptionDefault
alsoNoai_answers only: the brand's other domains, such as claude.ai beside claude.com. A citation to any of them counts as citing the target.
brandNoai_answers only: the brand names that count as a mention, such as Datadog for datadoghq.com. Default: each domain's name.
depthNoserp only: results per keyword, default 20. Deeper costs more.
scopeNoOptional: domain, prefix or exact, to read the target another way than its shape says.
tasksNoai_answers only: the tasks an earlier run returned as not ready, to read back at no cost.
actionYes
detailNosummary first. rows: the next page of rows. full: every field as JSON.summary
offsetNorows only: the first row to return.
targetNoDomain (the whole site), a path ending in / for every URL under it, such as example.com/blog/, or one page.
countryNoTwo-letter country code.us
keywordsNo
providerNoOptional. Without it, the saved key; DataForSEO when both are saved.
competitorsNolink_gap only: 2 to 5 competitor domains.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changed
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "keyword_metrics",
-  "ranked_keywords",
-  "serp",
-  "competitors",
-  "backlinks",
-  "link_gap",
-  "ai_answers"
-]New value: +[
+  "keyword_metrics",
+  "ranked_keywords",
+  "serp",
+  "competitors",
+  "backlinks",
+  "link_gap",
+  "ai_answers",
+  "top_pages",
+  "pages_by_backlinks",
+  "keyword_ideas",
+  "serp_overlap"
+]
    • addedInput schema / properties / also
      Added value: +{
+  "default": [],
+  "description": "ai_answers only: the brand's other domains, such as claude.ai beside claude.com. A citation to any of them counts as citing the target.",
+  "items": {
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 4,
+  "type": "array"
+}
    • addedInput schema / properties / brand
      Added value: +{
+  "default": [],
+  "description": "ai_answers only: the brand names that count as a mention, such as Datadog for datadoghq.com. Default: each domain's name.",
+  "items": {
+    "maxLength": 60,
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 10,
+  "type": "array"
+}
    • addedInput schema / properties / depth
      Added value: +{
+  "description": "serp only: results per keyword, default 20. Deeper costs more.",
+  "maximum": 100,
+  "minimum": 1,
+  "type": "integer"
+}
    • addedInput schema / properties / provider / description
      Added value: +"Optional. Without it, the saved key; DataForSEO when both are saved."
    • addedInput schema / properties / scope
      Added value: +{
+  "description": "Optional: domain, prefix or exact, to read the target another way than its shape says.",
+  "enum": [
+    "domain",
+    "prefix",
+    "exact"
+  ],
+  "type": "string"
+}
    • changedInput schema / properties / target / description
      Previous value: -"Domain or URL."New value: +"Domain (the whole site), a path ending in / for every URL under it, such as example.com/blog/, or one page."
    • changedInput schema / required
      Previous value: -[
-  "provider",
-  "action"
-]New value: +[
+  "action"
+]
  2. Changed2 schema fields changed
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "keyword_metrics",
-  "ranked_keywords",
-  "serp",
-  "competitors",
-  "backlinks",
-  "ai_answers"
-]New value: +[
+  "keyword_metrics",
+  "ranked_keywords",
+  "serp",
+  "competitors",
+  "backlinks",
+  "link_gap",
+  "ai_answers"
+]
    • addedInput schema / properties / competitors
      Added value: +{
+  "default": [],
+  "description": "link_gap only: 2 to 5 competitor domains.",
+  "items": {
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 5,
+  "type": "array"
+}
  3. Changed1 schema field changed
    • addedInput schema / properties / tasks
      Added value: +{
+  "default": [],
+  "description": "ai_answers only: the tasks an earlier run returned as not ready, to read back at no cost.",
+  "items": {
+    "pattern": "^([a-z_]+):([0-9a-f-]{20,64})$",
+    "type": "string"
+  },
+  "maxItems": 30,
+  "type": "array"
+}
  4. Changed1 schema field changed
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "keyword_metrics",
-  "ranked_keywords",
-  "serp",
-  "competitors",
-  "backlinks"
-]New value: +[
+  "keyword_metrics",
+  "ranked_keywords",
+  "serp",
+  "competitors",
+  "backlinks",
+  "ai_answers"
+]
  5. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the readOnlyHint and openWorldHint annotations, the description discloses that calls consume the user's paid provider credits, explains provider key fallback behavior, details the ai_answers queue and paid-task retry mechanism, and gives a concrete cost estimate with an instruction to warn the user. These are exactly the behavioral traits annotations cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single very long, dense paragraph that buries the action-by-action semantics in run-on prose. Most sentences carry useful information, but structure and scannability suffer, and the opening cost/account context precedes the core purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 13-parameter, multi-action tool with no output schema, the description covers every action, the cost model, provider behavior, async queue handling, and how rows and citations are returned. An agent has enough information to select an action and invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although schema coverage is already 85%, the description adds substantial meaning beyond field-level definitions: target shape controls scope, scope overrides target shape, keywords vary by action with different limits, competitors applies only to link_gap, and tasks/also/brand apply only to ai_answers. It also explains how depth and per-action row outputs behave.

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 states a specific resource (DataForSEO/Ahrefs SEO data) and enumerates the actions it can perform with clear per-action scope. It does not distinguish itself from sibling tools such as seo_compare or seo_report, but the purpose is otherwise unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is explained action by action: target shape determines domain, prefix or exact scope; provider defaults are described; keyword counts and limits are given for each action. It lacks explicit routing versus sibling tools like seo_compare, but within the tool the when-to-use guidance is strong.

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

All SEO Skill toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources