_ registry / mcp streamable-http · checked 22h ago

seoscoreapi

https://seoscoreapi.com

Registry code: 44e3d41785e91739

api record

SEO Score API audits web pages for SEO, GEO (how visible a page is to AI assistants and AI search), ADA / WCAG 2.1 AA accessibility and conversion, and tracks how often AI engines mention and cite a brand.

Good first calls:

endpoint
https://seoscoreapi.com/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is seoscoreapi live?
Yes — it answered the hub's last check (checked 22h ago). It answered 100% of checks over the last 30 days.
Is seoscoreapi free to use?
Not measured yet.
What tools does seoscoreapi have?
46 tools: history_domains, get_citation_run, usage, report_url, add_monitor, list_monitors, citation_topup_checkout, deep_audit_usage, ….
Is seoscoreapi safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
669ms

last good check

priced tools
0

of 46 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 46 tools
46 never probed 0 of 46 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • history_domains unknown never probed

    List every domain audited by this API key with the latest score and 30-day trend. Starter+.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • get_citation_run unknown never probed

    A citation run's status plus every per-prompt, per-engine result (mentioned, cited, position, snippet).

    mcp-tool

    {
      "type": "object",
      "required": [
        "run_id"
      ],
      "properties": {
        "run_id": {
          "type": "integer",
          "minimum": 1,
          "description": "The run_id from run_citation_tracker."
        }
      },
      "additionalProperties": false
    }
    arguments 14 lines
  • usage unknown never probed

    Get the current plan, monthly usage, and remaining quota for the API key in use.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • report_url unknown never probed

    Return the public, shareable HTML report URL for a domain (https://seoscoreapi.com/report/{domain}). Useful for sending results to a client without exposing an API key. Makes no request and uses no quota.

    mcp-tool

    {
      "type": "object",
      "required": [
        "domain"
      ],
      "properties": {
        "domain": {
          "type": "string",
          "examples": [
            "example.com"
          ],
          "maxLength": 253,
          "description": "Bare domain without protocol or path, e.g. example.com."
        }
      },
      "additionalProperties": false
    }
    arguments 17 lines
  • add_monitor unknown never probed

    Add a URL to score monitoring: it is re-audited on a schedule (daily or weekly) and the account owner is emailed when the score drops. Each plan allows a set number of monitors; the error says when the limit is reached.

    mcp-tool

    {
      "type": "object",
      "required": [
        "url"
      ],
      "properties": {
        "url": {
          "type": "string",
          "format": "uri",
          "examples": [
            "https://example.com"
          ],
          "maxLength": 2048,
          "description": "Full page URL including the protocol, e.g. https://example.com/pricing."
        },
        "frequency": {
          "enum": [
            "daily",
            "weekly"
          ],
          "type": "string",
          "default": "daily",
          "description": "How often to re-audit."
        }
      },
      "additionalProperties": false
    }
    arguments 27 lines
  • list_monitors unknown never probed

    List all URLs currently under score monitoring for the active API key.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • citation_topup_checkout unknown never probed

    Create a one-time Stripe Checkout link for a pack of top-up citation checks and return its URL. Paid plans only. This charges nothing: the user must open the link and pay by card, and the checks are added when the payment completes. Get the pack keys and prices from citation_topups first.

    mcp-tool

    {
      "type": "object",
      "required": [
        "pack"
      ],
      "properties": {
        "pack": {
          "type": "string",
          "examples": [
            "500"
          ],
          "description": "A pack `key` from citation_topups (e.g. \"500\")."
        }
      },
      "additionalProperties": false
    }
    arguments 16 lines
  • deep_audit_usage unknown never probed

    Deep Audits used and remaining this calendar month for the API key in use.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • remove_monitor unknown never probed

    Stop score monitoring for a URL. Its past history is kept.

    mcp-tool

    {
      "type": "object",
      "required": [
        "url"
      ],
      "properties": {
        "url": {
          "type": "string",
          "format": "uri",
          "examples": [
            "https://example.com"
          ],
          "maxLength": 2048,
          "description": "Full page URL including the protocol, e.g. https://example.com/pricing."
        }
      },
      "additionalProperties": false
    }
    arguments 18 lines
  • competitive_audit unknown never probed

    Head-to-head SEO comparison of your page against a competitor's page with keyword-relevance scoring. Requires Pro plan ($39/mo) or higher.

    mcp-tool

    {
      "type": "object",
      "required": [
        "url",
        "competitor_url",
        "keyword"
      ],
      "properties": {
        "url": {
          "type": "string",
          "format": "uri",
          "examples": [
            "https://example.com"
          ],
          "maxLength": 2048,
          "description": "Your page's full URL including the protocol, e.g. https://example.com/pricing."
        },
        "keyword": {
          "type": "string",
          "examples": [
            "seo audit api"
          ],
          "maxLength": 200,
          "description": "Target keyword (max 200 characters)."
        },
        "competitor_url": {
          "type": "string",
          "format": "uri",
          "examples": [
            "https://competitor.com"
          ],
          "maxLength": 2048,
          "description": "The competitor page's full URL including the protocol, e.g. https://competitor.com/pricing."
        }
      },
      "additionalProperties": false
    }
    arguments 37 lines
  • ai_readability unknown never probed

    Score how easily AI assistants and LLM search (ChatGPT, Perplexity, Google AI Overviews) can read, quote and cite a page: structure, answer-first content, entities and machine-readable data, with recommendations. Counts as one audit.

    mcp-tool

    {
      "type": "object",
      "required": [
        "url"
      ],
      "properties": {
        "url": {
          "type": "string",
          "format": "uri",
          "examples": [
            "https://example.com"
          ],
          "maxLength": 2048,
          "description": "Full page URL including the protocol, e.g. https://example.com/pricing."
        }
      },
      "additionalProperties": false
    }
    arguments 18 lines
  • quick_wins unknown never probed

    Find the page-2 quick wins in the user's own Google Search Console data: queries ranking 11-20 worth working on first, each with an opportunity score and an estimate of the extra clicks from moving onto page 1. The API does not connect to Search Console: pass the exported rows or the CSV export text. Nothing is stored. The click numbers are estimates. Works on every plan; counts as one audit. Up to 1 MB per request.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "csv": {
          "type": "string",
          "maxLength": 1048576,
          "description": "The Performance export as text, with a header row. Use instead of rows."
        },
        "rows": {
          "type": "array",
          "items": {
            "type": "object"
          },
          "description": "Rows like {query, page, clicks, impressions, position}. `page` is optional."
        },
        "limit": {
          "type": "integer",
          "maximum": 200,
          "minimum": 1,
          "description": "Default 25, max 200."
        },
        "exclude_terms": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Words to leave out, such as the brand name."
        },
        "min_impressions": {
          "type": "integer",
          "minimum": 0,
          "description": "Skip queries with fewer impressions. Default 50."
        },
        "target_position": {
          "type": "integer",
          "maximum": 10,
          "minimum": 1,
          "description": "1-10, default 5."
        }
      },
      "additionalProperties": false
    }
    arguments 42 lines
  • geo_brand_probe unknown never probed

    Probe LLMs to measure how often a brand is mentioned in AI responses. Requires Basic plan ($15/mo) or higher; uses the plan's monthly GEO allowance. Can take a while.

    mcp-tool

    {
      "type": "object",
      "required": [
        "brand",
        "domain",
        "prompts"
      ],
      "properties": {
        "brand": {
          "type": "string",
          "examples": [
            "Acme"
          ],
          "description": "Brand name as people say it, e.g. Acme."
        },
        "domain": {
          "type": "string",
          "examples": [
            "example.com"
          ],
          "maxLength": 253,
          "description": "Bare domain without protocol or path, e.g. example.com."
        },
        "models": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Optional engines to ask, e.g. [\"claude\", \"nova\"]. Default: the server's set."
        },
        "prompts": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Questions to ask, e.g. \"What are the best X?\""
        },
        "runs_per_prompt": {
          "type": "integer",
          "minimum": 1,
          "description": "Default 3."
        }
      },
      "additionalProperties": false
    }
    arguments 45 lines
  • geo_monitor_history unknown never probed

    Score history for one GEO monitor, newest first, paginated.

    mcp-tool

    {
      "type": "object",
      "required": [
        "monitor_id"
      ],
      "properties": {
        "page": {
          "type": "integer",
          "default": 1,
          "minimum": 1,
          "description": "Page number, from 1."
        },
        "per_page": {
          "type": "integer",
          "default": 20,
          "maximum": 100,
          "minimum": 1,
          "description": "1-100."
        },
        "monitor_id": {
          "type": "integer",
          "description": "The monitor's id from list_geo_monitors."
        }
      },
      "additionalProperties": false
    }
    arguments 26 lines
  • remove_geo_monitor unknown never probed

    Stop a GEO monitor by its URL. Past history is kept.

    mcp-tool

    {
      "type": "object",
      "required": [
        "url"
      ],
      "properties": {
        "url": {
          "type": "string",
          "format": "uri",
          "examples": [
            "https://example.com"
          ],
          "maxLength": 2048,
          "description": "Full page URL including the protocol, e.g. https://example.com/pricing."
        }
      },
      "additionalProperties": false
    }
    arguments 18 lines
  • crawl_site unknown never probed

    Crawl one site and wait for the result: follows same-site links plus the sitemap and reports broken pages, redirects, duplicate titles and headings, pages missing a title or heading, orphan pages and slow pages. Pro: 25 pages per crawl, 20 crawls a month. Ultra: 100 pages, 100 crawls a month. Any other plan: one Deep Audit credit covers a 25-page crawl. A failed crawl is not counted. For long waits use start_crawl + get_crawl.

    mcp-tool

    {
      "type": "object",
      "required": [
        "url"
      ],
      "properties": {
        "url": {
          "type": "string",
          "format": "uri",
          "examples": [
            "https://example.com"
          ],
          "maxLength": 2048,
          "description": "Full page URL including the protocol, e.g. https://example.com/pricing."
        },
        "max_pages": {
          "type": "integer",
          "maximum": 100,
          "minimum": 1,
          "description": "Fewer pages than the plan's cap (1-100)."
        },
        "timeout_seconds": {
          "type": "integer",
          "default": 600,
          "maximum": 3600,
          "minimum": 10,
          "description": "How long to wait before giving up (the crawl keeps running)."
        }
      },
      "additionalProperties": false
    }
    arguments 31 lines
  • start_crawl unknown never probed

    Start a site crawl and return immediately with a job_id and a shareable site_map link. Poll it with get_crawl. Same plans as crawl_site.

    mcp-tool

    {
      "type": "object",
      "required": [
        "url"
      ],
      "properties": {
        "url": {
          "type": "string",
          "format": "uri",
          "examples": [
            "https://example.com"
          ],
          "maxLength": 2048,
          "description": "Full page URL including the protocol, e.g. https://example.com/pricing."
        },
        "max_pages": {
          "type": "integer",
          "maximum": 100,
          "minimum": 1,
          "description": "Fewer pages than the plan's cap (1-100)."
        }
      },
      "additionalProperties": false
    }
    arguments 24 lines
  • get_crawl unknown never probed

    Get a site crawl's status: queued, running (pages_done counts up), completed (result: summary, issues, pages, links) or failed (error). Only the key that started a crawl can read it.

    mcp-tool

    {
      "type": "object",
      "required": [
        "job_id"
      ],
      "properties": {
        "job_id": {
          "type": "string",
          "maxLength": 64,
          "description": "The job_id from start_crawl."
        }
      },
      "additionalProperties": false
    }
    arguments 14 lines
  • citation_suggest_prompts unknown never probed

    Suggest AI-citation prompts to track, read off what a site says it does (fetches the site's pages). Use the result with create_citation_tracker.

    mcp-tool

    {
      "type": "object",
      "required": [
        "domain"
      ],
      "properties": {
        "domain": {
          "type": "string",
          "examples": [
            "example.com"
          ],
          "maxLength": 253,
          "description": "Bare domain without protocol or path, e.g. example.com."
        }
      },
      "additionalProperties": false
    }
    arguments 17 lines
  • list_citation_trackers unknown never probed

    List the key's citation trackers plus `usage`: the month's checks (limit, used, remaining), the top-up balance and checks_available (what a run can spend now).

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • get_citation_tracker unknown never probed

    Read one citation tracker: brand, domains, prompts, engines, competitors, cadence and webhook.

    mcp-tool

    {
      "type": "object",
      "required": [
        "tracker_id"
      ],
      "properties": {
        "tracker_id": {
          "type": "integer",
          "minimum": 1,
          "examples": [
            12
          ],
          "description": "The tracker's id from list_citation_trackers or create_citation_tracker."
        }
      },
      "additionalProperties": false
    }
    arguments 17 lines
  • update_citation_tracker unknown never probed

    Edit a citation tracker's prompts, engines, competitors, samples, cadence or webhook. Only the fields passed change.

    mcp-tool

    {
      "type": "object",
      "required": [
        "tracker_id"
      ],
      "properties": {
        "cadence": {
          "enum": [
            "daily",
            "weekly",
            "monthly",
            "manual"
          ],
          "type": "string",
          "description": "daily, weekly, monthly or manual."
        },
        "engines": {
          "type": "array",
          "items": {
            "enum": [
              "gpt",
              "gemini",
              "perplexity",
              "claude",
              "nova",
              "chatgpt"
            ],
            "type": "string"
          },
          "description": "Default: gpt, gemini, perplexity, claude. gpt answers from the model's own knowledge (no browsing); chatgpt is the web-search product and needs an OpenAI key on the server."
        },
        "prompts": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Replaces the tracked prompts."
        },
        "samples": {
          "type": "integer",
          "minimum": 1,
          "description": "Samples per prompt per engine."
        },
        "tracker_id": {
          "type": "integer",
          "minimum": 1,
          "examples": [
            12
          ],
          "description": "The tracker's id from list_citation_trackers or create_citation_tracker."
        },
        "competitors": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Replaces the competitor list."
        },
        "webhook_url": {
          "type": "string",
          "description": "https URL POSTed after each run."
        }
      },
      "additionalProperties": false
    }
    arguments 65 lines
  • delete_citation_tracker unknown never probed

    Stop tracking a brand. Run history is kept until its retention expires.

    mcp-tool

    {
      "type": "object",
      "required": [
        "tracker_id"
      ],
      "properties": {
        "tracker_id": {
          "type": "integer",
          "minimum": 1,
          "examples": [
            12
          ],
          "description": "The tracker's id from list_citation_trackers or create_citation_tracker."
        }
      },
      "additionalProperties": false
    }
    arguments 17 lines
  • citation_starter_prompts unknown never probed

    Build a starter set of prompts to track for AI citations, from a topic plus optional brand, competitors and audience. Fixed templates, not a model: no AI check is spent. Works on every plan and is not metered. Returns `prompts`, ready to pass to create_citation_tracker.

    mcp-tool

    {
      "type": "object",
      "required": [
        "topic"
      ],
      "properties": {
        "brand": {
          "type": "string",
          "description": "Your brand name (optional)."
        },
        "limit": {
          "type": "integer",
          "maximum": 60,
          "minimum": 1,
          "description": "Cut the list to this many (1-60)."
        },
        "topic": {
          "type": "string",
          "examples": [
            "SEO audit API"
          ],
          "description": "What you sell, as a buyer would type it, singular (e.g. \"SEO audit API\")."
        },
        "audience": {
          "type": "string",
          "description": "Who buys it, plural (e.g. \"marketing agencies\")."
        },
        "features": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Up to 6 features buyers ask about."
        },
        "use_cases": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Up to 6 jobs it is bought for."
        },
        "competitors": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Up to 5 competitor names."
        },
        "per_category": {
          "type": "integer",
          "maximum": 10,
          "minimum": 1,
          "description": "Prompts per category, 1-10 (default 2 = 12 prompts)."
        }
      },
      "additionalProperties": false
    }
    arguments 57 lines
  • citation_topups unknown never probed

    Top-up packs for AI citation checks (`packs` is the live list with prices) and this account's balance. Top-up checks are spent only after the plan's monthly allowance, do not reset on the 1st, and expire 12 months after purchase. `can_buy` is false on the free tier.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • citation_auto_reload unknown never probed

    Read the auto-reload setting for AI citation checks and this month's reloads and charges. Read-only: auto-reload is off unless the account owner turns it on, and it can only be turned on or changed from the dashboard (signed in), never through the API or this server, because turning it on authorizes charges.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • audit unknown never probed

    Run a full SEO audit on a URL. Returns score (0-100), letter grade, category breakdowns (meta, technical, social, performance, accessibility), compliance risk signals scored separately from SEO (third-party fonts, session recording without a consent tool, subscription terms, privacy/terms links, email-form privacy links, copyright policy; not legal advice), AI readability score, SXO/AEO/AIO scores (paid plans), and a prioritized list of fixes. Usually returns in seconds. Free tier: 20 audits a month. Core Web Vitals (LCP, INP, CLS) are not measured unless include_core_web_vitals is true.

    mcp-tool

    {
      "type": "object",
      "required": [
        "url"
      ],
      "properties": {
        "url": {
          "type": "string",
          "format": "uri",
          "examples": [
            "https://example.com"
          ],
          "maxLength": 2048,
          "description": "The URL to audit. Must include the protocol (https://...)."
        },
        "include_core_web_vitals": {
          "type": "boolean",
          "default": false,
          "description": "Also measure Core Web Vitals (LCP, INP, CLS, FCP, TTFB) with Google PageSpeed Insights and return them under core_web_vitals. Adds about 10 seconds the first time a URL is measured (cached 24 hours). Needs an API key. Leave off unless the user asks about page speed or Core Web Vitals."
        }
      },
      "additionalProperties": false
    }
    arguments 23 lines
  • batch_audit unknown never probed

    Audit multiple URLs in one call. Requires Starter plan ($9/mo) or higher. Returns one audit object per URL.

    mcp-tool

    {
      "type": "object",
      "required": [
        "urls"
      ],
      "properties": {
        "urls": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "maxItems": 10,
          "minItems": 1,
          "description": "URLs to audit (1–10)."
        },
        "include_core_web_vitals": {
          "type": "boolean",
          "default": false,
          "description": "Also measure Core Web Vitals for every URL. Slower: the batch can take a few minutes."
        }
      },
      "additionalProperties": false
    }
    arguments 23 lines
  • history unknown never probed

    Fetch the audit-score history for a URL. Returns a time-series of past scores so you can see trends. Requires Starter plan ($9/mo) or higher.

    mcp-tool

    {
      "type": "object",
      "required": [
        "url"
      ],
      "properties": {
        "url": {
          "type": "string",
          "format": "uri",
          "examples": [
            "https://example.com"
          ],
          "maxLength": 2048,
          "description": "Full page URL including the protocol, e.g. https://example.com/pricing."
        },
        "limit": {
          "type": "integer",
          "default": 100,
          "maximum": 1000,
          "minimum": 1,
          "description": "Max points to return (1-1000)."
        }
      },
      "additionalProperties": false
    }
    arguments 25 lines
  • backlinks unknown never probed

    Look up observed backlinks for a domain. SEO Score API maintains an audit-fed backlink graph: every audit contributes the external links found on the audited page. The dataset is a sample (NOT a comprehensive backlink index like Ahrefs) and the response always includes a data_caveat. Coverage grows over time. Requires Basic plan ($15/mo) or higher.

    mcp-tool

    {
      "type": "object",
      "required": [
        "domain"
      ],
      "properties": {
        "limit": {
          "type": "integer",
          "default": 50,
          "maximum": 500,
          "minimum": 1,
          "description": "Max sample rows to return (1-500)"
        },
        "domain": {
          "type": "string",
          "examples": [
            "example.com"
          ],
          "maxLength": 253,
          "description": "Bare domain without protocol or path, e.g. example.com."
        }
      },
      "additionalProperties": false
    }
    arguments 24 lines
  • deep_audit unknown never probed

    Run a Deep Audit — a thorough, AI-assisted SEO audit that scores a URL across 9 dimensions (technical, crawlability, content/entity, Core Web Vitals, technical SEO, structured data, security, media, off-site): thousands of catalog checks plus up to 150 AI checks. Runs asynchronously server-side; this tool waits for the result (about 90 seconds once it starts, longer if queued). Included on Pro ($39/mo, 20/month) and Ultra ($99/mo, 100/month); other keys spend a purchased Deep Audit credit. For long waits use start_deep_audit + get_deep_audit instead.

    mcp-tool

    {
      "type": "object",
      "required": [
        "url"
      ],
      "properties": {
        "url": {
          "type": "string",
          "format": "uri",
          "examples": [
            "https://example.com"
          ],
          "maxLength": 2048,
          "description": "URL to audit. Must include the protocol (https://...)."
        },
        "business_type": {
          "enum": [
            "saas",
            "local_service",
            "ecommerce",
            "storefront",
            "blog",
            "publisher"
          ],
          "type": "string",
          "description": "Optional. Tunes which checks apply; worked out from the page when omitted."
        },
        "timeout_seconds": {
          "type": "integer",
          "default": 600,
          "maximum": 3600,
          "minimum": 10,
          "description": "How long to wait before giving up (job keeps running)."
        }
      },
      "additionalProperties": false
    }
    arguments 37 lines
  • start_deep_audit unknown never probed

    Queue a Deep Audit and return immediately with a job_id. Poll it with get_deep_audit. Same plans as deep_audit.

    mcp-tool

    {
      "type": "object",
      "required": [
        "url"
      ],
      "properties": {
        "url": {
          "type": "string",
          "format": "uri",
          "examples": [
            "https://example.com"
          ],
          "maxLength": 2048,
          "description": "URL to audit. Must include the protocol (https://...)."
        },
        "webhook_url": {
          "type": "string",
          "format": "uri",
          "description": "Optional public URL POSTed once when the job completes."
        },
        "business_type": {
          "enum": [
            "saas",
            "local_service",
            "ecommerce",
            "storefront",
            "blog",
            "publisher"
          ],
          "type": "string",
          "description": "Optional. Tunes which checks apply; worked out from the page when omitted."
        }
      },
      "additionalProperties": false
    }
    arguments 35 lines
  • get_deep_audit unknown never probed

    Get a Deep Audit job's status: queued (queue_position, eta_seconds), running (progress 0-100, stage), completed (result) or failed (error). Poll every 5-10 seconds.

    mcp-tool

    {
      "type": "object",
      "required": [
        "job_id"
      ],
      "properties": {
        "job_id": {
          "type": "string",
          "maxLength": 64,
          "description": "The job_id from start_deep_audit."
        }
      },
      "additionalProperties": false
    }
    arguments 14 lines
  • compare unknown never probed

    Compare 2-5 URLs side by side with a structured diff: each URL's score and category breakdown plus who is ahead and by how much, per category and per URL pair. Requires Basic plan ($15/mo) or higher.

    mcp-tool

    {
      "type": "object",
      "required": [
        "urls"
      ],
      "properties": {
        "urls": {
          "type": "array",
          "items": {
            "type": "string",
            "format": "uri"
          },
          "maxItems": 5,
          "minItems": 2,
          "description": "2 to 5 URLs."
        }
      },
      "additionalProperties": false
    }
    arguments 19 lines
  • accessibility_audit unknown never probed

    Run an ADA / WCAG 2.1 AA accessibility audit (axe-core). Paid plans only. Returns the compliance score and grade, lawsuit risk (high/medium/low/minimal), category breakdowns, violations (WCAG 2.1 AA failures with affected elements and a plain-English fix), best_practices (not WCAG requirements; they never lower the score), needs_review and priorities. ADA audits have their own monthly allowance, separate from the audit quota (the usage tool reports ada_remaining). Each key may run 2 at a time; a 429 is not counted.

    mcp-tool

    {
      "type": "object",
      "required": [
        "url"
      ],
      "properties": {
        "url": {
          "type": "string",
          "format": "uri",
          "examples": [
            "https://example.com"
          ],
          "maxLength": 2048,
          "description": "The URL to audit. Must include the protocol (https://...)."
        },
        "include_trackers": {
          "type": "boolean",
          "description": "Also add the tracker and pixel inventory to the report."
        }
      },
      "additionalProperties": false
    }
    arguments 22 lines
  • trackers unknown never probed

    List the third-party trackers and pixels a page loads (analytics, advertising, session replay, chat, marketing automation, A/B testing, monitoring), including pixels a tag manager injects. Loads the page in a real browser with no interaction; it does not determine whether a tracker waited for consent, and it is not legal advice. Counts as one audit; a page that can't be loaded is not counted.

    mcp-tool

    {
      "type": "object",
      "required": [
        "url"
      ],
      "properties": {
        "url": {
          "type": "string",
          "format": "uri",
          "examples": [
            "https://example.com"
          ],
          "maxLength": 2048,
          "description": "Full page URL including the protocol, e.g. https://example.com/pricing."
        }
      },
      "additionalProperties": false
    }
    arguments 18 lines
  • conversion unknown never probed

    Score how well a page turns a visitor into a lead or a sale: headline, call to action, trust, forms and objections, each 0-100, with a prioritized fix list. It does not measure the actual conversion rate. Counts as one audit. Free keys get the scores and the first two priorities; paid plans get the full list.

    mcp-tool

    {
      "type": "object",
      "required": [
        "url"
      ],
      "properties": {
        "url": {
          "type": "string",
          "format": "uri",
          "examples": [
            "https://example.com"
          ],
          "maxLength": 2048,
          "description": "Full page URL including the protocol, e.g. https://example.com/pricing."
        },
        "page_type": {
          "enum": [
            "local_service",
            "ecommerce",
            "saas",
            "general"
          ],
          "type": "string",
          "description": "Detected from the page when omitted."
        }
      },
      "additionalProperties": false
    }
    arguments 28 lines
  • agent_view unknown never probed

    Check whether AI agents receive the same page a browser does. Fetches the page as a browser and as ChatGPT-User, GPTBot, PerplexityBot and ClaudeBot (each with its published user agent) and reports per agent the HTTP status, whether it was blocked or challenged (401/403/429, a bot-check page, a robots.txt disallow), the words it received, how much of the browser's text that is, and whether the content only appears after JavaScript runs, with a verdict and a prioritized fix list. The requests come from SEO Score API's server, not the AI companies, so a block is a strong signal to confirm in the site's logs, not proof. Paid plans; counts as one audit; a page a browser can't load is not counted.

    mcp-tool

    {
      "type": "object",
      "required": [
        "url"
      ],
      "properties": {
        "url": {
          "type": "string",
          "format": "uri",
          "examples": [
            "https://example.com"
          ],
          "maxLength": 2048,
          "description": "Full page URL including the protocol, e.g. https://example.com/pricing."
        }
      },
      "additionalProperties": false
    }
    arguments 18 lines
  • llms_txt unknown never probed

    Generate an llms.txt file for a domain and return its text, ready to save at /llms.txt. Basic plan ($15/mo) and higher get the curated version with per-page descriptions; other keys (or no key) get the basic version.

    mcp-tool

    {
      "type": "object",
      "required": [
        "domain"
      ],
      "properties": {
        "domain": {
          "type": "string",
          "examples": [
            "example.com"
          ],
          "maxLength": 253,
          "description": "Bare domain without protocol or path, e.g. example.com."
        }
      },
      "additionalProperties": false
    }
    arguments 17 lines
  • geo_audit unknown never probed

    Run a GEO (Generative Engine Optimization) audit: 26 checks measuring how visible a page is to LLMs. Requires Basic plan ($15/mo) or higher; uses the plan's monthly GEO allowance.

    mcp-tool

    {
      "type": "object",
      "required": [
        "url"
      ],
      "properties": {
        "url": {
          "type": "string",
          "format": "uri",
          "examples": [
            "https://example.com"
          ],
          "maxLength": 2048,
          "description": "Full page URL including the protocol, e.g. https://example.com/pricing."
        }
      },
      "additionalProperties": false
    }
    arguments 18 lines
  • add_geo_monitor unknown never probed

    Create a GEO monitor for a URL. Requires Basic plan or higher (the Basic plan runs weekly).

    mcp-tool

    {
      "type": "object",
      "required": [
        "url"
      ],
      "properties": {
        "url": {
          "type": "string",
          "format": "uri",
          "examples": [
            "https://example.com"
          ],
          "maxLength": 2048,
          "description": "Full page URL including the protocol, e.g. https://example.com/pricing."
        },
        "frequency": {
          "enum": [
            "daily",
            "weekly"
          ],
          "type": "string",
          "default": "weekly",
          "description": "How often to re-run (Basic runs weekly)."
        },
        "webhook_url": {
          "type": "string",
          "format": "uri",
          "description": "Optional https URL to POST alerts to."
        },
        "alert_threshold": {
          "type": "integer",
          "default": -5,
          "description": "Alert when the score moves by this many points or more (negative = drop)."
        }
      },
      "additionalProperties": false
    }
    arguments 37 lines
  • list_geo_monitors unknown never probed

    List the active GEO monitors for the API key in use.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • create_citation_tracker unknown never probed

    Track a brand's visibility in AI answers (ChatGPT, Gemini, Perplexity, Claude): mention rate, citation rate, share of voice and position over time. Requires Starter ($9/mo) or higher. Monthly allowance (checks / tracked prompts): Starter 150 / 15, Basic 500 / 30, Pro 1,500 / 75, Ultra 4,000 / 200. A check is one prompt on one engine, sampled once. With no prompts, pass `starter` and a starter set is generated to fit the plan.

    mcp-tool

    {
      "type": "object",
      "required": [
        "brand"
      ],
      "properties": {
        "brand": {
          "type": "string",
          "examples": [
            "Acme"
          ],
          "description": "Brand to track, e.g. Acme."
        },
        "cadence": {
          "enum": [
            "daily",
            "weekly",
            "monthly",
            "manual"
          ],
          "type": "string",
          "description": "How often it runs automatically; manual = only when run_citation_tracker is called."
        },
        "domains": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "The brand's domains (e.g. [\"acme.com\"])."
        },
        "engines": {
          "type": "array",
          "items": {
            "enum": [
              "gpt",
              "gemini",
              "perplexity",
              "claude",
              "nova",
              "chatgpt"
            ],
            "type": "string"
          },
          "description": "Default: gpt, gemini, perplexity, claude. gpt answers from the model's own knowledge (no browsing); chatgpt is the web-search product and needs an OpenAI key on the server."
        },
        "prompts": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "The questions buyers type."
        },
        "samples": {
          "type": "integer",
          "minimum": 1,
          "description": "Samples per prompt per engine (each is one check)."
        },
        "starter": {
          "type": "object",
          "properties": {
            "topic": {
              "type": "string"
            },
            "audience": {
              "type": "string"
            }
          },
          "description": "Use instead of prompts: {topic, audience?}."
        },
        "competitors": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Competitor brand names to compare share of voice against."
        },
        "webhook_url": {
          "type": "string",
          "format": "uri",
          "description": "https URL."
        }
      },
      "additionalProperties": false
    }
    arguments 84 lines
  • run_citation_tracker unknown never probed

    Run a citation tracker now. Every prompt x engine x sample counts as one check. A run needs all of its checks up front (the month's remaining allowance plus any top-up balance); if that is short the run is refused and nothing is spent. A check whose engine returned an error is not counted. A run that takes over 45 seconds returns {run_id, status: "running", poll} instead of the summary; it keeps running, so call get_citation_run with that run_id until status is completed.

    mcp-tool

    {
      "type": "object",
      "required": [
        "tracker_id"
      ],
      "properties": {
        "tracker_id": {
          "type": "integer",
          "minimum": 1,
          "examples": [
            12
          ],
          "description": "The tracker's id from list_citation_trackers or create_citation_tracker."
        }
      },
      "additionalProperties": false
    }
    arguments 17 lines
  • citation_tracker_history unknown never probed

    Timeseries of mention rate, citation rate, share of voice and average position for a citation tracker. Pass change_date (the day a change went live) to also get before_after: the runs completed runs before that date compared with the first runs on or after it, overall and per engine, with the counts behind every rate. comparable is false, and summary says so, when either side has fewer than 2 runs.

    mcp-tool

    {
      "type": "object",
      "required": [
        "tracker_id"
      ],
      "properties": {
        "days": {
          "type": "integer",
          "default": 90,
          "maximum": 365,
          "minimum": 1,
          "description": "1-365."
        },
        "runs": {
          "type": "integer",
          "default": 4,
          "maximum": 26,
          "minimum": 1,
          "description": "Completed runs on each side of change_date."
        },
        "tracker_id": {
          "type": "integer",
          "minimum": 1,
          "examples": [
            12
          ],
          "description": "The tracker's id from list_citation_trackers or create_citation_tracker."
        },
        "change_date": {
          "type": "string",
          "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
          "examples": [
            "2026-11-03"
          ],
          "description": "YYYY-MM-DD (UTC), the day the change went live. A run that starts that day counts as after."
        }
      },
      "additionalProperties": false
    }
    arguments 39 lines
  • citation_check unknown never probed

    One-off AI citation check for a brand and one prompt: no tracker, metered per check (one check per engine per sample). Paid plans only (Starter and up).

    mcp-tool

    {
      "type": "object",
      "required": [
        "brand",
        "prompt"
      ],
      "properties": {
        "brand": {
          "type": "string",
          "description": "Brand to look for in the answers, e.g. Acme."
        },
        "prompt": {
          "type": "string",
          "examples": [
            "What is the best SEO audit API?"
          ],
          "maxLength": 500,
          "description": "The question a buyer would ask an AI assistant."
        },
        "domains": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "The brand's domains, to count citations of them."
        },
        "engines": {
          "type": "array",
          "items": {
            "enum": [
              "gpt",
              "gemini",
              "perplexity",
              "claude",
              "nova",
              "chatgpt"
            ],
            "type": "string"
          },
          "description": "Default: gpt, gemini, perplexity, claude. gpt answers from the model's own knowledge (no browsing); chatgpt is the web-search product and needs an OpenAI key on the server."
        },
        "samples": {
          "type": "integer",
          "description": "Default 1."
        },
        "competitors": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Competitor names to compare against."
        }
      },
      "additionalProperties": false
    }
    arguments 55 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 44e3d41785e91739.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/44e3d41785e91739/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/44e3d41785e91739/badge.svg)](https://brick.blue/agent/44e3d41785e91739?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.