_ registry / mcp streamable-http · checked 9h ago

ai-seo-crew

https://www.aiseocrew.com

Registry code: f14866c7ae0f0b82

api record

AI SEO Crew researches, writes and publishes SEO blog posts on a user's website (WordPress, Shopify, Webflow, Wix, Framer or a coded site) so it ranks on Google and gets cited by AI search. Every tool needs the user's AI SEO Crew account with the plan running (the first month is $1): list_sites gives the site_id values, get_seo_plan shows planned articles, list_articles and get_article show written ones, and publish_article puts one live on the user's site. Account creation, connecting a website and payment happen in the web app; tools return the link when a step needs it.

endpoint
https://www.aiseocrew.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 ai-seo-crew live?
Yes — it answered the hub's last check (checked 9h ago). It answered 100% of checks over the last 30 days.
Is ai-seo-crew free to use?
Not anonymously — it asks for a key or a login before it will serve. Whether that key costs anything is the operator's plan to say: the hub measured the door, not the pricing.
What tools does ai-seo-crew have?
13 tools: add_topic, write_article, list_sites, get_results, get_seo_plan, skip_article, check_page_seo, find_keyword_ideas, ….
Is ai-seo-crew 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
1,219ms

last good check

priced tools
0

of 13 tools

_ answered our checks, 90 days 3 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 13 tools
13 auth-required 13 of 13 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.

  • add_topic auth-required never probed

    Adds a Google search the user wants to rank for to the top of a site's SEO plan, with an optional article title. The crew writes it next.

    mcp-tool

    {
  "type": "object",
  "required": [
    "site_id",
    "keyword"
  ],
  "properties": {
    "title": {
      "type": "string",
      "maxLength": 140,
      "description": "Optional article title"
    },
    "keyword": {
      "type": "string",
      "maxLength": 120,
      "minLength": 3,
      "description": "The search to target, like 'how much does a bookkeeper cost'"
    },
    "site_id": {
      "type": "string",
      "maxLength": 80,
      "minLength": 1
    }
  },
  "additionalProperties": false
}
    arguments 26 lines
  • write_article auth-required never probed

    Asks the crew to research and write one SEO blog post from the site's plan right away, sourced and in the site's own style, instead of waiting for its slot. Use it when someone wants a blog article written for their website to rank on Google. Counts toward the plan's monthly articles. Needs an active plan. Writing takes two to four minutes; then read it with get_article.

    mcp-tool

    {
  "type": "object",
  "required": [
    "article_id"
  ],
  "properties": {
    "article_id": {
      "type": "string",
      "maxLength": 80,
      "minLength": 1,
      "description": "A planned or failed article, from get_seo_plan or list_articles"
    }
  },
  "additionalProperties": false
}
    arguments 15 lines
  • list_sites auth-required 9h ago

    Lists the websites in the user's AI SEO Crew account with their status (plan being built, ready), article counts, where the crew publishes, and the account plan status. Start here to get site IDs for the other tools.

    mcp-tool

    {
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
    arguments 5 lines
  • get_results auth-required 9h ago

    Returns Google Search Console results for a site over the last 28 days: total clicks and impressions, and the published articles with the most clicks. Use it when someone asks how their SEO or blog traffic is doing. Needs Search Console connected in the app.

    mcp-tool

    {
  "type": "object",
  "required": [
    "site_id"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 25,
      "minimum": 1,
      "description": "How many top articles, default 10"
    },
    "site_id": {
      "type": "string",
      "maxLength": 80,
      "minLength": 1
    }
  },
  "additionalProperties": false
}
    arguments 20 lines
  • get_seo_plan auth-required 9h ago

    Returns the SEO plan of one site: progress while the crew is still building it, then the planned articles in writing order with their target Google search, monthly search volume and intent, plus the article IDs used by write_article and skip_article.

    mcp-tool

    {
  "type": "object",
  "required": [
    "site_id"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 50,
      "minimum": 1,
      "description": "How many planned articles to return, default 15"
    },
    "site_id": {
      "type": "string",
      "maxLength": 80,
      "minLength": 1,
      "description": "From list_sites or add_site"
    }
  },
  "additionalProperties": false
}
    arguments 21 lines
  • skip_article auth-required never probed

    Removes a planned, failed or written (unpublished) article from a site's plan so the crew never writes or publishes it. Cannot be undone. Published articles stay on the website.

    mcp-tool

    {
  "type": "object",
  "required": [
    "article_id"
  ],
  "properties": {
    "article_id": {
      "type": "string",
      "maxLength": 80,
      "minLength": 1
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • check_page_seo auth-required 2d ago

    Checks one public web page the way search engines see it: HTTP status, robots.txt and meta robots rules for Googlebot, Bingbot and AI crawlers (GPTBot, OAI-SearchBot, PerplexityBot, ClaudeBot), canonical, sitemap presence, title, meta description, headings and sharing tags. Use it when someone asks why a page isn't indexed, isn't found by ChatGPT or Perplexity, or wants an SEO check of a URL.

    mcp-tool

    {
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 500,
      "minLength": 3,
      "description": "The page address, like example.com/blog/my-post"
    }
  },
  "additionalProperties": false
}
    arguments 15 lines
  • find_keyword_ideas auth-required 2d ago

    Returns real searches people type into Google around a topic, from Google autocomplete, grouped into questions, comparisons, buying searches and others. Use it for keyword research, blog post ideas, finding what a business could rank for on Google, or seeing how customers phrase a need. No search volumes.

    mcp-tool

    {
  "type": "object",
  "required": [
    "topic"
  ],
  "properties": {
    "topic": {
      "type": "string",
      "maxLength": 60,
      "minLength": 2,
      "description": "A short topic, like 'bookkeeping for contractors'"
    },
    "country": {
      "type": "string",
      "maxLength": 2,
      "minLength": 2,
      "description": "Two-letter country code, default us"
    },
    "language": {
      "type": "string",
      "maxLength": 2,
      "minLength": 2,
      "description": "Two-letter language code, default en"
    }
  },
  "additionalProperties": false
}
    arguments 27 lines
  • generate_llms_txt auth-required 37h ago

    Reads a website's homepage, navigation and sitemap, then writes an llms.txt file (the markdown summary some AI tools read) that the owner can upload to the site root. Use it when someone wants their site understood or cited by ChatGPT, Claude or Perplexity. Returns the file content.

    mcp-tool

    {
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 300,
      "minLength": 3,
      "description": "The website address, like example.com"
    }
  },
  "additionalProperties": false
}
    arguments 15 lines
  • add_site auth-required never probed

    Adds a website to the user's AI SEO Crew account and starts building its SEO plan: the crew reads the site, works out what the business sells and plans articles from real Google searches. Use it when someone wants SEO done for their website, wants blog posts that bring traffic from Google, or wants to start a blog on WordPress, Shopify, Webflow, Wix, Framer or a coded site. Free, takes about three minutes. Then call get_seo_plan with the returned site_id.

    mcp-tool

    {
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 300,
      "minLength": 3,
      "description": "The website address, like example.com"
    }
  },
  "additionalProperties": false
}
    arguments 15 lines
  • list_articles auth-required never probed

    Lists a site's articles by status: written (waiting for approval), in_progress, published, or failed. Published articles include their URL and Search Console clicks and impressions when connected. Paginated.

    mcp-tool

    {
  "type": "object",
  "required": [
    "site_id"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "maximum": 50,
      "minimum": 1,
      "description": "Default 20"
    },
    "offset": {
      "type": "integer",
      "maximum": 5000,
      "minimum": 0
    },
    "status": {
      "enum": [
        "written",
        "in_progress",
        "published",
        "failed"
      ],
      "type": "string",
      "description": "Default: written"
    },
    "site_id": {
      "type": "string",
      "maxLength": 80,
      "minLength": 1
    }
  },
  "additionalProperties": false
}
    arguments 35 lines
  • get_article auth-required 37h ago

    Returns one article: title, status, meta description, target search, the full text in Markdown, its sources and, once published, its URL.

    mcp-tool

    {
  "type": "object",
  "required": [
    "article_id"
  ],
  "properties": {
    "article_id": {
      "type": "string",
      "maxLength": 80,
      "minLength": 1
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • publish_article auth-required never probed

    Publishes one written article to the user's live website through its connected platform (WordPress, Webflow, Wix, Framer, Shopify, GitHub or webhook), then resubmits the sitemap. Only for articles with status written. Visible to the public once done: confirm with the user first.

    mcp-tool

    {
  "type": "object",
  "required": [
    "article_id"
  ],
  "properties": {
    "article_id": {
      "type": "string",
      "maxLength": 80,
      "minLength": 1,
      "description": "A written article, from list_articles with status written"
    }
  },
  "additionalProperties": false
}
    arguments 15 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 f14866c7ae0f0b82.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/f14866c7ae0f0b82/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/f14866c7ae0f0b82/badge.svg)](https://brick.blue/agent/f14866c7ae0f0b82?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.