SEOcrawl AI MCP
Your Search Console and SEO tasks, inside your AI assistant.
Twelve MCP tools, one connector. Pull live Search Console performance, drill into a single keyword or page, and create or close SEO tasks — all from a chat. Built on the open Model Context Protocol, so it works with Claude, ChatGPT, Cursor and Claude Code out of the box.
Show the top 6 keywords for seocrawl.ai over the last 28 days, sorted by clicks, with the change vs the previous 28 days.
Here are the top 6 queries from your seocrawl.ai property, ranked by clicks. Δ shows the period-over-period change.
Want me to pull the daily trend for the ‘geo optimization’ query, or open a task to expand the page that ranks for it?
SEOcrawl AI MCP Use Cases
Five real conversations you can have today. Each one maps to the actual MCP tools listed below — no hand-waving, no copy-paste, no exports.
get_gsc_summary · compare_date_rangesPeriod-over-Period Recap
Get your weekly Search Console recap in one chat. Skip the manual export — ask for last 28 days vs the 28 before, and your assistant pulls the four headline metrics with diff and change_pct already calculated.
Example prompt
“Compare seocrawl.ai performance for the last 28 days vs the previous 28 — clicks, impressions, CTR and average position.”
Compare seocrawl.ai performance for the last 28 days vs the previous 28 — clicks, impressions, CTR and average position.
Here's the comparison for seocrawl.ai (period A: 2026-04-30 → 2026-05-27, period B: 2026-04-02 → 2026-04-29):
Clicks +14% and position improved by 0.8 spots — want me to break that down by top page?
get_top_pages · get_page_detailGrowing and Declining Pages
See which pages move the needle, and which just dropped. Ask for top pages with period-over-period and your assistant ranks them by clicks, flags the losers, and offers to fetch the daily breakdown for any URL you call out.
Example prompt
“Top 5 pages by clicks on seocrawl.ai this last 28 days, and which ones dropped vs the previous 28.”
Top 5 pages by clicks on seocrawl.ai this last 28 days, and which ones dropped vs the previous 28.
Top 5 pages by clicks (last 28 days), with the period-over-period delta:
/seo-tools/rank-tracker3,240+22%/blog/generative-engine-optimization2,815+148%/seo-tools/seo-dashboard1,902+9%/blog/technical-seo1,184-38%/free-seo-tools/schema-validator905-12%Two pages dropping — /blog/technical-seo is the biggest loser. Want the daily breakdown for that URL?
get_keyword_detailKeyword Deep Dive
Zoom into a single keyword’s day-by-day trend. Once you’ve spotted a query worth investigating, pull its daily time series — useful for catching the exact day a position shift happened or correlating with a Google update.
Example prompt
“Show me the daily trend for 'geo optimization' on seocrawl.ai for the last 28 days — clicks, impressions and position.”
Show me the daily trend for 'geo optimization' on seocrawl.ai for the last 28 days — clicks, impressions and position.
Daily breakdown for the query ‘geo optimization’ over the last 28 days. Bars are scaled to peak clicks:
Total clicks
904
Avg. CTR
6.1%
Avg. position
4.8 ↑ 2.1
Position jumped 2.1 spots on the 17th. Want me to open a task to update the page that ranks for it?
create_taskFrom Insight to Action
Spin up an SEO task without leaving the chat. When the data points to action, your assistant creates it right there — title, description, assignee, priority (1–5) and taskbox, all in one call.
Example prompt
“Create a task to update the meta title on /blog/technical-seo. Priority 2, assigned to me, description should mention the -38% click drop.”
Create a task to update the meta title on /blog/technical-seo. Priority 2, assigned to me, description should mention the -38% click drop.
Task created on the seocrawl.ai property:
technical-seo-meta-fix-4a2cDone. Want me to also add a checklist comment with the meta-title hypotheses?
list_tasks · update_task · add_commentOne-Chat Task Triage
Triage your open SEO tasks in a single chain. Your assistant lists what’s open, changes status on any one of them, and appends a comment with what was done — three MCP calls, one natural-language request.
Example prompt
“List my open tasks on seocrawl.ai, mark 'Update meta title on /blog/technical-seo' as Done, and add a comment with the new title.”
List my open tasks on seocrawl.ai, mark 'Update meta title on /blog/technical-seo' as Done, and add a comment with the new title.
3 open tasks assigned to you. I'll close the meta-title one and leave a note:
Comment added
“Title updated to ‘Technical SEO checklist for 2026 — 14 fixes that actually move rankings’. Will re-check clicks in 14 days.”
1 task closed, 2 still open. Want a summary email of the 2 remaining ones for the team?
Every tool in the connector
12 tools across 5 groups. Names below match the real MCP tool IDs so you (or your assistant) can call them directly.
Properties
1 toolDiscover which Search Console properties (projects) are connected to the account before any other query.
list_propertiesList every GSC property the authenticated user can access. Returns the property ID (UUID) and URL (sc-domain:…) you pass to all other tools.
Performance overview
2 toolsHigh-level Search Console performance for any property, plus apples-to-apples comparison between two date windows.
get_gsc_summaryClicks, impressions, CTR and average position for a property over a chosen window. Accepts presets (last_7_days, last_28_days, last_3_months, last_year) or absolute from/to dates.
compare_date_rangesCompare two GSC windows side by side and get diff + change_pct for clicks, impressions, CTR and position. Period A can be a preset; Period B is absolute.
Keywords
2 toolsFind which queries actually drive traffic, then zoom into any single keyword's day-by-day trend.
get_top_keywordsTop keywords for a property ranked by clicks, impressions, CTR or position — with period-over-period comparison. Paginated via next_cursor.
get_keyword_detailDaily time series (clicks, impressions, CTR, position) for a single search query in a property. Same date-range options as the summary.
Pages
2 toolsSee which URLs carry the traffic, where they lost ground, and pull a daily breakdown for any one of them.
get_top_pagesTop pages for a property ranked by clicks, impressions, CTR or position — with period-over-period comparison. Paginated via next_cursor.
get_page_detailDaily time series (clicks, impressions, CTR, position) for a single page URL in a property. Drop-in compatible with the summary's date-range syntax.
Tasks
5 toolsThe SEOcrawl task system — fully wired into the MCP. Create work, edit it, comment on it, never leave the chat.
list_tasksAll tasks for a property. Filter by status (open / done), assignee, taskbox (column) or q (case-insensitive title search). Paginated via next_cursor.
get_taskFull detail for a single task. Accepts a UUID, a slug, or a full browser task URL (the property arg is optional when you pass a URL).
create_taskCreate a task on a property with title (required) plus optional description, assignee, priority (1–5, default 3) and taskbox (defaults to the TO-DO column).
update_taskPartially update a task — any combination of title, description, assignee, priority, taskbox, or unassign:true to clear the owner.
add_commentAppend a comment to a task. Same flexible ticket reference (UUID / slug / URL) as get_task and update_task.
Use it where you already chat
SEOcrawl AI MCP follows the open Model Context Protocol — any MCP-compatible client works. Here are the four most common setups today.
Claude
Connect SEOcrawl AI from Claude.ai and Claude Desktop. Ask for performance summaries, top pages or task triage and Claude calls the right MCP tool for you.
Setup
Settings → Connectors → Add custom MCPChatGPT
Use SEOcrawl AI inside ChatGPT via the Apps connector. Mention @SEOcrawl in a chat to pull live Search Console data or open a task without leaving the conversation.
Setup
ChatGPT Apps → Add SEOcrawl AICursor
Drop the SEOcrawl AI MCP into Cursor and pull live performance or task data while you're writing code, briefs or release notes.
Setup
Settings → MCP → Add serverClaude Code
Register SEOcrawl AI in Claude Code from your terminal. Every tool becomes a one-line CLI call inside your existing dev workflow.
Setup
claude mcp add seocrawl https://mcp.seocrawl.aiFrequently Asked Questions
What is MCP?
MCP (Model Context Protocol) is an open standard that lets AI assistants like Claude and ChatGPT talk to external tools and data sources. Instead of copy-pasting reports into a chat, the assistant calls SEOcrawl AI directly and brings the data back.
What is the SEOcrawl AI MCP?
It's a server that exposes 12 SEOcrawl AI tools — Search Console performance queries, keyword and page drill-downs, and the full SEOcrawl task system — as MCP tools your AI assistant can call. You ask in natural language; the assistant runs the right query against your account and brings the result back.
What does it actually do today?
Three families of work: (1) Search Console performance — clicks, impressions, CTR and position summaries plus side-by-side date comparisons; (2) Keyword and page analysis — top lists with period-over-period deltas and daily breakdowns for any single keyword or URL; (3) SEO tasks — list, create, update, comment on and close tasks inside your SEOcrawl projects. New tools (Brand Radar, backlinks, audit) ship on a rolling basis — we update this page when they go live.
Which plans include MCP access? How are calls metered?
MCP access is included on every SEOcrawl AI plan. Each plan ships with a monthly MCP credit pool — 3,000 (Starter), 10,000 (Growth), 30,000 (Pro), 100,000 (Agency) and Unlimited (Enterprise). Each MCP call burns 1–6 credits depending on the tool: light lookups (list_properties, get_task) cost 1, performance summaries and time-series cost 3, top-keyword / top-page calls cost 5, side-by-side date comparisons cost 6. A per-minute rate limit and a hard daily cap apply on every plan to protect the platform from runaway agents. Your account's project, click and LLM-credit limits still apply on top.
Which AI clients does it work with?
Claude (Claude.ai and Claude Desktop), ChatGPT (via the Apps connector), Cursor and Claude Code today. Any MCP-compliant client should work — the server uses the open MCP transport, with no client-specific code paths.
Does it use my real SEOcrawl AI data?
Yes. The MCP authenticates against your SEOcrawl AI account and reads the same Search Console properties and tasks you see in the app. We never share data across accounts.
How do I set it up?
Log into SEOcrawl AI, open the MCP section in account settings, copy your personal MCP URL, and paste it into your AI client's MCP/connector configuration. Most clients pick the 12 tools up automatically and you can start chatting in under a minute.