MCP server

Endpoint

https://app.monoranks.com/api/mcp

Streamable HTTP over POST, JSON responses, no session to keep. Send a key as Authorization: Bearer mr_ws_… (a website key mr_site_… works too), or let the client sign you in with OAuth 2.1 (below). Scopes, the hourly limit (1,200 calls per key) and the key owner’s access are checked on every tool call, as for the REST API.

Connect

Claude Code

claude mcp add --transport http monoranks https://app.monoranks.com/api/mcp \
  --header "Authorization: Bearer mr_ws_…"

Claude.ai and Claude Desktop: add the URL above as a custom connector (unverified: the menu names in those apps change often). Where the client lets you set a header, send the key as a bearer header; otherwise it signs you in with OAuth.

ChatGPT and other OAuth clients: add https://app.monoranks.com/api/mcp as an MCP server. Without a key, the endpoint answers 401 and points the client to /.well-known/oauth-protected-resource. The client registers itself (/api/oauth/register), sends you to sign in and approve access (/oauth/authorize, with PKCE), and gets its token from /api/oauth/token. It can only ask for the read scopes and issues:recheck; audits:run and actions:apply are never granted this way, so start_audit, the apply tools and update_outreach_target need a key. See API keys and scopes.

Tools

Read

Tool	Does	Scope
list_sites	Websites the key covers, with ids	sites:read
portfolio	Every website in one call: scores and their change, issues, actions, last and next audit, and Search Console clicks (with search:read)	sites:read
site_summary	Scores, last audit, open issues, WordPress access, how fresh each connection is	sites:read
speed_results	Speed per tested page: lab test and real-visitor data	sites:read
audit_status	The latest audits, or one audit by audit_id, with pages crawled and the page budget	sites:read
list_issues	Issues, the same list as the Issues screen	issues:read
issue_detail	One issue with pages, evidence, explanation and suggested new values (100 at a time, suggestions_offset for more)	issues:read
list_actions	Prioritized actions with estimated gain and how long each has been open	issues:read
page_findings	Findings for one page, by id or address	pages:read
page_history	What changed on one page from one audit or recheck to the next, by id or address	pages:read
search_summary	Search Console totals, top pages and queries	search:read
search_rows	Search Console rows for a date range, by query, page, query and page, or day (pass nextCursor back as cursor; CSV export is in the REST API only)	search:read
near_page_one	Your query and page pairs sitting just off page one (positions 8 to 20 by default), most impressions first, with the extra clicks a top-3 position could bring	search:read
topics	The website’s pages grouped into topics, with clicks, top queries and whether each topic is strong, weak or gets no clicks	search:read
analytics_pages	Conversions and revenue per landing page from Google Analytics (GA4), next to Search Console clicks	analytics:read
keywords	Keywords as the Keywords screen lists them, with demand, position, opportunity and the relevance review; off-topic suggestions left out	search:read
competitors	The competitor set with a match score, the AI review of each suggestion, which ones drive gaps, shared keywords, keywords where they rank above you, strength and visibility	search:read
competitor_gaps	Each competitor’s position and yours per keyword (gaps, content, lost, lead). Each row also names the page where each competitor ranks.	search:read
content_ideas	The keyword gaps grouped into topics, most opportunity first: whether to write a new page or expand one, your pages already in the topic, the competitor pages that rank, and the top keywords	search:read
backlinks	The backlink summary and the referring domains of one view (all, new, lost, review, strong)	search:read
list_outreach_targets	Pages and sites worth asking for a link or a mention, ranked, with why and their status	search:read
ai_visibility	What AI assistants answered to your tracked questions, per week, with the pages each answer cites	ai:read
answer_gaps	Questions where AI answers name other websites but not yours	ai:read
geo_access	AI crawler access, llms.txt and entity signals from the last audit	ai:read
llms_txt	The live llms.txt and a ready-to-publish draft	ai:read
ai_crawler_rules	What robots.txt says to each AI crawler now	ai:read
agentic_results	Agentic browsing results with what to fix, or one re-run by job_id	ai:read

Act

Tool	Does	Scope
recheck	Queue a recheck of an issue	issues:recheck
run_agentic_check	Re-run the Agentic browsing check for one page	issues:recheck
start_audit	Start a full audit now, with an optional page budget	audits:run
apply	Approve an action’s new SEO titles, descriptions, canonicals or noindex and write them to WordPress	actions:apply
apply_llms_txt	Approve a new llms.txt and write it to WordPress	actions:apply
apply_ai_crawler_rules	Approve allow or deny rules for AI crawlers and write them into robots.txt	actions:apply
update_competitors	Pick, dismiss or add a competitor; picking or adding looks up its keyword gaps within your data limit	actions:apply
update_outreach_target	Set the status (to contact, contacted, added, declined) and note of an outreach target	actions:apply

Example conversation

“Which of my websites lost the most clicks this month, and what is the top action for it?”

The assistant calls portfolio once, picks the website with the biggest drop, then calls list_actions for it, and answers with the action and its estimated gain. If you say “apply it”, it reads the suggested values with issue_detail, calls apply, and the change shows up in the app’s activity with Undo.