Boost Google & AI search rankings with Rank.ai. All-in-one platform or full-service agency to optimize content, track rankings, and dominate AI search.
This listing identifies a third-party MCP server. MCPBundles is not affiliated with, sponsored by, or endorsed by the service or its operator unless stated on this page.
This server may ask you to sign in when your AI client connects.
Last probed Nov 16, 2026 · api.rank.ai
63tools discovered
For AI agents — MCPBundles Directory API
For MCP client apps (human connect):
MCP connect URL: https://api.rank.ai/mcp
Skill page: https://www.mcpbundles.com/skills/rank-mcp-2c598c40cb
Explore capabilities (63)
other 25
Showing 25 of 63
Showing 25 of 63 tools from the public preview. Connect the server to inspect the full live tool list.
Report9
Audit6
Ai Rank5
Agent Analytics2
National Rank2
Other capabilities1
Audit Create
other
audit_create
Start a new conversational audit.
Cost: ~200 tokens.
Args:
domain: The site to audit. Bare host or full URL both fine.
category: Optional industry hint that biases keyword extraction
(e.g. "Dentists", "Saas").
Audit Create — Start a new conversational audit.
Cost: ~200 tokens.
Args:
domain: The site to audit. Bare host or full URL both fine.
category: Optional industry hint that biases keyword extraction
(e.g. "Dentists", "Saas").
Audit Next — Inspect the current state of an audit session and return whatever
the LLM needs next: scrape progress, the awaiting_review proposal,
running progress, the final report_id, or an error.
Cost: ~500 tokens (depends on state).
Audit Answer — Respond to a gate. Validates payload against the schema returned
by audit.next. If ``confirm=True`` and the session is in
``awaiting_review``, this dispatches the audit and transitions to
``running``.
Cost: ~400 tokens.
Audit Cancel — Cancel an in-progress session. Idempotent.
Audit Usage — Return the caller's current month's audit-credit balance.
Cost: ~100 tokens. Cheap — call before audit.create if you're
unsure whether the user can afford the audit.
Audit List — List the caller's recent audit sessions.
Args:
status: Optional state filter (``"awaiting_review"``, ``"running"``,
``"complete"``, etc).
limit: Max sessions to return (1-100, default 20).
cursor: Opaque pagination cursor from a previous call.
Cost: ~50 tokens per row.
Org Websites — List the caller's org's tracked websites with id, domain, and
audit counts. The starting point for any per-website tool —
``national_rank_list_keywords``, ``ai_rank_list_prompts``,
``report_*`` etc. all need a ``website_id`` and this is how you
get one.
Use this first when the user asks about "my rankings" / "my
keywords" / "my site" without naming a domain. If the org has
exactly one website, you don't need to ask the user — just use
its id. If there are several
Report Summary — Single-paragraph overview, top KPIs, biggest gap, severity counts.
Always start here — every other report tool returns more focused
data once you know what to drill into.
Cost: ~800 tokens.
Get your MCP into directories
A working endpoint is step one. Directory coverage is the coordinated launch across ChatGPT, Claude, Cursor, the MCP Registry, and community indexes.
What is the Rank.ai | AI-Powered SEO Platform & Agency MCP server?
Boost Google & AI search rankings with Rank.ai. All-in-one platform or full-service agency to optimize content, track rankings, and dominate AI search.
How do I connect Rank.ai | AI-Powered SEO Platform & Agency to my AI agent?
Use the MCP endpoint listed on this page in your MCP client configuration. One-click install pills support Claude, Cursor, VS Code, and other hosts. Copy the remote MCP URL if your client needs a manual entry.
Operate this server?
Request removal if you do not want Rank.ai | AI-Powered SEO Platform & Agency listed here, or claim the listing if you want to manage it on MCPBundles.
Operate Rank.ai | AI-Powered SEO Platform & Agency?
This server appears in the MCPBundles directory. Verify you operate it to take over the listing — name, description, logo, contact email, and skill content. We email a 6-digit code to a maintainer address your server publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.
MCPBundles publishes this directory for MCP discovery. Except where we host or operate an offering, third-party services run under their own terms. Product and company names on this page are used in a descriptive, identifying way (including under nominative fair use where applicable); they remain the property of their owners. Nothing here grants you rights in those marks, and nothing here is an offer to sell a third party's services. Terms · Request removal
More in search
Other MCP servers in this category from the directory index
Report List Keywords — Per-keyword rows aggregated across all locations.
Args:
sort_by: ``"search_volume"`` (default), ``"organic_rank"``,
``"gmb_rank"``, or ``"keyword"``.
limit: 1-100, default 20.
cursor: Opaque integer offset from a previous call.
Cost: ~50 tokens per row.
Report List Locations — Per-location rows: address, coords, avg rank, num keywords,
current vs potential leads.
Cost: ~40 tokens per row.
Report Location — Single-location detail: rankings dict, lead estimates, review
summary. No raw grid points (call report.grid_summary for those).
``location_id`` is the stable index returned by report.list_locations
(e.g. ``"0"``, ``"1"``).
Cost: ~2k tokens.
Report Grid Summary — Bucketed histogram of grid ranks {1-3, 4-10, 11-20, 21+},
plus geographic centroid and the worst-ranked point.
Cost: ~200 tokens. Always prefer this over report.grid_points
unless the user explicitly asks to see individual points.
Report Grid Points — Drill-down to individual grid points.
Args:
ranks: ``"poor"`` returns only points ranking >10. ``"all"``
returns everything (use with limit).
limit: Max points per page (default 50, max 200).
cursor: Opaque integer offset.
Cost: ~30 tokens per point.
Report Competitor — List competitors with presence counts, or detail for one if
``domain`` is provided.
Cost: ~1.5k tokens.
Report Findings — Enriched findings for non-local site reviews. severity filter
accepts ``"critical"``, ``"needs_work"``, or ``"good"``.
Returns 404 for client-audit reports that don't have a ``site_review``
payload — those use report.summary / list_keywords / list_locations
instead.
Cost: ~2k tokens.
Report Insights — Pre-computed "interesting findings" cards (high-volume blind
spots, competitor dominance, geographic gaps, quick wins, etc).
Cost: ~1.5k tokens. Cheap to fetch repeatedly — these are
pre-baked when the report finishes. For older reports without
pre-computed insights, this falls back to computing them on the fly
from the loaded payload.
National Rank List Keywords — List national-SERP keywords being tracked for a website with their
latest rank and 30-day trend.
Args:
website_id: UUID of the website.
Cost: ~80 tokens per keyword.
National Rank Keyword History — Time-series of rank checks for a tracked keyword.
Args:
keyword_id: UUID of the NationalKeywordTracking row.
days: How far back to go (1-180).
Cost: ~30 tokens per data point.
Ai Rank List Prompts — List AI Rank prompts tracked for a website + their latest visibility per provider.
Args:
website_id: UUID of the website.
Cost: ~150 tokens per prompt.
Ai Rank Create Prompt — Add a prompt to track. Charges nothing on creation; daily checks bill
the org's credit pool when they run.
Args:
website_id: UUID of the website to track this prompt for.
prompt_text: The natural-language prompt to send to each provider.
intent: informational | commercial | navigational | transactional.
providers: subset of ["openai","anthropic","gemini"]. Defaults to all.
frequency: "daily", "weekly", or "on_demand".
samples_per_check: 1-
Ai Rank Run Now — Trigger an ad-hoc AI Rank check for a prompt. Each (provider × sample)
pair charges 50 credits.
Args:
prompt_id: UUID of the prompt.
providers: optional subset of the prompt's enabled providers.
samples: 1-5 samples per provider (default 1).
Cost: ~80 tokens.
Ai Rank Get Run Detail — Drill into a specific AI Rank run: answer text, underlying search
queries the model issued, and citations (URLs the model linked).
Args:
run_id: UUID of the AIRankRun.
Cost: highly variable — answer text alone can be 1k+ tokens. Use
sparingly.
Ai Rank Suggest Prompts — Generate prompt ideas tailored to this website's industry + tracked
keywords. Returns suggestions; does NOT auto-track them.
Args:
website_id: UUID of the website.
target_count: How many suggestions to return (3-20).
Cost: ~120 tokens per suggestion (LLM call ~1 cent).
Agent Analytics Summary — Return per-bot crawl stats for a website.
Args:
website_id: UUID of the website.
days: How far back to look (1–180).
Cost: ~120 tokens.
Agent Analytics List Visits — Recent raw bot visits for a website.
Args:
website_id: UUID of the website.
bot_name: Filter to one canonical bot ("gptbot", "claudebot", etc.).
limit: 1–200 visits to return.
Cost: ~30 tokens per visit.
Showing the first 25 tools — full list and schemas: Directory API.
How many tools does Rank.ai | AI-Powered SEO Platform & Agency provide?
MCPBundles probed 63 tools on the live server. The tool list on this page reflects what was discovered at the last refresh — connect your client to see the full set available to your session.
What authentication does Rank.ai | AI-Powered SEO Platform & Agency require?
Rank.ai | AI-Powered SEO Platform & Agency may require signing in to the provider before tools can run. Connect through MCPBundles or your MCP client and complete any provider login when prompted.
Don't want this listed?
Request removal from the MCPBundles directory. We stop publishing this listing on mcpbundles.com.
MCPBundles is an independent platform built on the open Model Context Protocol standard. MCPBundles is not affiliated with, sponsored by, or endorsed by Anthropic PBC.