AI Visibility API, MCP Server & Webhooks | Rank Prompt

Three ways to build on your AI visibility data

An AI search visibility API for your backend, an MCP server for your AI agent, and webhooks that push events to you. Monitor how ChatGPT, Claude, Gemini, Perplexity, Google AI Mode (AI Overviews), and Grok recommend your brand, all from one contract.

Get an API key Read the API docs

Public REST API (/v1) MCP server Outbound webhooks Scoped, brand-restricted keys OpenAPI 3.1 spec

Three surfaces, one platformbashLive Copy

# 1 · REST API · your backend pulls
curl https://api.rankprompt.com/v1/reports \
  -H "Authorization: Bearer $RANKPROMPT_API_KEY"

# 2 · MCP server · your AI agent acts
claude mcp add --transport http --scope user rankprompt \
  https://mcp.rankprompt.com/mcp

# 3 · Webhooks · we push to you
curl https://api.rankprompt.com/v1/brands/$BRAND/webhooks \
  -H "Authorization: Bearer $RANKPROMPT_API_KEY" \
  -d '{"url":"https://you.app/hooks","events":["report.completed"]}'

One AI search visibility API, three ways to wire it in

An AI visibility API returns programmatic data on how a brand appears in AI-generated answers: mentions, ranking position, visibility score, and the sources each engine cites. Ours covers ChatGPT, Claude, Gemini, Perplexity, Google AI Mode (AI Overviews), and Grok, normalized into one schema. The REST API, the MCP server, and webhooks all read from that same data layer, so pick the surface that matches how you work, or use all three.

REST API

your backend pulls

Call /v1 from your code

Six AI engines normalized into one schema. Manage brands, run reports, and read citations from your backend, warehouse, or product.

Read the API docs

MCP server New

your AI agent acts

Connect your AI agent

Plug your AI visibility data into Claude Code, Cursor, or any MCP client over OAuth. Your agent reads reports and citations, then runs reports and ships fixes.

Set up the MCP server

Webhooks

we push to you

Get events as they happen

Subscribe a per-brand endpoint and we POST signed events the moment a report or a scheduled run finishes. No polling loop to babysit.

See webhook events

What you can build

Every AI visibility metric, available as an API

The same building blocks that power the Rank Prompt dashboard. Brand management ships today; the rest is rolling out under /v1 over the coming months. Every endpoint follows the same auth, error, and idempotency contract from day one.

Available

Brand management

Programmatically onboard brands, update categories, languages, aliases, and competitors. Perfect for agencies provisioning new clients without touching the dashboard.

AI visibility reports

Run prompts across ChatGPT, Perplexity, Google AI Mode, Claude, Gemini, and Grok. Pull mentions, ranking position, and visibility score into your stack.

Citation & source tracking

Discover the sources AI assistants cite when recommending brands in your space, with the Rank Prompt Score so you only outreach to reachable targets.

Scheduled reports

Cron-style report definitions: weekly competitor snapshots, monthly visibility deltas, anomaly alerts. Delivered as JSON or shareable PDFs.

Coming soon

How it works

Start monitoring AI visibility in under 10 minutes

No oddly-named handshakes, no SDK install dance. A bearer token, a curl command, and you're moving data.

  1. Mint a scoped API key
    API access is included on any Starter and up plan (or pick a standalone API plan). Open the Developers page in your workspace, choose the scopes you need, and (optionally) pin the key to a single brand for white-label work.

  2. Call /v1 from your backend
    Send a bearer token, follow the OpenAPI spec. Every metered response carries quota headers so you can pace work; idempotency keys make every POST safe to retry.

  3. Stream insights into your stack
    Pipe results into your dashboard, warehouse, CRM, or Slack. Register a webhook so we push report.completed and schedule.run.completed events the moment they happen, no polling loop required.

See the full quickstart in the docs

Built for production

A production AI visibility API you can depend on

Every primitive you'd expect from a serious payments or analytics API. Boring, predictable, and well-documented; not flashy and brittle.

OpenAPI 3.1 spec

Spec-first design. Generate an idiomatic client in any language with openapi-generator, Stainless, Fern, or Speakeasy. The whole surface is browseable in the hosted reference.

Scoped & brand-restricted keys

Mint keys with the minimum surface area required: read-only, write-only, per-resource, or pinned to a single brand for white-label work. Keys are shown once, stored hashed.

Idempotent writes

Every POST accepts an Idempotency-Key. Network retries, queue redelivery, and worker restarts are safe by default.

Predictable rate limits

120 requests per minute per key plus a monthly quota. Every metered response carries X-RP-Quota-* headers; throttled calls return Retry-After. No surprise back-pressure.

Structured errors

Stable error.code values from a published catalog, machine-readable details, and a request_id echoed in every response for end-to-end tracing in support tickets.

Versioned forever

The /v1 contract is additive: new fields and endpoints only. When a breaking change is needed we ship /v2 alongside, with long deprecation windows announced via Sunset headers.

Use cases

What teams build with the AI visibility API

The four shapes most teams take when they integrate. Pick the one closest to yours; mix and match the rest.

Agencies
White-label AI visibility dashboards. Spin up a per-client dashboard in your own product. One brand-pinned API key per client, your branding, your billing, our data layer.

BI & analytics
Pipe AI metrics into your warehouse. Schedule nightly pulls of ranking, citation, and visibility data into Snowflake, BigQuery, or Looker. Track AI presence right next to organic traffic.

Ops & alerting
Trigger Slack and PagerDuty when reports land. Subscribe a webhook to schedule.run.completed, diff the new visibility score against last week, and page the team only when it actually moves.

CI/CD
Catch SEO/AEO regressions on every push. Add a GitHub Action that calls /v1/page-audit (a URL, a list, or a whole sitemap) on each pull request, comments the score and concrete fixes, and fails the build below your threshold.

API plans

AI visibility API pricing built for developers

The API, the MCP server, and webhooks are included free on every Starter plan and up. Want the API on its own? Two standalone subscriptions cover that, with no surprise overages.

Best value

Included with your plan
API, MCP server, and webhooks
Free
on any Starter plan and up, from $49/mo

Monthly request cap by plan

Start free trial

Free AI visibility report first

7-day trial on any plan

API Starter

Standalone API plan for customers without a dashboard plan

$99/mo

Get started

API Pro

Standalone API plan for embedded SaaS and high-volume workloads

$299/mo

Get started

How requests are metered

Two meters. Request units cap raw API throughput; credits cap LLM and search work. You never pay twice for the same operation, whether you trigger it from the dashboard or from /v1.

Per-endpoint cost map

0 request units: /v1/me and /v1/me/quota: free to poll, anytime.

1 request unit: Typical CRUD call (list brands, fetch a brand, mint a key).

120 req / minute: Per-key burst limit. Quota and Retry-After exposed on every response.

FAQ

Developer questions

Everything teams ask before they integrate. Email us if your question isn't covered.

  1. Can I pipe AI visibility metrics into my BI dashboard?
    Yes. The AI search visibility API returns JSON over plain REST, so anything that can call an HTTP endpoint can read it: Looker Studio, Power BI, Tableau, Metabase, or a warehouse job on a schedule. Pull visibility scores, mention rates, ranking positions, and cited sources per brand and per engine, then join them against your own tables. Scoped read-only keys (read:brands, read:reports) mean a BI connector never gets write access.

  2. Does the API cover ChatGPT, Claude, Gemini and Perplexity in one place?
    Yes. One request returns AI visibility data across all six engines: ChatGPT, Claude, Gemini, Perplexity, Google AI Mode (AI Overviews), and Grok. They are normalized into a single schema, so you compare positions and citations across engines without writing per-platform parsers or maintaining six different scrapers.

  3. Do you offer real-time AI search visibility updates?
    Close to it. Reports run on demand or on a schedule, and outbound webhooks push report.completed, report.failed, schedule.run.completed, and schedule.run.failed to your endpoint the moment a run finishes, with HMAC-signed payloads. You do not need to poll: your systems learn about new AI visibility data as soon as it exists.

  4. What can I build with the Rank Prompt API today?
    Brand management (create, list, retrieve, update, delete), AI visibility reports across the six major LLM platforms, citation & source tracking with the Rank Prompt Score, scheduled reports, outbound webhooks, plus the account endpoints (/v1/me, /v1/me/quota). You can also connect an MCP client. Brand audits, AI-optimized content generation, technical SEO audits, and outreach are on the public roadmap and ship under the same /v1 contract; subscribe to the changelog to track release dates. The eventual surface mirrors the dashboard 1:1.

  5. How is the API priced?
    Developer API access is included with every Starter and up dashboard plan, with a monthly request cap per tier: 10,000 on Starter, 25,000 on Pro, 50,000 on Agency, and 100,000 on Agency Plus. Credit-consuming /v1 endpoints (the ones that hit a paid LLM or third-party search backend) draw from your plan's own monthly credits, so you never pay twice. Want the API on its own, with no dashboard plan? Two standalone subscriptions cover that: API Starter ($99/mo, 50,000 request units, 500 bundled API credits) and API Pro ($299/mo, 200,000 request units, 2,000 bundled API credits). Every plan applies a 120 requests/minute per-key burst limit, and the per-endpoint cost map lives in the developer docs.

  6. What are the rate limits?
    A per-key burst limit of 120 requests per rolling minute is applied to every API key, regardless of plan. On top of that, your plan grants a monthly request-unit quota. Every metered response includes X-RP-Quota-Limit, X-RP-Quota-Used, X-RP-Quota-Remaining, and X-RP-Quota-Reset so you can pace work without polling. Throttled calls return a 429 with Retry-After.

  7. Is there a sandbox or test environment?
    The GET /v1/me and GET /v1/me/quota endpoints cost 0 request units and never count against your quota, so you can validate keys, scopes, and request signing without burning budget. For full end-to-end tests, mint a separate key with limited scopes and exercise it against a test brand.

  8. Can I issue per-brand keys for my clients?
    Yes. Optionally bind a key to a single brand at creation time (allowed_brand_id). The API will refuse any request whose target brand does not match, even if the calling key carries write:all. This lets agencies and platforms issue per-brand keys to clients without spinning up a new Rank Prompt workspace.

  9. Can my AI agent (Claude Code or Cursor) use Rank Prompt?
    Yes. The Rank Prompt MCP server lets Claude Code, Cursor, Claude Desktop, or any MCP client read your reports, brands, and citations, and run reports on your behalf. You connect over OAuth in the browser, so there is no key to paste. See the MCP server page at rankprompt.com/mcp for the 30-second setup.

  10. Where is the AI visibility API documentation?
    The full reference lives at /docs/v1/, generated from an OpenAPI 3.1 specification. Every endpoint documents its parameters, response schema, and error codes, with runnable curl, JavaScript (fetch), and Python (httpx) examples. Because the spec is machine-readable, you can also generate a typed client in any language with openapi-generator, Stainless, Speakeasy, or Fern.

  11. Can I access competitor AI visibility data through the API?
    Yes. Competitive AI search visibility data is part of the report payload: alongside your own brand, reports return the competing brands each engine named for the same prompt, their position in the answer, and the sources cited for them. That lets you track share of voice over time and alert when a competitor overtakes you in a category.

  12. Do you support enterprise dashboards and custom API integrations?
    Yes. Per-brand key restriction lets you mint a key scoped to a single brand, which is what makes white-label and per-client enterprise dashboards practical: each customer sees only their own AI visibility data. Combined with scoped permissions, idempotent writes, and a stable error envelope, the API is built to sit behind custom integrations you support in production.

  13. How do I get an API key?
    Every Starter and up dashboard plan includes Developer API access, so you can mint a key straight from the Developers page in your workspace. Want the API on its own, without a dashboard plan? Subscribe to a standalone API Starter or API Pro plan instead. Each key carries scoped permissions (e.g. read:brands, write:brands) and an optional brand restriction for white-label use. Keys are prefixed with rp_live_, are shown once at creation, and stored hashed in the database.

  14. I'm already on a Starter / Pro / Agency plan. Do I need an API plan?
    No. Developer API access is included with your Starter, Pro, Agency, or Agency Plus plan, with a monthly request cap that scales by tier (10,000 / 25,000 / 50,000 / 100,000 requests). Credit-consuming /v1 endpoints draw from the same monthly credits you already pay for, so there's nothing extra to buy. You'd only add a standalone API Starter or API Pro plan if you don't run a dashboard plan at all, or you want a larger dedicated request quota with its own bundled API credits.

  15. Are there official client libraries?
    Not yet. The API ships with an OpenAPI 3.1 spec, so you can generate idiomatic clients in any language using openapi-generator, oazapfts, hey-api, Stainless, Speakeasy, or Fern. The docs include curl, JavaScript (fetch), and Python (httpx) examples for every endpoint. First-party TypeScript and Python SDKs are on the roadmap.

  16. How do you handle versioning and breaking changes?
    The /v1 contract is additive. We only add fields and endpoints; we never silently remove or rename them. When a breaking change is unavoidable, we ship /v2 alongside /v1 with a long deprecation window, and we announce the sunset of any endpoint via the standard Sunset HTTP header well in advance.

  17. Do you support webhooks?
    Yes, webhooks are live. Register a per-brand endpoint with POST /v1/brands/{brand_id}/webhooks and subscribe to report.completed, report.failed, schedule.run.completed, and schedule.run.failed. Payloads are HMAC-signed, the signing secret rotates (the old secret stays valid for 24 hours), and an endpoint auto-disables after repeated failures. You no longer need to poll report status from a worker.

  18. How is the API secured?
    Bearer-token authentication over TLS, scoped per-resource. Browser CORS calls are blocked at the edge: the API is server-to-server only. Keys are stored hashed and we submit the rp_live_ prefix to GitHub secret scanning so leaked keys are caught automatically. The API runs on the same hardened infrastructure as the rest of the Rank Prompt platform, with EU/US data residency options.

Still have questions? Contact our team

Public API v1

Start building today

Read the quickstart, mint your first API key, and ship a working integration before lunch.

Read the docs Get an API key