API & MCP platform
Your AI visibility data, over an API — on every plan
A read-only REST API and an MCP server, both backed by the exact computations that render your dashboard — included with every plan, not locked behind an enterprise tier. Ten read endpoints on every tier — crawler analytics follows the Growth-and-up agent-analytics gate — plus historical time series and a contract that only ever grows.
No enterprise gate
One key, no enterprise gate
Access is gated by API-key scope, not plan tier: create a key under Settings → API keys and read your workspace's data. Competitors typically reserve API access for enterprise contracts — peec, for example, documents API keys as Enterprise-only (July 2026).
Keys come in two scopes — full for reads and a deliberately narrow ingest-only scope for edge workers that can post crawler logs but never read workspace data. Every keyed request is metered at 120 requests/minute with X-RateLimit-* headers and an honest 429 with Retry-After when you hit it.
-H "Authorization: Bearer mf_…"
"visibility": 61.4,
"share_of_voice_fraction": 0.312,
"citation_share": 0.208,
"sentiment_index": 64
}
Illustrative — the API is served by the same computations that render the dashboard.
11 read endpoints
The same computations that render your dashboard
Brands, the visibility scorecard, prompts, competitors, cited sources and individual cited URLs, raw answer receipts, shopping placements and trend, historical metric time series, and crawler analytics (Growth and up, matching the dashboard's agent-analytics gate) — plus one ingest endpoint for streaming AI-crawler logs. Because the API and the dashboard are served by the same functions, they can never drift apart.
GET /api/v1/metrics/history returns the daily series behind the charts — blended across the search-grounded engines like the dashboard, or per engine, with competitor series on request. List resources paginate with keyset cursors past the default caps, and requests without pagination params get the exact frozen response.
Illustrative — uncollected days are honest nulls with sample_size 0, never fabricated zeros.
The contract
Additive-only, versioned, and public
The v1 contract is frozen: released fields never change meaning, scale, or name — every change is additive. Each response carries an X-MF-API-Version header dated to the newest released change, matching the top entry of the public changelog. Metric math is versioned separately, so a computation change can never silently alter a field you already parse.
| Version | Released (additive) |
|---|---|
| 2026-07-11 | Pagination on the list resources; crawler analytics endpoint + MCP tool; metrics history; X-MF-API-Version header |
| 2026-07-10 | URL-level citations; per-key rate limiting with honest 429s; share_of_voice_fraction |
| 2026-07-09 | Ingest-only key scope for edge workers |
| 2026-07-08 | Self-serve workspace API keys, lifecycle in the audit log |
MCP server
Ask your own visibility data questions — from any AI agent
The MCP server exposes the same reads as 11 tools over the Model Context Protocol (Streamable HTTP). Point Claude, Cursor, or any MCP client at /api/mcp with your API key and ask — which prompts did we lose this week, which pages earned citations, what does GPTBot fetch on our site.
Tool descriptions embed the data-honesty contract — a null is missing data and never zero, one observed day is a snapshot and not a trend — so an agent gets the rules exactly where it reads the data.
Illustrative — 4 of the 11 tools. Descriptions embed the data-honesty rules an agent needs.
Frequently asked questions
Does MentionFlow have an API?+
Yes — a read-only v1 REST API over the same data your dashboard shows: brands, the visibility scorecard, prompts, competitors, cited sources and URLs, raw answers, shopping placements, historical metric time series, and crawler analytics, plus one write endpoint for ingesting AI-crawler logs. Both the API and the dashboard are served by the same computations, so a number in an API response and the number on your screen can never disagree.
Is the API available on every plan?+
Yes. API access is gated by API-key scope, not by plan tier — any workspace can create a full-scope key under Settings → API keys and read its data. There is no enterprise gate in front of programmatic access.
What is the MentionFlow MCP server?+
An MCP (Model Context Protocol) endpoint that exposes the same reads as tools an AI agent can call — 11 tools, from list_brands and get_overview to get_metrics_history and get_crawler_analytics. Point Claude, Cursor, or any MCP client at the endpoint with your API key and ask questions about your own visibility data. Each tool's description embeds the data-honesty rules — for example, that a null is missing data, never a zero — so an agent reads the rules in context.
Can I pull historical data over the API?+
Yes. GET /api/v1/metrics/history returns the daily series behind the dashboard charts — visibility, share-of-voice fraction, citation share, or sentiment index — over preset windows of 7, 14, 28 or 56 days, or a custom date range. You can request the blended search-grounded scope the dashboard uses, a single engine's series, or competitor series alongside your own. Days with no collection are honest nulls with a sample size of zero, never fabricated zeros.
Will API changes break my integration?+
The v1 contract is frozen additive-only: released fields never change meaning, scale, or name. Every response carries an X-MF-API-Version header — the date of the newest released change — and every change is listed in the public API changelog. Metric math is versioned separately, so a computation change bumps a version instead of silently altering a field.
Is there a Looker Studio connector?+
Yes — a Looker Studio community connector, linked from the Reports hub, so you can build and share your own dashboards on top of your MentionFlow data using Looker Studio's charting tools.
The full reference lives in the docs: API & MCP overview, resources, MCP server and the changelog. Pair the API with client reporting for the deliverables, or AI crawler analytics for the ingest side.
Build on your visibility data
Create a key in Settings → API keys and make your first request in under a minute — on any plan.
Start your free trial