TrustMRR Verified Startup Revenue MCP server

How an agent would call it

Two steps: search returns refs, then data_fetch opens one of them. The arguments below are the arguments that were sent.

{
  "tool": "search",
  "arguments": {
    "query": "analytics",
    "sources": [
      "trustmrr"
    ],
    "limit": 2,
    "runId": "<from run_begin>"
  }
}

{
  "tool": "data_fetch",
  "arguments": {
    "sourceId": "trustmrr",
    "ref": {
      "id": "gumroad"
    },
    "runId": "<from run_begin>"
  }
}

This runs against an account — send Authorization: Bearer <token> with the call. Get one at app.bedrocktap.com/dashboard/tokens; the free tier needs no card, and it reaches trustmrr like every other source.

What it costs. 0.45 credits per company returned, and 0.45 per fetch. The search above returned 2 companies and cost 0.9 credits; the fetch cost 0.45.

What came back

{
  "ref": {
    "id": "gumroad",
    "url": "https://gumroad.com",
    "title": "Gumroad"
  },
  "text": "Gumroad\nGo from 0 to $1",
  "fetchedAt": "2026-09-12T14:58:10.463Z"
}

The search rows carried category and the selfReported flag. The fetch is where the numbers are: its data ran to 48 fields, among them revenue, growth30d, growthMRR30d, customers, activeSubscriptions, multiple, askingPrice, profitMarginLast30Days, visitorsLast30Days, revenuePerVisitor, domainRating, foundedDate, country, techStack, marketingChannels and targetAudience.

Observed 2026-09-12. One call against a live source — ask again tomorrow and the rows move.

What a row contains

One row is one company: its slug as the id, its own website, and its name. meta carries the reported monthly and annual revenue where the listing states them, the category, the founding year, whether the platform marked the listing verified, and a selfReported flag set on every single row. That flag is the point: these are figures a founder chose to publish. They are a comparable, never an audit.

A question it answers. What does a company my size in my category say it earns, and how fast is it growing?

Routing guidance

What an agent reads to decide whether trustmrr is the right source, and what to reach for when it is not.

Answers

What a company actually earns, and which startups are for sale at what multiple. Every money figure is read from a connected payment account, so it is evidence rather than a founder’s claim. Fetching a result returns the full profile — tech stack, marketing channels, cofounders, domain rating and founder message.

Query shape

A company name or slug resolves directly. Filters are `key:value` tokens and combine with free text — category, sort, onSale, minMrr, maxPrice, minGrowth, country, teamSize, fundingStatus, slug. Money is written in dollars and growth in percent; nothing is scaled. An unknown category or sort is refused and named, never silently ignored.

Price

Priced in credits, per row, per query or per call depending on the source. Every call is quoted before it runs — `cost_estimate` returns the exact figure and spends nothing. See /pricing.

Legal basis

Public API — the platform’s own documented, openly available interface.

Latency

Fast for a name lookup; a free-text or category sift costs several sequential requests.

Prefer instead

`producthunt` when you want launches, upvotes and reviews rather than money. `linkedin` for headcount and corporate profile. `google-serp` or `hackernews` for a company with no profile here.

Cannot answer

Full-text search of any kind — the upstream has no search endpoint. Private companies, funding rounds, valuations, headcount, or any startup that has not connected a payment account.

Caveat

Free text is matched locally against a bounded window of ONE ordering, so a company outside that window reads as absent even though it exists. Reach a specific company by name or slug instead — that path is exact.

Caveat

Coverage is opt-in: a few hundred startups whose founders connected a payment account, not a market census.

Related sources