Technology install base API: who uses a tool
who_uses_tech
2.5 credits / company returnedFind companies detected running a technology (e.g. "hubspot", "salesforce", "segment"), ranked by detection confidence. Optionally filter by HQ country and employee size range, and paginate with limit/offset. The tool input is matched against the scanner's tool vocabulary (exact name preferred, fuzzy fallback); matched_tools echoes what was searched. tech_source picks the detection signal: "stack" (default) reads only precise website tech-stack scans; "jobs" reads only LinkedIn job-posting mentions of the tool (broader reach, softer signal — also catches competitor/integrator mentions, not just direct users); "both" merges the two and marks each company's source(s) so you can tell a confirmed website detection from a softer job-posting mention.
Parameters
| param | type | description |
|---|---|---|
| tool required | string | Technology name to look for, e.g. "hubspot", "salesforce", "google-analytics". Required. |
| country | string | HQ country — name or ISO-2 code (e.g. "India", "US"). Optional. |
| limit | integer | Companies per page (default 10, max 100). COST: each company returned costs 2.5 credits (plus a 0.1 base fee per call), so this limit sets the price of the call — ask for what you need. |
| offset | integer | Rows to skip for pagination (default 0; offset+limit must not exceed 5000). |
| size_range | string | Employee size bucket, exact values: "1 employee", "2-10 employees", "11-50 employees", "51-200 employees", "201-500 employees", "501-1,000 employees", "1,001-5,000 employees", "5,001-10,000 employees", "10,001+ employees". Compact forms like "51-200" or "1001-5000" are normalized. Optional. |
| tech_source | string: stack | jobs | both | Which detection signal to search. "stack" (default) = website tech-stack scan only, precise. "jobs" = LinkedIn job-posting mentions only, broader/noisier. "both" = either, deduped, each company tagged with its source(s). |
Call it from your agent (MCP)
Connect once and who_uses_tech appears in your agent’s toolbox next to every other gtm.dev tool. Claude Code:
claude mcp add --transport http gtm https://mcp.gtm.dev \
--header "Authorization: Bearer YOUR_API_KEY"Under the hood, the client sends:
curl -X POST https://mcp.gtm.dev \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call",
"params":{"name":"who_uses_tech","arguments":{"tool":"hubspot","country":"IN","size_range":"51-200"}}}'other clients (cursor, claude desktop, openai agents sdk, langchain): mcp setup
Call it over REST
curl -X POST https://api.gtm.dev/v1/tools/who_uses_tech \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"tool":"hubspot","country":"IN","size_range":"51-200"}'Errors (401, 402, 429, 400) are listed in the REST reference. Calls that error are not billed — see pricing.