Hand it to your AI agent
Copy this prompt into Claude Code, Cursor, Codex or any coding agent. It tells the agent where the docs are and how to use your API key.
Use the Lovely Router data tool "Search LinkedIn companies" (id `linkedin-company-search`, LinkedIn) to get data for me. It returns JSON.
- Docs (read first): https://lovelyrouter.com/docs/tools/run.md and https://lovelyrouter.com/docs/api/tools.md
- Input fields and price: GET https://lovelyrouter.com/v1/tools/linkedin-company-search (public, no key needed). Price: $0.003 / company + $0.0015 / call.
- Run: POST https://lovelyrouter.com/v1/tools/linkedin-company-search/run with a body like `{"input":{"searchQuery":"web scraping","maxItems":3},"max_results":10}`. A 200 has the finished run with `items`; a 202 means it is still running, so poll the `poll` path until `status` is `succeeded`, `failed`, `timed_out` or `stopped`.
- Only delivered results are billed. Keep max_results small on the first run, check the output, then scale up (up to 500 per run).
- If you support MCP, you can instead connect the server https://lovelyrouter.com/mcp (Streamable HTTP, same key; https://lovelyrouter.com/docs/tools/mcp.md) and use suggest_tools, get_tool and run_tool with tool "linkedin-company-search".
- Auth: read my API key from the LOVELY_API_KEY environment variable and send it as `Authorization: Bearer $LOVELY_API_KEY`. Never print or commit the key. If it is not set, ask me to create one at https://lovelyrouter.com/app/keys.
- Billing is prepaid: every call is charged to my balance, so test with a small request before running anything large.
- Every docs page is plain Markdown; the full index is https://lovelyrouter.com/llms.txt.
My task: <describe the data you need, e.g. which places, profiles, keywords or URLs, and the output format>Input
searchQuerystringQuery to search LinkedIn companies. (e.g., `marketing`). [The query supports search operators](https://www.linkedin.com/help/linkedin/answer/a524335)
locationsarrayFilter Companies by these LinkedIn locations. Example: `San Francisco`. LinkedIn does not always understand your text queries. For example for "UK" query it will apply "Ukraine" location, so you should use "United Kingdom" in this case. Try this out first in the location filter input of LinkedIn search at `https://www.linkedin.com/search/results/people/?geoUrn=%5B%22103644278%22%5D`
companySizestring[]Filter Companies by these company size ranges.
maxItemsintegerMaximum number of companies to scrape. The tool will stop scraping when this limit is reached.
Try it
Call it from code
How runs, polling and billing work →curl https://lovelyrouter.com/v1/tools/linkedin-company-search/run \
-H "Authorization: Bearer $LOVELY_API_KEY" \
-H "content-type: application/json" \
-d '{"input":{"searchQuery":"web scraping","maxItems":3},"max_results":20}'# MCP (agents): suggest_tools → get_tool → run_tool
run_tool({
"tool": "linkedin-company-search",
"input": {"searchQuery":"web scraping","maxItems":3},
"max_results": 20
})What it costs
| Results | Runs (at 500 per run) | Cost |
|---|---|---|
| 100 | 1 | $0.301 |
| 1,000 | 2 | $3.00 |
| 10,000 | 20 | $30.03 |
Prepaid, no subscription. Fewer results than requested cost less. Pricing
Used for
Frequently asked questions
How much does the Search LinkedIn companies API cost?
$0.003 / company + $0.0015 / call. 1,000 results, fetched in runs of up to 500, cost $3.00. There is no subscription: you pay from a prepaid balance.
Is this a LinkedIn company search scraper?
Yes. If you searched for a LinkedIn company search scraper or a company search API, this is it: Search LinkedIn companies by keyword, location and size: name, industry, size, URL.
How many results does one run return?
20 by default and up to 500 per run. Set max_results to cap a run: you are billed only for the results it delivers.
Do I need a LinkedIn account or API key?
No. You call the tool with your Lovely Router API key and get JSON back. There is nothing to set up on LinkedIn.
Can an AI agent use this tool?
Yes. Connect Claude Code, Cursor or any MCP client to the Lovely Router MCP server: the agent finds the tool with suggest_tools and runs it with run_tool and the id linkedin-company-search.
What happens if a run fails?
A run that fails or is stopped pays only for the results it delivered, with no call fee. The most a run can cost is held when it starts and the rest is released when it settles.