Map the buying committee at a target account from LinkedIn
List the people at a company on LinkedIn, filtered by job title and location, with name, headline, position and profile URL, to find who you should talk to.
An enterprise deal rarely closes with one contact. You need the sponsor, the user who feels the pain, and the person who signs, and on LinkedIn they are buried in a staff list of hundreds. Lovely Router pulls that list for you. Send a company and the titles you care about, get one JSON object per profile, pay per profile from a prepaid balance. Call it from a script, a CRM sync or an AI agent.
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.
Map the buying committee at a target account from LinkedIn. Use the Lovely Router data tools: each returns JSON and is billed per result.
- Docs (read first): https://lovelyrouter.com/docs/tools/find.md and https://lovelyrouter.com/docs/tools/run.md
- Plan first: POST https://lovelyrouter.com/v1/tools/suggest with `{"task": "<my task in plain words>"}` (free). It returns the tools to run in order, each with an example `input`, the `input_required` fields, an estimated cost and a ready-made `run` request. Replace the example values with my task's; if a field is unclear, read the tool with GET https://lovelyrouter.com/v1/tools/<id>. To browse instead, POST https://lovelyrouter.com/v1/tools/discover searches the catalog.
- Show me the plan and its estimated cost (`total_est_cost_usd`) before running anything large.
- Run: POST https://lovelyrouter.com/v1/tools/<id>/run with `{"input": {...}, "max_results": N}`. 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.
- If you support MCP, connect https://lovelyrouter.com/mcp instead (Streamable HTTP, same key; https://lovelyrouter.com/docs/tools/mcp.md) and use suggest_tools, get_tool and run_tool.
- 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: <the inputs (links, keywords or accounts) and how many results you need>How it works
Pick the account and the roles
Take the company page URL and write the job titles of the roles on your usual buying committee: sponsor, evaluator, user, procurement.
Run the tool with a cap
Send the company in
companiesand the roles injobTitlestoPOST /v1/tools/linkedin-company-employees/run.maxItemscaps the profiles andmax_resultscaps the run.Sort into roles
Group the results by position, pick one or two names per role, and start from the profile URLs.
List the right people at a company with one request
List LinkedIn company employees takes company page URLs in companies. Narrow the list with jobTitles, locations or a free-text searchQuery; maxItems caps the profiles, and one run returns up to 500:
curl https://lovelyrouter.com/v1/tools/linkedin-company-employees/run \
-H "Authorization: Bearer $LOVELY_API_KEY" \
-H "content-type: application/json" \
-d '{
"input": {
"companies": [
"https://www.linkedin.com/company/nvidia"
],
"jobTitles": [
"Director of Infrastructure"
],
"maxItems": 25
},
"max_results": 25
}'For locations, write the full place name (United Kingdom, not UK), because LinkedIn can match a short text to the wrong place. A run still going after 60 seconds returns 202; Run a tool shows how to poll.
What each profile holds
| Field group | What you get |
|---|---|
| Person | Name |
| Role | Headline and current position |
| Link | Profile URL |
This is the short profile. For experience, education and skills of someone on your list, run the profile URL through linkedin-profile. You are responsible for using people and contact data lawfully, including privacy and anti-spam rules in the countries of the people you contact.
Recipes
Set jobTitles to the finance and operations titles at a target account and cap at 20. You get the names to approach first.
For your top ten accounts, run one title group per role and keep one contact per role, so a deal does not depend on one champion.
Use locations to list only the people in the city where you have a rep.
Re-run an account each quarter and compare the names; a new head of a function is a good reason to reach out.
Run the profile URLs of your shortlist through a model to write one line on each person's current position.
Prefer plain words? Connect the MCP server and tell Claude Code or Cursor: "For the company linkedin.com/company/nvidia, run linkedin-company-employees with jobTitles Director of Infrastructure and VP Engineering, maxItems 20, and give me a table of name, position and profile URL. Set max_results to 20."
Pair it with account and contact data
Employees are only the middle of the funnel. Around them:
Employees of LinkedIn companies, filterable by job title, location and keyword: name, headline, position, profile URL.
LinkedIn company pages: description, industry, size, headquarters, website, followers.
Public LinkedIn profile by URL: headline, experience, education, skills, location.
Work email address for LinkedIn profile URLs.
Check whether email addresses are deliverable: syntax, domain, MX records and mailbox status.
linkedin-companyconfirms the account's industry and size first.linkedin-profilereads the full profile of the people you shortlist.linkedin-email-finderlooks up the email for a profile URL.email-verifychecks an address before you send to it.
For the end-to-end workflow, see lead generation.
What you pay
You pay per profile: starting a run holds its maximum cost, the per-call fee plus the per-profile fee times max_results, and the run settles to what it returned. The rest of the hold goes back to your balance. A run that fails or times out pays only for the profiles it delivered, and a run refused at the start costs nothing.
Listing 200 people is billed as 200 profiles. There is no subscription and no monthly minimum: top up from $5, and one balance pays for tools and models. The card above shows today's price; pricing lists every tool.
Frequently asked questions
Can I filter employees by job title?+
Yes. jobTitles takes a list of titles, such as Software Engineer. locations and searchQuery narrow it further.
How many people can one run return?+
Up to 500 profiles per run. Set maxItems and max_results to the number you want.
Does it return email addresses?+
No. It returns name, headline, position and profile URL. Use linkedin-email-finder for an email, and check how you may use it. You are responsible for using people and contact data lawfully, including privacy and anti-spam rules in the countries of the people you contact.
Can I list employees of several companies?+
Yes, pass several company URLs in companies.
Do I need a subscription?+
No. You add credit to a prepaid balance and each run draws it down. Failed runs pay only for the results they delivered, and nothing renews automatically.
Going from a list to outreach? See lead generation, and the rest of the tool catalog. Run settings are in Run a tool.