Find People

Describe the person you want, get back matching professional profiles.

What it does

• Finds professional profiles based on the filters you pass — role, seniority, headcount, location, tenure, education and more.
• No single parameter is required, but a call with no filters has nothing to search on — pass at least one.
• Filters stack. Combining role, headcount and location narrows a broad search into a usable list.
• Cost scales with results — 0.5 credits per profile returned. A default page of 25 costs 12.5 credits; a full page of 100 costs 50.

It returns profiles. It does not return emails or phone numbers — chain find_work_email for those.

Use cases

• Build a prospect list against an ICP. Role, seniority, company size and geography in one call produces the people layer of a target list, not just the accounts.
• Work the job-change signal at scale. recently_changed_jobs plus a title filter returns buyers in their first months, when the stack is still up for grabs.
• Find champions who already know you. Filter on past company to surface people who used your product at their last employer.
• Map a buying committee across accounts. Pass several company domains with the titles that sign, and get every relevant stakeholder in one pass.
• Source on skills and credentials. Skills, certifications and education filters find technical audiences that title filters alone miss.

How to use it

Find VP Sales and Head of Sales at Privately Held SaaS companies with
51-200 employees in the United States. Limit 25.

Same search, but only people who have been in the role at least 1 year
and have a verified business email.

Get the next page using the cursor from that result. Stop after 3 pages
and tell me how many credits you used.

For the 10 best matches, find work emails and verify them.

Example prompts

Best prompting practices

• Always pass a filter. A search with nothing to match on still bills 0.5 credits for every profile it returns, and returns noise.
• Use domains, not company names. current_company_domains is exact. Names are easy to get wrong.
• Use the exact enum strings. c_suite and vp are the accepted seniority values — “C-level” and “Vice President” are not.
• Paste the docs URL into the prompt. “Parameter reference: https://docs.syncgtm.com/mcp_server/tools/find_people — read it first and use the exact parameter names and value formats.” This tool has more than sixty filters, and a client left to guess invents job_title and location.
• Reach for the normalized fields when raw titles are messy. current_departments and current_sub_departments are cleaned taxonomies, so they hold where current_titles misses a variant. normalized_titles does the same job at title level.
• State the exclusions. exclude_current_titles is free and applies before anything is billed — dropping the near-miss titles a broad list pulls in is cheaper than paying 0.5 credits each to read them.
• Dates are YYYY-MM-DD. current_role_started_after, past_role_started_after and their _before pairs will not parse “since January”.
• person_cities is exact, person_locations is fuzzy. Use the fuzzy one when you are unsure how a metro is spelled, the exact one when you are not.
• Set limit deliberately. limit is the cost dial — every profile returned is 0.5 credits. Ask for the number you will actually work, not the maximum.
• Cap the paging. “Stop after 3 pages” prevents a broad search from walking the whole result set. Three pages of 100 is 300 profiles and 150 credits.
• Ask for the rows as a table. Name, title, company, domain, location, LinkedIn URL. Left to itself your client summarizes the list and you lose the columns you paid for.
• Search first, enrich second. Filter down to the profiles you want before spending credits on emails or phones. “No enrichment yet” belongs in the same prompt.

Output

{
  "profiles": [
    {
      "name": "Jane Doe",
      "title": "VP Sales",
      "company": "Stripe",
      "location": "San Francisco, United States",
      "linkedin_url": "https://linkedin.com/in/janedoe"
    }
  ],
  "next_cursor": "eyJwYWdlIjoyfQ"
}

Credits and limits

0.5 credits per profile returned. limit accepts 1–100 and defaults to 25, so a default call costs 12.5 credits and a full page costs 50. Each extra page fetched with cursor bills the same way.

Run check_credits (free) before a long paging run.

Parameters

Nothing is strictly required. Pass at least one filter from the families below — they are listed in the order the tool accepts them.

Filters combine as AND across families and any-of within a single array filter. current_titles: ["CTO", "VP Engineering"] matches a profile holding either title; adding person_countries narrows that set rather than widening it.

Person

Role

Company

Company size

Past experience

Location

Tenure and experience

Education

Skills and credentials

Network

Signals

Paging

Filter reference

Several filters only match values from a fixed list. A near-miss does not error — it silently matches nothing, which reads like “no profiles found”. These are the full accepted value lists, hosted as JSON.

The title and region files are keyed by name and carry LinkedIn’s internal id as the value. Pass the key, not the id — person_locations: ["Greater Boston"], not ["90000007"].

To search one locally:

curl -s https://dyyboia6z5eq9.cloudfront.net/mcp/filters/find_people/linkedin_titles.json \
  | jq -r 'keys[]' | grep -i "revenue operations"

current_titles and past_titles are fuzzy, so a close string still matches. normalized_titles, skills and the region filters are exact — use the lists above for those.

Related tools

Next steps

• All MCP tools — the full catalogue with credit costs
• MCP use cases — search-to-outreach workflows
• AI for Sales Reps — workflows that chain this tool into a list build

Keep learning

Two courses take these tools past the reference page — clustered by GTM job, then chained into workflows.