Niches · Lead & company data

Qualify first, pay to reveal only the shortlist

Four or more companies' docs show a full fit.

6companies, full fit
12companies, fit with a limit
29companies carry the tag
8share of the category's work
5first-hand accounts

What counts as done

Free preview or search fields used to filter, a cost preview or count before any paid call, reveals only for rows that pass, and total spend within the cap with a ledger of what was charged.

How agents ask for it: score these leads and only get emails for the good ones, keep enrichment under 200 credits this month, don't spend credits on companies outside my ICP

Does the job 6

The docs show it meets the test above, and nothing we read says otherwise.

ListingWhy
Apollo API + MCP B
ZenLeads Inc. d/b/a Apollo.io
People search is free and returns has_email and has_direct_phone flags, personal email and phone reveal are off unless asked, and credit usage stats are an endpoint; acc-01 and acc-02 run this exact free-search, paid-reveal pattern. source
Databar C
Databar, Inc.
Run conditions limit which rows get enriched, the enrichment shows an expected total before running, a flow cost estimate endpoint returns a min and max, and GET /v1/user/me gives the balance. source
Gojiberry D
SUPERFRUITS SAS
Search is free with partial fields and an AI intent score, reveal costs a stated 0.5 credit a lead and takes chosen ids only; if the balance falls short only the first affordable leads are revealed and charged, as documented. source
Hunter API + MCP C
Hunter Web Services, Inc.
Discover and email-count are free, X-Credits-Used reports each call's cost (0 for a repeat in the billing period), and the finder charges nothing on a miss, so an agent can qualify free and pay only for found emails. source
LeadMagic API + MCP B
Lead Magic Corporation
Search stats are free, search returns no contact values, /v1/batch/preview-cost is a free dry run, credit budgets cap spend, and credit history is an endpoint, so reveals happen only for chosen rows. source
RocketReach API D
RocketReach, LLC
Search costs nothing over MCP and filters on contact availability, lookup_type picks which data to pay for, misses and B or F grade emails aren't charged, and the account tool reports balances. source

Does the job, with a limit 12

It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.

ListingWhy
Clay C
Clay Labs Inc.
Search then run a function on the shortlist is a documented recipe and GET /credits/balance gives the balance, but there is no cost estimate before a routine run, and acc-04 had to impose its own ordering and caps to keep spend predictable. source
Coresignal API + MCP B
Deeptrace Inc.
Search is free and every collect has a fixed published credit cost with x-credits-remaining on each response, but free search returns IDs only, so filtering on preview fields costs 20 credits a page. source
Crustdata API + MCP D
Crustdata Inc.
GET /account/endpoints lists every price free, X-Credits-Used reports each call, and contact types are billed only when requested, but search is not free at 0.03 a result and contact reveal is Enterprise only. source
Dievio F
Dievio
Count Preview is free, max_results caps spend and charges follow returned rows, but a low API balance shrinks the page with no error, which is the map's named blocker for this listing. source
Enrich Layer API + MCP C
Vertical Int, Inc.
Each operation's x-credits gives its cost and credit-balance is free, but search bills 3 credits per result, so there is no free preview to qualify against. source
Explorium AgentSource E
Explorium Ltd.
Statistics give a free count, contact fields are requested explicitly, and per-call credit usage can be returned inline, but every fetched row costs 1 credit, so qualifying on fetched fields is never free. source
FullEnrich API + MCP B
FullEnrich Corp
Search returns a total and a balance endpoint exists, and enrichment only charges for found data, but search rows cost 0.25 credits each and no cost estimate before an enrichment is documented. source
Fuse MCP D
FuseAI, LLC
Counts and GET /business/data/pricing are free, the usage ledger reports spend by product and day, and finding charges only for values found, but search rows cost 1 credit each and every MCP call needs 100 credits in the balance. source
Lusha API + MCP B
Lusha Systems Inc.
Search returns previews with canReveal giving each field's credit cost (0 if already revealed) and isCreditCharged reports billing, but search results are themselves charged per result, so filtering isn't free. source
People Data Labs C
People Data Labs, Inc.
Autocomplete and the sandbox are free and enrichment charges only on a match, but search bills every record returned, with no free count or cost estimate documented. source
Prospeo API + MCP D
Defastra Tech Inc.
Search returns person and company previews at 1 credit per 25, repeat pages are free for 30 days, and enrich can be limited to verified emails or mobiles so misses aren't charged, but there is no free search or cost estimate. source
ZoomInfo API + MCP BB
ZoomInfo Technologies LLC
Search, lookup and similar-record calls are free and the docs tell agents to state worst-case credits before enriching, but there is no cost preview call, and free-tier records aren't kept under management, so re-enrichment can bill again. source

Doesn't do this job 4

Listings in the category that do something else, with the reason.

ListingWhy
Clearbit F
HubSpot, Inc.
No public search or reveal endpoints for new customers, and no published credit model to preview. source
Dropcontact API + MCP C
Dropcontact SAS
No search or preview step; every call is a paid enrichment of a record you supply. source
FullContact E
J2 Martech Corp.
No search, preview or cost estimate; every call is a paid enrichment counted against the account. source
ZeroBounce B
Hertza L.L.C.
No search or reveal step; nothing to qualify before paying. source

What stops agents finishing

  • no cost preview before a paid MCP call (zoominfo)
  • failed calls still billed (acc-19)
  • low balance returns fewer rows with no error (dievio)

Around it

Before: lead-data.prospect-list-by-filter, decision-models.score-lead. After: lead-data.find-work-email, lead-data.verify-before-send.

Where this comes from

Weight 8 of 100 in Lead & company data: 5 of 39 accounts (acc-01, 02, 03, 04, 05); the pattern every agent-built pipeline in the accounts converged on

The same as data: /api/v1/use-cases/lead-data.qualify-then-reveal.json, or the MCP tool get_use_case with id lead-data.qualify-then-reveal. Other jobs in this category: /api/v1/niches?category=lead-data.

Draft, read 2026-11-12 from public docs and first-hand accounts, not yet reviewed by a person. A mark says what the docs show, not what a run measured.

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.