Niches · Agent tool access

Call a paid provider or site action without a key per provider

One company's docs show a full fit.

1companies, full fit
3companies, fit with a limit
47companies carry the tag
4share of the category's work
0first-hand accounts

What counts as done

A provider or action chosen and run, charged once to one balance, with the price known before the call.

Measured, for our own tests: this takes one or two calls. No docs we read state these figures, so they don't count against a listing here.

How agents ask for it: scrape this with whatever is cheapest, order dinner on the site I use, pick a tool for this job

Does the job 1

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

ListingWhy
AgentWeb D
Agent Web Labs, Inc.
$0.05 per completed action from one shared balance, failed actions refunded, get_usage shows whether calls were charged, and an Idempotency-Key on REST retries charges once. source

Does the job, with a limit 3

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
Composio (API + MCP) A
Sampark Inc (d/b/a Composio)
Instant tools run on Composio's own accounts for search, media, enrichment and research, paid from credits, but the pages read give no per-tool price before the call. source
letme BB ours
Long Lunch Labs Limited (company number 17523112, registered in England and Wales, incorporated 15 October 2026), trading as Anchor Terminal and letme
One call picks a provider by a published rule with keyless=1, x402=yes and max= price filters and shows the price. letme holds no balance or cap and forwards nothing; the agent pays the pick itself, and calling through letme comes later. source
Monid C
Monid, Inc.
One prepaid balance or x402, price shown in discover and inspect, maxCost refuses a run above the estimate, workspace budgets block runs, and provider errors pass through with their status. It takes three calls, and with no idempotency key a resent run bills again. source

Doesn't do this job 7

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

ListingWhy
MCP Gateway BB
No legal entity found. COMMERCIAL.md, CLA.md and AUTHORSHIP.md name Mikko Parkkola, Finland, as licensor and author
It sells no provider calls; per-key budgets limit spend on backends the operator already pays for. source
Merge Agent Handler BB
Merge API, Inc.
Credits pay for tool calls on the user's own connected apps; no paid provider is called on Merge's account. source
One B
One Systems, Inc.
Actions run on the user's own connected apps; One sells no paid provider calls on its own account. source
Smithery F
Clavia, Inc. (doing business as Smithery)
Nothing is sold; the service is shut down. source
StackOne B
StackOne Technologies Limited
Credits pay for calls on customers' own linked accounts; StackOne sells no provider calls on its own account. source
Unified.to MCP Server B
Unified API Inc.
Calls run on tenants' own connected apps under a plan from $750 a month; no provider calls are sold. source
Zapier MCP (agent actions) C
Zapier Inc.
Each call runs on the person's own app connection; the 2-task price is known, but no paid provider is called without the person's own account. source

1 listings in the category were added after this reading and aren't marked yet.

What stops agents finishing

  • no balance cap
  • site terms put on the user

Around it

After: web-scrapers.page-to-markdown.

Where this comes from

Weight 4 of 100 in Agent tool access: No first-hand account; rests on Monid, AgentWeb and letme vendor pages only

The same as data: /api/v1/use-cases/aggregator.paid-call-without-keys.json, or the MCP tool get_use_case with id aggregator.paid-call-without-keys. Other jobs in this category: /api/v1/niches?category=aggregator.

Draft, read 2026-11-15 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.