Niches · Restaurant & local bookings

Take bookings for a venue as its phone or chat agent

Two or three companies' docs show a full fit.

2companies, full fit
3companies, fit with a limit
12companies carry the tag
20share of the category's work
9first-hand accounts

What counts as done

Availability searched and an appointment or reservation created, changed or cancelled in the venue's own calendar through the API, with the venue's no-show and deposit rules applied, on the venue's current plan.

Measured, for our own tests: zero overlapping bookings when two creates for the same slot run at once. No docs we read state these figures, so they don't count against a listing here.

How agents ask for it: answer the salon's calls and book people in, rebook all of Devon's clients, he's off Thursday, let customers book from our own app

Does the job 2

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

ListingWhy
OpenTable APIs F
OpenTable
The In-House Booking (Voice AI) API covers availability, booking lock, create with credit-card hold, change, lookup, cancel and status, with X-Request-Id idempotency on writes. source
TheFork B2B API E
La Fourchette SAS
Built for AI phone agents: timeslots, create, update and cancel in TheFork Manager, guarantee requests sent to the diner, and 409 DOUBLE_BOOKING on conflicts. 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
Eat App Partner API E
EAT APPLICATION DMCC
Availability, create, update, cancel, table_ids that fail with 422 when taken and payment reporting all exist, but the context records API access as an Enterprise or add-on item priced through sales, which this pass did not re-read. source
Square Appointments (Bookings API) BB
Block, Inc.
Seller-level create, update and cancel work into the live calendar (acc-07), but need Appointments Plus or Premium or return 403, no-show-fee services are excluded, and acc-26 saw concurrent creates both ACCEPTED, below the zero-overlap bar. source
TableCheck API C
TableCheck Inc.
Booking v1 serves merchant-owned flows with blockages, amend and cancel, but has no payments support, so deposit rules can't be applied, and POST reservations has no idempotency key. source

Couldn't check 2

The docs were closed to us, or silent. These carry no mark either way.

ListingWhy
Resy F
Resy Network, Inc.
acc-10 reports API keys are issued to venues, but no venue API documentation is public, so endpoints and plan rules could not be read. source
SevenRooms F
SEVENROOMS LLC
SevenRooms advertises a booking API and voice partners, but the public docs are an empty index (the llms.txt points to a page with a title only), so endpoints and limits could not be read. source

Doesn't do this job 3

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

ListingWhy
Chope F
The Chope Group Pte Ltd
No venue API is documented on chope.co. source
Tock F
Tock LLC
No documented write endpoints for a venue's agent; the docs index says docs are coming. source
Treatwell F
Treatwell Limited
No partner API documentation is public; the supplier pages are contract terms, not an integration guide. source

What stops agents finishing

  • writes fail with 403 unless the venue pays for a higher plan
  • a service with a no-show fee cannot be booked through the API
  • each venue runs a different booking platform with its own integration

Around it

Before: voice-agents.answer-call, messaging.receive-sms. After: messaging.send-confirmation, crm.upsert-contact.

Where this comes from

Weight 20 of 100 in Restaurant & local bookings: 9 of 30 counted accounts; all but one on Square's developer forum, so the weight leans on one vendor's API

The same as data: /api/v1/use-cases/local-bookings.venue-booking-agent.json, or the MCP tool get_use_case with id local-bookings.venue-booking-agent. Other jobs in this category: /api/v1/niches?category=local-bookings.

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.