MCP.Market

Mercantry Registry MCP server

online · 100% uptime
by mercantry.org·org.mercantry/registry·v0.1.0

Agent-native registry: 168k+ real restaurants in LA, Hong Kong & Tokyo. Unranked, honest signals.

B79/100grade B
What users say
No reviews yet
Be the first
Safety scan
B79/100

full report

Adoption
New

0 stars

Reviews

Write one

Nobody has reviewed Mercantry Registry yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Mercantry Registry tools (9, 2 write)

write = sends, deletes, buys or posts
  • cancel_bookingwrite actionFree

    Cancel a booking in any non-terminal state, or a confirmed reservation (the registry notifies the merchant). Cancellation is mandatory when the human no longer wants the table — no-shows destroy merchant trust and are tracked per developer key.

  • get_availabilityFree

    V1 does NOT hold live table availability — availability is checked on the phone call at booking time. This tool returns the merchant's reservation policy, structured hours, and holiday exceptions so you can pick a plausible time before calling place_booking.

  • get_booking_statusFree

    State machine position for a booking: pending → queued → in_progress → confirmed | failed | needs_input (plus cancelled). Includes structured details on confirmation (confirmed_time, confirmation_code, merchant_instructions), structured failure reason (no_answer | fully_booked | closed | policy_mismatch | merchant_declined | bad_data), or needs_input options awaiting your decision. include_events=true returns the full audit log.

  • get_merchantFree

    Every field the registry holds on one merchant: schema fields, structured hours, raw feedback history, platform-observed operational stats, and per-field provenance with timestamps. Maximal data, zero opinion — the registry never scores or ranks.

  • get_registry_metaFree

    Evaluate the registry itself: per-city coverage (with each city's IANA timezone), merchant/bookable counts, verification and freshness stats, feedback corpus size, schema version, and the documented deterministic ordering rule. Honest by design — including how stale the data is.

  • modify_bookingFree

    Amend a booking before or after the call. For a booking in needs_input: pass accept_option_index to take one of the merchant's offered times (confirms immediately), or pass a new datetime/party_size to re-queue an amended request. Modifying an already-confirmed booking cancels it and books the new request (new booking_id returned).

  • place_bookingFree

    Request a table reservation. Returns booking_id with state 'queued' immediately; fulfillment is asynchronous (a call is placed to the merchant). Poll get_booking_status or supply callback_url for webhooks. RETRY SAFETY: pass a unique client_reference_id (recommended: always); if this call times out or errors ambiguously, retry with the SAME client_reference_id and the registry returns the already-created booking instead of double-booking the restaurant. Never re-call place_booking after a timeout without one. If the merchant counter-offers a time within window_minutes and accept_within_window=true, it is auto-accepted (recommended). Otherwise the booking pauses in needs_input for you to resolve via modify_booking. Merchants on the human_call channel are fulfilled by a human operator during the operator window published in get_registry_meta — those bookings queue until worked (up to the channel SLA), so book ahead rather than for the next hour.

  • search_merchantsFree

    Filter-based search over the restaurant registry (coverage cities + timezones in get_registry_meta). NOT ranked: results come back in deterministic order (merchant_id ASC by default; distance ASC when lat/lng given and order_by="distance"). Returns compact records with pagination. Use get_merchant for the full signal dump on a specific merchant. All filters are optional and combinable.

  • submit_feedbackwrite actionFree

    Report how a confirmed reservation actually went. Accepted only against a confirmed booking_id, once per booking, within 14 days of confirmation. Structured fields first; optional free text ≤ 500 chars. This corpus is served raw to all agents via get_merchant — it is never editorialized or turned into a score.

Public scan report

scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it

1 high
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 591ms20/20
  • Tool poisoning9 tool descriptions checked15/15
  • Auth qualityopen endpoint exposes 2 write-action tools with no auth3/15
  • Maintenancelast push 61 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; website matches verified namespace9/10

Findings (1)

  • highWrite-action tools reachable without authenticationauth.open-write
Overall 79/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Mercantry Registry compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
79/100
higher than 58% of 4,460 AI and agents servers
Tools
9
the typical AI and agents server has 6
Tools that change things
22%
typical: 0%. Fewer write tools means less an agent can break
Uptime
100%
of our recent checks; the typical remote AI and agents server answers 100%
Response time
72 ms
faster than 92% of 2,331 AI and agents servers

What its tools let an agent do: 6 read · 2 change · 1 delete

Install Mercantry Registry in Claude Code, Cursor or VS Code

claude mcp add --transport http registry https://mercantry.org/mcp
Add to Cursor

What the publisher says

From the Mercantry Registry repository's README, as published. We do not edit it. Read it on GitHub

Mercantry

Mercantry is an open commerce registry for AI agents — structured merchant data, honest signals, and real-world booking fulfillment.

Current status — read this first.

Mercantry is pre-launch. What is real and what is not, precisely:

- The merchant data is real: 168,000+ restaurants across Los Angeles, Hong Kong, and Tokyo, built exclusively from openly licensed sources (Overture Maps CDLA-P-2.0 + official government registers), conflated with per-field provenance and QA-gated versioned releases. Live counts: getregistrymeta.

- Real merchants are discovery-only for now: placebooking against a real merchant returns the structured rejection fulfillmentnot_live. A booking guard makes it structurally impossible for our booking simulator to dial a real restaurant.

- The booking loop is testable end-to-end against sandbox: true merchants — fictional records with deterministic outcomes ("test cards for bookings"). Do not call sandbox phone numbers; they are not real businesses.

- Fulfillment, when it launches, is human-operated phone booking on a phone-verified merchant tranche (voice automation is deferred). Outbound-calling sections of the spec operate only after legal review — publication of the spec is not operation.

- Mercantry is built and operated by a team of AI agents with human oversight, stated here as a fact rather than a gimmick.

Connect your agent

The live endpoint serves MCP over Streamable HTTP:

claude mcp add --transport http mercantry https://agentic-commerce-registry.fly.dev/mcp
  • REST mirror: /v1 — self-describing via /v1/openapi.json
  • Discovery manifest: /.well-known/mcp.json · agent card: /.well-known/agent-card.json · health: /healthz · PII-free ops stats: /v1/stats · privacy policy: /privacy · demo & reviewer guide: /demo
  • Keys are optional (abuse control, not gating): POST /v1/keys with developer_name + contact. All reads are free and unauthenticated.
  • Bulk export encouraged: GET /v1/export/merchants.ndjson — caching, embedding, and training on the data are permitted under the open license.

Copy-paste integrations — curl, Claude Code/Desktop, raw MCP JSON-RPC, OpenAI Agents SDK, LangChain, webhook receiver: examples/. Agent-first tool documentation with example transcripts: docs/mcp-tools.md. If you are an agent working in this repo, read AGENTS.md.

MCP tools

searchmerchants (filter-based, never ranked, deterministic documented order) · getmerchant (full signal dump: every field, raw feedback history, operational stats, per-field provenance) · getavailability (honest: performedatbooking) · placebooking (async) · getbookingstatus · modifybooking · cancelbooking (mandatory when plans change — no-shows are tracked per developer key) · submitfeedback (confirmed bookings only, once, within 14 days) · getregistry_meta (evaluate the registry itself, staleness included)

Run it yourself

npm install
npm run dev        # seeds a sandbox corpus on first boot; everything in one process
npm test           # full suite
npm run typecheck

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Mercantry Registry: common questions

Is Mercantry Registry MCP server safe?
Mostly: it is graded B (79/100). Read the Mercantry Registry safety report
How do I install Mercantry Registry?
It runs remotely at mercantry.org. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Mercantry Registry need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Mercantry Registry maintained?
The last commit was 101 days ago (2026-07-26). The latest release is v0.1.0.
Is Mercantry Registry up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of Mercantry Registry?
Servers from other publishers that do the same job: Agent-Native Slides MCP server and Ts Core MCP server.
How does Mercantry Registry compare with other AI and agents MCP servers?
safety score 79/100 (higher than 58% of 4,460 AI and agents servers); tools 9 (the typical AI and agents server has 6); tools that change things 22% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Mercantry Registry

Same job from other publishers: the closest match first, then the best rated.