FRAYT · Agentic Access

FRAYT Agentic Access

x-agentic-access generated

FRAYT exposes 8 API operations that an AI agent could call, of which 7 are state-changing ‘acting’ operations. This is a recommended x-agentic-access execution contract — the scope, audience, consequence tier, short-lived token constraints, and escalation each action should carry before it is handed to an autonomous agent.

By consequence: 1 read and 7 safety-critical.

7 operations are classed safety-critical and should require human-in-the-loop approval at runtime.

Contracts are classified heuristically from the provider’s OpenAPI and refresh on every APIs.io network build; audience is bound per deployment. The model follows Curity’s Access Intelligence (apidays Munich 2026). Browse every provider’s agent contracts at agentic-access.apis.io.

CompanyLast Mile DeliveryLogisticsCouriersOn-Demand DeliveryShippingFreightSupply ChainTransportationThird Party LogisticsDelivery TrackingWebhook
Operations: 8 Acting: 7 Human-in-the-loop: 7 Method: generated

By consequence

read 1 safety-critical 7

Highest-consequence actions

The physical and safety-critical operations an agent could invoke — the ones that most warrant scoped tokens, tight TTLs, and escalation. Full per-operation contracts are in the source below.

MethodPathConsequenceHuman-in-loop
POST /api/v2.2/matches safety-critical required
POST /api/v2.2/matches/estimate safety-critical required
PATCH /api/v2.2/matches/estimate/{id} safety-critical required
DELETE /api/v2.2/matches/{id} safety-critical required
PATCH /api/v2.2/matches/{id} safety-critical required
PATCH /api/v2.2/matches/{match_id}/stops/{stop_id} safety-critical required
POST /api/v2.2/oauth/token safety-critical required

Source

Agentic Access

Raw ↑
generated: '2026-08-16'
method: generated
source: openapi/frayt-match-estimates-openapi.yml, openapi/frayt-matches-openapi.yml, openapi/frayt-oauth-openapi.yml
description: Recommended x-agentic-access execution contracts, classified heuristically from
  the OpenAPI. A governance starting point for exposing this API to AI agents — review and bind
  audience per deployment. See research/curity/agentic-governance/.
x-apievangelist-review:
  reviewed: '2026-08-16'
  by: enrichment pipeline (human-readable curation note, classifications left unmodified)
  note: >-
    The heuristic classifier raised every write operation on this API to
    consequence "safety-critical" because the FRAYT vocabulary is dense with
    dispatch/delivery keywords. Two of those are over-classified against what the
    operations actually do, and an implementer should downgrade them before use:
    (1) POST /api/v2.2/matches/estimate only PRICES a delivery — it books nothing,
    charges nothing and dispatches nobody, so it is effectively a read;
    (2) POST /api/v2.2/oauth/token is a credential exchange, not a physical action.
    The genuinely consequential operations are POST /api/v2.2/matches and
    PATCH /api/v2.2/matches/estimate/{id} (both dispatch a real driver),
    DELETE /api/v2.2/matches/{id} (irreversible, up to 50% cancellation charge per
    FRAYT's EULA), and PATCH /api/v2.2/matches/{match_id}/stops/{stop_id} (a
    monetary tip change). Those four are correctly flagged.
    Note also that FRAYT supports no idempotency key, which raises the real risk of
    every write here: a retry is a duplicate dispatch. See
    conventions/frayt-conventions.yml.
summary:
  operations: 8
  by_action_class:
    acting: 7
    connected: 1
  by_consequence:
    safety-critical: 7
    read: 1
  human_in_the_loop_required: 7
operations:
- path: /api/v2.2/matches/estimate
  method: post
  operationId: FraytElixirWeb.API.V2x2.MatchEstimateController.create
  x-agentic-access:
    action-class: acting
    consequence: safety-critical
    subject: required
    audience: null
    token:
      max-ttl: 120
      exchange: true
      purpose-required: true
      proof-of-possession: true
    escalation:
      human-in-the-loop: required
    audit: required
- path: /api/v2.2/matches/estimate/{id}
  method: patch
  operationId: FraytElixirWeb.API.V2x2.MatchEstimateController.update
  x-agentic-access:
    action-class: acting
    consequence: safety-critical
    subject: required
    audience: null
    token:
      max-ttl: 120
      exchange: true
      purpose-required: true
      proof-of-possession: true
    escalation:
      human-in-the-loop: required
    audit: required
- path: /api/v2.2/matches
  method: post
  operationId: FraytElixirWeb.API.V2x2.MatchController.create
  x-agentic-access:
    action-class: acting
    consequence: safety-critical
    subject: required
    audience: null
    token:
      max-ttl: 120
      exchange: true
      purpose-required: true
      proof-of-possession: true
    escalation:
      human-in-the-loop: required
    audit: required
- path: /api/v2.2/matches/{id}
  method: delete
  operationId: FraytElixirWeb.API.V2x2.MatchController.delete
  x-agentic-access:
    action-class: acting
    consequence: safety-critical
    subject: required
    audience: null
    token:
      max-ttl: 120
      exchange: true
      purpose-required: true
      proof-of-possession: true
    escalation:
      human-in-the-loop: required
    audit: required
- path: /api/v2.2/matches/{id}
  method: get
  operationId: FraytElixirWeb.API.V2x2.MatchController.show
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
- path: /api/v2.2/matches/{id}
  method: patch
  operationId: FraytElixirWeb.API.V2x2.MatchController.update
  x-agentic-access:
    action-class: acting
    consequence: safety-critical
    subject: required
    audience: null
    token:
      max-ttl: 120
      exchange: true
      purpose-required: true
      proof-of-possession: true
    escalation:
      human-in-the-loop: required
    audit: required
- path: /api/v2.2/matches/{match_id}/stops/{stop_id}
  method: patch
  operationId: FraytElixirWeb.API.V2x2.MatchStopController.update
  x-agentic-access:
    action-class: acting
    consequence: safety-critical
    subject: required
    audience: null
    token:
      max-ttl: 120
      exchange: true
      purpose-required: true
      proof-of-possession: true
    escalation:
      human-in-the-loop: required
    audit: required
- path: /api/v2.2/oauth/token
  method: post
  operationId: FraytElixirWeb.API.OauthController.authenticate
  x-agentic-access:
    action-class: acting
    consequence: safety-critical
    subject: required
    audience: null
    token:
      max-ttl: 120
      exchange: true
      purpose-required: true
      proof-of-possession: true
    escalation:
      human-in-the-loop: required
    audit: required

Work with this as data

Every access contract here is available over the APIs.io API and to AI agents over MCP. Agentic Access is not yet its own endpoint on the v1 API. Reach it through catalog search and the tag graph, or the MCP server.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for agentic access

3 MCP tools reach this
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
Search the catalog
curl "https://apis.io/api/v1/search?q=frayt-agentic-access&limit=10"
Everything under a tag
curl "https://apis.io/api/v1/tags/frayt-agentic-access"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.