Olipop · Agentic Access

Olipop Agentic Access

x-agentic-access searched

Olipop exposes 13 API operations that an AI agent could call, of which 8 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: 5 read, 5 write, and 3 physical.

1 operation 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.

BeverageConsumer Packaged GoodsDirect to ConsumerE-CommerceRetailAgent CommerceUniversal Commerce ProtocolMCPGraphQLShopifyprebiotic-sodaFunctional Beverage
Operations: 13 Acting: 8 Human-in-the-loop: 1 Method: searched

By consequence

read 5 write 5 physical 3

Source

Agentic Access

olipop-agentic-access.yml Raw ↑ 
generated: '2026-07-31'
method: searched
source: https://drinkolipop.com/llms.txt
also_from:
- https://drinkolipop.com/agents.md
- https://drinkolipop.com/robots.txt
- https://ucp.dev/2026-04-08/services/shopping/mcp.openrpc.json
notes: >-
  Unusually for this pipeline, the agentic-access contract here is SEARCHED rather than generated: OLIPOP
  actually publishes agent access guidance on its own domain, in three mutually consistent places
  (/llms.txt, /agents.md and comments at the top of /robots.txt). The operations classified below are the
  UCP shopping tools its merchant profile declares, and the escalation rules are the provider's own stated
  rules rather than our recommendations. Where a field is our classification rather than a published claim,
  it is marked derived_classification.
policy_summary:
  agents_welcome: true
  agent_identity_required: true
  identity_mechanism: UCP-Agent profile URL (meta["ucp-agent"].profile)
  read_without_enrollment: true
  purchase_without_human_approval: false
  preferred_agent_path: UCP/MCP at https://drinkolipop.com/api/ucp/mcp
  recommended_alternative: https://shop.app/SKILL.md (Shop skill / Shop Pay, for personal shopping agents)
  prohibited:
  - scripted checkout form fills
  - browser automation that finalizes payment
  - end-to-end agent flows that place an order without contemporaneous human approval
  - screen-scraping the storefront where the UCP/MCP or Shop skill path is available (discouraged, not
    prohibited)
  published_verbatim_rule: >-
    "Checkout requires human approval. Agents must not complete payment without explicit buyer consent. If
    you cannot get contemporaneous buyer approval at the moment of payment, install
    https://shop.app/SKILL.md and route the purchase through Shop Pay instead."
summary:
  operations: 13
  by_action_class:
    connected: 5
    acting: 8
  by_consequence:
    read: 5
    write: 5
    physical: 3
  human_in_the_loop_required: 1
  audit_required: 8
  idempotency_required: 3
operations:
- operation: search_catalog
  surface: ucp-mcp
  action_class: connected
  consequence: read
  scope: catalog:read
  audit: optional
  human_in_the_loop: not-required
  token_ttl_max_seconds: 3600
- operation: lookup_catalog
  surface: ucp-mcp
  action_class: connected
  consequence: read
  scope: catalog:read
  audit: optional
  human_in_the_loop: not-required
  token_ttl_max_seconds: 3600
- operation: get_product
  surface: ucp-mcp
  action_class: connected
  consequence: read
  scope: catalog:read
  audit: optional
  human_in_the_loop: not-required
  token_ttl_max_seconds: 3600
- operation: get_cart
  surface: ucp-mcp
  action_class: connected
  consequence: read
  scope: cart:read
  audit: optional
  human_in_the_loop: not-required
  token_ttl_max_seconds: 3600
- operation: get_checkout
  surface: ucp-mcp
  action_class: connected
  consequence: read
  scope: checkout:read
  audit: optional
  human_in_the_loop: not-required
  token_ttl_max_seconds: 3600
- operation: get_order
  surface: ucp-mcp
  action_class: connected
  consequence: read
  scope: order:read
  audit: required
  human_in_the_loop: not-required
  token_ttl_max_seconds: 3600
  note: returns buyer PII (addresses, contact details); treat as sensitive read
- operation: create_cart
  surface: ucp-mcp
  action_class: acting
  consequence: write
  scope: cart:write
  audit: required
  human_in_the_loop: not-required
  token_ttl_max_seconds: 900
- operation: update_cart
  surface: ucp-mcp
  action_class: acting
  consequence: write
  scope: cart:write
  audit: required
  human_in_the_loop: not-required
  token_ttl_max_seconds: 900
- operation: cancel_cart
  surface: ucp-mcp
  action_class: acting
  consequence: write
  scope: cart:write
  audit: required
  human_in_the_loop: not-required
  idempotency_key: required
  token_ttl_max_seconds: 900
- operation: create_checkout
  surface: ucp-mcp
  action_class: acting
  consequence: write
  scope: checkout:write
  audit: required
  human_in_the_loop: not-required
  token_ttl_max_seconds: 900
- operation: update_checkout
  surface: ucp-mcp
  action_class: acting
  consequence: write
  scope: checkout:write
  audit: required
  human_in_the_loop: not-required
  token_ttl_max_seconds: 900
  note: sets shipping address and delivery method; carries buyer PII
- operation: cancel_checkout
  surface: ucp-mcp
  action_class: acting
  consequence: physical
  scope: checkout:write
  audit: required
  human_in_the_loop: recommended
  idempotency_key: required
  token_ttl_max_seconds: 300
  note: derived_classification - cancelling a checkout is money-adjacent and irreversible from the agent's
    side; the provider does not classify it explicitly
- operation: complete_checkout
  surface: ucp-mcp
  action_class: acting
  consequence: physical
  scope: checkout:complete
  audit: required
  human_in_the_loop: required
  purpose_required: true
  idempotency_key: required
  token_ttl_max_seconds: 300
  note: PUBLISHED RULE, not a recommendation - the provider states that payment may not be completed
    without explicit contemporaneous buyer consent
read_only_surface:
  description: Endpoints an agent may use with no enrollment, identity or token at all.
  operations:
  - 'GET /products.json'
  - 'GET /products/{handle}.json'
  - 'GET /collections/{handle}/products.json'
  - 'GET /search?q={query}&type=product'
  - 'GET /collections/all'
  - 'GET /sitemap.xml'
  action_class: connected
  consequence: read
  audience: null
  source: https://drinkolipop.com/llms.txt
rate_limiting:
  scope: per IP
  signal: HTTP 429
  guidance: back off on 429 responses
  published_limit: not disclosed
buyer_context_required:
- context.address_country
- context.currency
x-evidence:
  fetched: '2026-07-31'
  probes:
  - {url: 'https://drinkolipop.com/llms.txt', http_status: 200}
  - {url: 'https://drinkolipop.com/agents.md', http_status: 200}
  - {url: 'https://drinkolipop.com/robots.txt', http_status: 200}

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=olipop-agentic-access&limit=10"
Everything under a tag 
curl "https://apis.io/api/v1/tags/olipop-agentic-access"

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

Get an API key

Free tier, no email required.

GitHub Google LinkedIn

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