Tako · Agentic Access

Tako Agentic Access

x-agentic-access generated

Tako exposes 13 API operations that an AI agent could call, of which 6 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: 7 read and 6 write.

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.

CompanyAIDataSearchAnswer EngineFinancial DataKnowledge GraphAgentsMCPData Visualization
Operations: 13 Acting: 6 Human-in-the-loop: 0 Method: generated

By consequence

read 7 write 6

Source

Agentic Access

Raw ↑ 
generated: '2026-07-21'
method: generated
source: openapi/tako-openapi-original.yml
audience: null
note: >-
  Recommended x-agentic-access execution contracts, classified per operation from
  the Tako OpenAPI (Curity Access Intelligence model). GET/HEAD → connected/read;
  write-method POSTs → acting/write. No operation is payment/transfer/safety-critical
  at the API-operation level (Tako's machine-payments surface is billing metadata,
  not a transfer endpoint). A governance starting point, not an authoritative
  provider claim.
summary:
  operations: 13
  by_action_class:
    connected: 7
    acting: 6
  by_consequence:
    read: 7
    write: 6
  human_in_the_loop: 0
  audit_required: 6
operations:
  - operationId: graphSearch
    method: GET
    path: /beta/graph/search
    action_class: connected
    consequence: read
    token: {ttl_seconds: 3600}
  - operationId: graphRelated
    method: GET
    path: /beta/graph/related
    action_class: connected
    consequence: read
    token: {ttl_seconds: 3600}
  - operationId: graphNode
    method: GET
    path: /beta/graph/node/{id}
    action_class: connected
    consequence: read
    token: {ttl_seconds: 3600}
  - operationId: listAnswerAgentRuns
    method: GET
    path: /v1/agent/answer/runs
    action_class: connected
    consequence: read
    token: {ttl_seconds: 3600}
  - operationId: getAnswerAgentRun
    method: GET
    path: /v1/agent/answer/runs/{run_id}
    action_class: connected
    consequence: read
    token: {ttl_seconds: 3600}
  - operationId: listRetrievalAgentRuns
    method: GET
    path: /v1/agent/retrieval/runs
    action_class: connected
    consequence: read
    token: {ttl_seconds: 3600}
  - operationId: getRetrievalAgentRun
    method: GET
    path: /v1/agent/retrieval/runs/{run_id}
    action_class: connected
    consequence: read
    token: {ttl_seconds: 3600}
  - operationId: search
    method: POST
    path: /v3/search
    action_class: acting
    consequence: write
    token: {ttl_seconds: 900}
    audit: required
  - operationId: answer
    method: POST
    path: /v1/answer
    action_class: acting
    consequence: write
    token: {ttl_seconds: 900}
    audit: required
  - operationId: contents
    method: POST
    path: /v1/contents
    action_class: acting
    consequence: write
    token: {ttl_seconds: 900}
    audit: required
    note: Meters/bills a card CSV export beyond the free row allowance.
  - operationId: createCard
    method: POST
    path: /v1/thin_viz/create/
    action_class: acting
    consequence: write
    token: {ttl_seconds: 900}
    audit: required
  - operationId: createAnswerAgentRun
    method: POST
    path: /v1/agent/answer/runs
    action_class: acting
    consequence: write
    token: {ttl_seconds: 900}
    audit: required
    note: PAYMENT_REQUIRED (402) pre-dispatch credit gate.
  - operationId: createRetrievalAgentRun
    method: POST
    path: /v1/agent/retrieval/runs
    action_class: acting
    consequence: write
    token: {ttl_seconds: 900}
    audit: required
    note: PAYMENT_REQUIRED (402) pre-dispatch credit gate.