Verse (autonomous agent) · Agentic Access

Verse (autonomous agent) Agentic Access

x-agentic-access searched

Verse (autonomous agent) exposes 12 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: 6 read and 6 physical.

6 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.

CompanyAI AgentsAutonomous AgentsA2Ax402Agentic CommerceForecastingPredictionsCalibrationFinancial AnalysisSEC EDGARBlockchainBaseAgent-Native
Operations: 12 Acting: 6 Human-in-the-loop: 6 Method: searched

By consequence

read 6 physical 6

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
physical required
physical required
physical required
physical required
physical required
physical required

Source

Agentic Access

verse-me-com-agentic-access.yml Raw ↑
generated: '2026-09-19'
method: searched
source: https://api.verse-me.com/.well-known/agent.json — AGP extension capabilitiesAnnounced[] policies + urn:verse:agent-extensions:v1 endpoint list + securityRequirements
description: >-
  Recommended x-agentic-access execution contracts for the twelve operations Verse's agent card names. There is no
  OpenAPI, so the heuristic derive-agentic-access.py could not run; the action-class and auth requirement are read
  from the provider's OWN Agent Gateway Protocol policy block (requiresAuth, cost, mode, dataScope per capability)
  and its securityRequirements (public vs x402Payment per skill), which is why the method is searched rather than
  generated. consequence is API Evangelist's reading: every paid call is an irreversible on-chain USDC transfer with
  no published refund path, so paid operations are rated physical with human-in-the-loop required and a token TTL
  ceiling of 300s; the free calibration/reputation reads are connected/read. TTL ceilings mirror the agentic-access
  Spectral ruleset. A governance starting point, not a provider claim; audience is left null to bind per deployment.
  See research/curity/agentic-governance/.
audience: null
custody_note: >-
  The caller pays from a wallet it controls; Verse never holds a caller credential. The consequence ratings describe
  what a signed x402 payment does once broadcast — it is final — not what Verse can do with the caller's keys.
summary:
  operations: 12
  by_action_class:
    connected: 6
    acting: 6
  by_consequence:
    read: 6
    physical: 6
  human_in_the_loop_required: 6
  provider_policy:
    capabilities_announced: 3
    requiresAuth_false: 2
    requiresAuth_true: 1
    payment_gated_skills: 3
    public_skills: 3
operations:
- operation: GET /expertise/calibration
  skill: calibration_track_record
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    provider-policy: {capability: 'expertise:calibration', requiresAuth: false, cost: 0, dataScope: aggregate_only}
- operation: GET /expertise/calibration/signed
  skill: signed_calibration
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    provider-policy: {capability: 'expertise:calibration:signed', requiresAuth: false, cost: 0, provenance: ed25519, dataScope: aggregate_only}
- operation: GET /expertise/calibration/history
  skill: calibration_history
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    provider-policy: {security: public}
- operation: GET /expertise/calibration/history/signed
  skill: calibration_history
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    provider-policy: {security: public, provenance: ed25519}
- operation: GET /reputation
  skill: null
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    provider-policy: {security: public (proof bundle)}
- operation: POST /expertise/consultation/price-estimate
  skill: consultation (preview)
  x-agentic-access:
    action-class: connected
    consequence: read
    subject: optional
    token:
      max-ttl: 3600
    audit: none
    dry-run-for: POST /expertise/consultation
    provider-policy: {security: public, listed under freeEndpoints as "Preview cost before paying"}
- operation: POST /expertise/consultation
  skill: consultation
  x-agentic-access:
    action-class: acting
    consequence: physical
    subject: required
    purpose-required: true
    token:
      max-ttl: 300
      exchange: required
    escalation:
      human-in-the-loop: required
      reason: irreversible on-chain USDC payment ($3–$50 published); no refund or cancel path published; price is dynamic
    audit: required
    provider-policy: {capability: 'expertise:consultation', requiresAuth: true, cost: 0.1 (disagrees with the skill's $3–$50), mode: async, paymentProtocol: x402, paymentNetwork: 'eip155:8453', paymentAsset: USDC, provenance: ed25519}
- operation: POST /expertise/consultation (strategy_recommendation)
  skill: strategy_recommendation
  x-agentic-access:
    action-class: acting
    consequence: physical
    subject: required
    purpose-required: true
    token:
      max-ttl: 300
      exchange: required
    escalation:
      human-in-the-loop: required
      reason: paid via x402 with NO published price; the caller cannot bound the spend from the card
    audit: required
    provider-policy: {security: x402Payment}
- operation: POST /expertise/epistemic-audit
  skill: epistemic_audit
  x-agentic-access:
    action-class: acting
    consequence: physical
    subject: required
    purpose-required: true
    token:
      max-ttl: 300
      exchange: required
    escalation:
      human-in-the-loop: required
      reason: paid via x402 with NO published price; irreversible
    audit: required
    provider-policy: {security: x402Payment}
- operation: POST /expertise/edgar (index)
  skill: edgar_financial_intelligence
  x-agentic-access:
    action-class: acting
    consequence: physical
    subject: required
    purpose-required: true
    token:
      max-ttl: 300
      exchange: required
    escalation:
      human-in-the-loop: required
      reason: on-chain payment ($0.01 published); irreversible even at this size
    audit: required
    provider-policy: {security: x402Payment, price: '$0.01'}
- operation: POST /expertise/edgar (analysis)
  skill: edgar_financial_intelligence
  x-agentic-access:
    action-class: acting
    consequence: physical
    subject: required
    purpose-required: true
    token:
      max-ttl: 300
      exchange: required
    escalation:
      human-in-the-loop: required
      reason: on-chain payment ($0.05 published); irreversible
    audit: required
    provider-policy: {security: x402Payment, price: '$0.05'}
- operation: POST /expertise/edgar (deep)
  skill: edgar_financial_intelligence
  x-agentic-access:
    action-class: acting
    consequence: physical
    subject: required
    purpose-required: true
    token:
      max-ttl: 300
      exchange: required
    escalation:
      human-in-the-loop: required
      reason: on-chain payment ($0.25 published); irreversible
    audit: required
    provider-policy: {security: x402Payment, price: '$0.25'}

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