Service card

GitHub API

github.com · Free

APIMCPoauthfree

Capabilities

connector · code repository · enrichment

Verified outcome telemetry

Probe + outcome evidence. Blank fields are honest gaps, not zeros.

Evidence for GitHub API
AttestationSeed (curated, not yet probed)
p50 latencyNot yet probed
p95 latencyNot yet probed
Success rateNot yet probed
Schema conformanceNot yet probed
Idempotencyunknown
Replay safetyunknown
Last probeNot yet probed

Policy flags

external_networkstores_datacode_execution

Operator review checklist

Derived from service-card facts. These prompts guide review; they do not create benchmark evidence.

Source and route-surface drift

Use when endpoint surfaces, marketplace snapshots, or seller-controlled catalogs may change route decisions.

Endpoint URL is route-decision material.MCP availability can change independently from provider count.
Source and route-surface drift field prompts
source_nameTie vendor claims to the feed or directory that made them.
source_service_countCapture catalog size at review time.
source_endpoint_countDetect callable-surface changes without a service-count change.
stackbroker_first_seenSeparate Stackbroker observation from vendor labels.
last_verified_route_surfaceMark the last date the callable surface was checked.
source_churn_summarySummarize added, removed, or materially changed endpoints.
seller_controlled_ranking_riskFlag when discovery, ranking, payment, and proof claims share an owner.
  • What changed since the prior snapshot: endpoints, pricing, auth, payment rail, receipt path, or policy terms?
  • Can a buyer reconstruct which endpoint set was available when the route decision was made?
  • Would a stale marketplace snapshot change the route decision or policy outcome?

Runtime payment skills

Use when an MCP tool, connector, wallet, or gateway can initiate or authorize spend for an agent.

MCP surface has a paid or credentialed rail.OAuth or connector custody needs revocation and approval review.
Runtime payment skills field prompts
runtime_skill_spend_surfaceDistinguish payment-capable skills from ordinary service providers.
wallet_or_key_custody_modelIdentify whether credentials are local, hosted, delegated, or user-held.
policy_controlsList budgets, allowlists, approval gates, rate limits, and per-task caps.
approval_surfaceState whether spend is automatic, user-confirmed, admin-approved, or externally authorized.
revocation_freshnessCapture how quickly revoked permission takes effect.
receipt_surfaceDescribe transaction history, receipt URLs, signed receipts, webhooks, or audit tools.
payment_metadata_exposureFlag prompt, PII, task context, or policy leakage into payment metadata.
security_review_requiredGate install/use until dependency, key-handling, and bypass risks are reviewed.
  • Can the skill spend without an explicit confirmation after setup?
  • Which recipients, assets, networks, and facilitators are allowed by default?
  • What proof does the agent receive after payment, and is it portable outside the skill?