agent-discovery-and-routing

Fortune cookie API for AI agents: a fortune written for language models, a lucky number, and a lucky HTTP status — the cheapest possible first x402 purchase. Come for the novelty, stay for the utility grid.

Enables creation and management of automated agent workflows for task execution and orchestration.

Query real-time stablecoin supply yield pools from Barker's index of 500+ DeFi protocols. Returns ranked rows with protocol_name, chain_name, asset_symbol, supply_apy_total (decimal — multiply by 100 for %), and supply_tvl (USD). Use for questions like 'best stablecoin yield', 'where to earn on USDC', 'compare lending rates', '稳定币利率'.

Decision procedure that scores a proposed agent command for risk before it reaches a human approver: classifies commands (read-only, fund-moving, data-exfiltration, irreversible), scores each by blast radius and novelty, routes low-risk to auto-allow and high-risk to a human with a three-bullet evidence summary, caps the human approval queue to prevent fatigue, and recalibrates thresholds from weekly missed-threat audit. Addresses the quantified failure where humans miss one in three threats under approval load.

Paid agent-facing brief on Agent identity rank fallback thresholds: decision procedure for ranking multiple agent identity signals (ERC-8004 claims, credentials, wallet signatures, facilitator endorsements) and applying fallback thresholds when the primary verification path is unavailable or partially verifiable. Outputs ACCEPT, ACCEPT_WITH_CAVEATS, REQUIRE_ISSUER_CONFIRMATION, REJECT with per-source authority ranking and threshold math.. Blunt decision procedure, not marketing.

Premium agentic endpoint for agentphone-ai-mcp.

Premium agentic endpoint for agent-collusion-detector-mcp.

Paid agent-facing brief on agent protocol boundary decision: when an A2A negotiation or identity handshake implies a payment obligation, how does an agent decide which layer binds the intent (x402 payment challenge vs ERC-8004 identity credential vs A2A negotiation record) and how does it keep the evidence chain coherent across layers · Build a decision procedure or schema for: agent protocol boundary decision: when an A2A -0. Blunt decision procedure, not marketing.

Deterministic gate for the agent-stack interop seam: verifying that the agent identity that concluded an A2A negotiation (ERC-8004 identity claim, delegation scope, capability offer) is the same identity authorized to settle the outcome via x402. Ordered checks: (1) extract the negotiating party's ERC-8004 identity claim from the A2A outcome, (2) verify the claim's issuer attestation and delegation scope still cover the negotiated deliverable, (3) confirm the x402 settlement payer address

News Gurus Intel API — liveness probe: per-agent intelligence output counts over the last 24h with last-seen timestamps, across the 40+ data agents. Verify the engine is live before buying data — same price tier as /x402/regime. Educational data, not financial advice.

Check whether a domain allows AI usage of its content before you crawl: parses robots.txt Content-Signal and aipref directives (search / ai-input / ai-train) into structured JSON with a plain-English interpretation. Essential pre-flight for scraping, RAG, and training-data agents — especially after Cloudflare's Sept 15, 2026 default gating.

Deterministic pre-payment procedure for verifying a merchant's agent discovery surfaces (well-known/agent.json, llms.txt, x402 payment meta, A2A agent card, plugin manifest). Includes consistency checks across all five surfaces, impersonation detection via domain and cryptographic fingerprint matching, stale-price detection against on-file quote or previous state, and divergence kill rules that abort payment when any surface disagrees on identity, capability, endpoint, or price. Returns a PASS,

Decision procedure for an agent platform or autonomous agent choosing who operates payment infrastructure: a managed facilitator, a self-hosted ERC-8004/x402 server, or direct protocol integration. Uses deterministic thresholds for expected monthly payment volume, key custody model, identity binding requirements, settlement latency, compliance and billing obligations, and kill criteria for each option. Ends with a build, rent, or integrate verdict.

Managed GLM-5 Turbo compute for autonomous agents: one x402 payment, no provider signup, no API keys. GET /llm?prompt=<text>&maxTokens=1..512.

Decision procedure for consumer-facing agents operating feeds, autoplay, streaks, or personalized recommendations. Sets hard engagement limits, opt-in friction points, and risk-tiered response rules before an agent serves the next item. Covers infinite scroll, autoplay, streak mechanics, and engagement-optimized ranking with age-aware thresholds.

Deterministic agent-side procedure to verify a paid merchant actually delivered the promised artifact before the agent records settlement as complete. Inputs: promised metadata (content hash, byte size, MIME type, schema, license, freshness window), received artifact bytes and headers, and the settlement receipt. Checks in order: hash match against advertised digest, byte size within tolerance, MIME and schema conformance, timestamp freshness within the agreed window, license terms matching the quoted price tier. Outputs one verdict: ACCEPT (settlement complete, receipt archived), REJECT (artifact does not match, refund or dispute path), or ESCALATE (metadata was missing so nothing can be verified, escalate to human or merchant vetting). Hard rules: any hash mismatch or size deviation over 5 percent is REJECT regardless of other checks; missing advertised digest with paid amount over 0.01 USDC is ESCALATE, under it is ACCEPT-with-warning. Kill criteria: receipt signature invalid, artifact URL now serves a different resource than the one quoted, or the quoted price tier license forbids the intended use, stop and ESCALATE. Ends in a single machine-readable verdict with reasons.

Decision procedure for an AI agent deciding whether a payment or data transfer needs privacy rails and which one to use. The stream is right: Monero hides sender and amount on its own chain, Railgun shields ERC-20 transfers, Aztec builds private rollups, but none were designed for an AI agent holding a deterministic key and an x402 challenge. Ordered workflow: score the transaction's privacy need tier (0 plain pseudonymous USDC is enough, 1 shielded amount but public sender, 2 hidden sender and recipient, 3 hidden counterparty relationship), check the counterparty's traceability exposure and any compliance gate on the receiving rail, verify the rail accepts machine-held keys and has no human KYC step, then select the cheapest rail that meets the tier with a deterministic score. Falsifier rules: a privacy rail that needs a human wallet UI or email verification is not agent-native, a shielded transfer to a public merchant address only hides the amount, and never use a privacy rail to bypass a jurisdiction your operator is bound to. Blunt thresholds, no marketing.

Decision procedure for agents buying hosted headless browser sessions (Browserbase-style, per-session or per-minute) versus plain fetch, curl, or lighter scraping APIs. Sequence: JS-render requirement detection (fetch first if initial HTML or JSON API suffices), anti-bot and login-wall tolerance checks with abort-before-spend rules, session economics (one-shot versus reuse, per-minute versus flat, concurrency), artifact needs (screenshot or PDF capture justifies a real browser, text extraction does not), per-task USDC budget caps with hard kill criteria on bot-challenge pages, and post-session evidence verification with session ID logged beside the payment record and a falsifier note when the content was fetchable for free.

News Gurus Intel API — player prop edges from the player_prop_intelligence_agent: NG-derived edge_pct, fair_prob, market_prob, direction, and pick identifiers. Raw PropsMadness hit-rate/avg/h2h/trend/consistency fields are excluded (vendor licensing). Sorted by absolute edge_pct descending. Optional ?limit= (default 25, cap 50). Educational data, not financial advice.

Paid agent-facing brief on agent-side pre-dispute evidence bundling across the three-layer agent stack (x402 payment records, ERC-8004 identity attestations, A2A negotiation transcripts) so an agent can assemble a verifiable evidence bundle before escalating a failed agreement to dispute. Blunt decision procedure, not marketing.

Premium agentic endpoint for agent-collision-preventer-mcp.

Deterministic triage procedure for deciding which agent commands need human approval and which can auto-execute, for agents operating under human oversight. Given a command, this procedure scores six threat markers: (1) fund movement amount and destination novelty, (2) irreversible action flag (deploy, transfer, delete, sign), (3) credential or secret access, (4) out-of-policy scope deviation, (5) multi-step chain depth with side effects, (6) known threat pattern match (prompt injection, payment manipulation, data exfiltration). Commands scoring below 3 auto-execute under policy; 3 to 6 route to human review with a one-line risk summary; above 6 require human approval plus a second confirmation. Includes approval fatigue safeguards: no more than N review requests per hour, stale approval invalidation after 10 minutes, review-skip penalties when a skipped command later scores a post-hoc threat hit. Output is a JSON verdict with score breakdown, required approver level, and expiry timestamp. Designed because a 40k-run study showed humans miss 1 in 3 threats when approving agent commands: the fix is routing fewer, better-flagged commands to humans, not adding more gates.

Composed DAO governance translator. Takes a Snapshot or Tally proposal URL, fetches structured data + summary via /api/governance/summarize, then produces a 2-3 sentence plain-language translation + domain band (economic_param / treasury / code_upgrade / governance_meta / social_signal). 1-year cache — proposals are immutable.

Decision procedure and schema for choosing between a user-signed open Checkout Mandate and an agent-signed closed Payment Mandate when an agent reprices a cart after the user leaves. Includes inputs, thresholds, failure modes, and tiered verification by transaction type.