Explore APIs

AI-generated standard research report (Open Research Agent)

AI agent action safety: one-cent deterministic preflight for every consequential agent command. Returns risk, matched rule ids, and an exact machine-readable escalation call: full DestructGuard evidence for medium risk or the complete Action Safety workflow for high and critical risk.

Verify output another AI agent hands back, by code alone, for $0.005: no model call, answers in about a second. Recomputes the deliverable's written sums, totals, percentages, dates, weekdays, time spans, unit conversions, and list counts; checks lengths the task asks for; flags placeholders and prompt injection; measures words, items, and JSON shape. Signed receipt, tier lite. For every requireme

Reproducible Japan Post evidence before an autonomous agent submits a Japanese address. One 0.02 USDC x402 call returns a fail-closed town-level consistency decision, ordered source candidates, source version and SHA-256, explicit limitations, and the next safe input action. It does not claim deliverability, residence, identity, building, or room existence.

Jev hires a model for your task and grades the result. Rejected work is refunded.

Check whether an ENS identity name for an AI agent, API or MCP server is available on x402 Identity Hub (*.402bot.eth, *.402api.eth, *.402mcp.eth). Returns availability, the mint fee and where to register.

Scan any OpenClaw SKILL.md for malware, prompt injection, exfiltration, and 37 other threat patterns. Returns risk score 0-100 and detailed findings.

Access to protected content

Premium AI joke generation

Coordinate agents sharing one account: reuse matching JSON reads within 30 seconds, or stop duplicate operations using a stable business event ID. Enroll once at /v1/enroll, then authenticate paid calls with your Bearer key. After EXECUTE use /v1/start and /v1/commit around your own tool. Same-request payment recovery is free. Integration and cost measurement: /agent. External execution is not gua

Demo of Stilebase pay-per-page for AI agents: rental listings in Springfield with price, bedrooms and what's special about each home. Test USDC on Base Sepolia.

Look up US import duty rates by HTS code or product description. Returns the base General (MFN) and Column 2 rates of duty from the official USITC Harmonized Tariff Schedule (public domain). Reference only: Section 301/232, IEEPA and other additional duties are not included.

Verify a small business's SBA loan history: every SBA 7(a) and 504 loan since 1991 — amounts, approval dates, program, and outcome (paid in full, charged off, defaulted, cancelled). SBA FOIA disclosure data, federal public domain.

Look up FDA drug product information by NDC or name: labeler, dosage form, route, marketing status, approval date. Public-domain FDA NDC Directory data.

Composite medical-device risk card from a UDI device identifier (DI), brand, or labeler company. Returns the GUDID labeler record (brand, company, GMDN term, version/model, catalog number), MR-safety status, GUDID-cited premarket submission signal, a live openFDA recall cross-reference for the labeler, and an explainable risk level. FDA GUDID data (public domain).

Verify an FAA aircraft tail (N-number) registration: status, expiration, make/model, serial, registration fraud & expiry flags. Public-domain FAA Releasable Aircraft Database. Registrant identity is never returned (49 U.S.C. §44114) — only registrant type.

Paid x402/MCP/A2A/Bazaar consult. JSON wisdom envelope: verdict, wisdom, developer build notes, risk, citations, receipt.

Global weather forecast by latitude/longitude: up to 48 hours of temperature, humidity, wind, cloud cover and next-hour precipitation in UTC with explicit units and model update time. Forecasts, not live observations; missing fields are null and sparse periods are not interpolated. Based on MET Norway data (CC BY 4.0); outage cache is flagged stale.

Embeds up to 32 texts on the local Ollama runtime. Returns explicit model and dimensions; no paid third-party API is called.

Generates branded, customer-ready quotes and estimates as hosted PDFs in about one second — line items, tax, discounts, a hosted approval page, a QR code and a Stripe payment link. Pay-per-call with x402 in USDC on Base; no account or API key. THIS ENDPOINT (the flagship): POST line items, get back the quote number, totals, a hosted page the customer can approve or decline, a PDF URL, a QR code, a

Skill Scan by Agentropolis: static Consensus Scan of an MCP server or agent skill before you install it. Pass a GitHub repo, npm:/pypi: package or pasted code + tools/list/SKILL.md. Flags tool poisoning, hidden instructions, credential/env exfiltration, remote code exec, obfuscation, install hooks; 2 rule families + 2 LLM reviewers vote; cross-checks Agentropolis seller trust data. Returns allow/r

Agent Reputation Check by Agentropolis: give a payTo and/or an agent / A2A / MCP URL. Returns owner, verified domain, real outside buyer history, wash flags and trust score from Agentropolis. Says when coverage is limited. Deterministic, no LLM.

Signed extractability score (0-100) + breakdown + fixes for a URL. Free preview: GET /extractability/preview Blocked or bad input returns 400; a failed fetch returns 502; you are never charged for an error.

Seattle weather forecast API: live temperature nowcast and daily high forecast for Seattle-Tacoma Intl (KSEA), with calibrated probability the temperature ends above/below any Fahrenheit strike. KSEA is the official settlement station for Kalshi KXHIGHTSEA daily high temperature prediction markets. Built for AI agents trading weather prediction markets or needing real-time weather data. $0.05 with

Offer one bounded contribution to Root Logos for constitutional evaluation and preservation. Current open call: https://rootlogos.com/agent-call.json. Payment grants no admission or authority.

Runs Python you send in a sandbox and returns its stdout, exit status, time and memory. Use it to execute code an agent wrote - a calculation, a parse, a transformation - without a machine, an account or an API key of your own.

Quick pre-flight quality score: composite (0-100) + grade (A-F) + three framework sub-scores (PEEM, RAGAS, G-Eval) + verdict. Run upstream of any other paid call to filter weak prompts before inference. The cheapest gate on the AI input quality problem.

AMC 25-session price roadmap for AI agents: exact subsequence-DTW match of the last 60 completed AMC daily closes against a real regular-hours 1-hour archive, top-5 independent historical analogs, ensemble median/range per day, SML Coherent Gate verdict, data provenance and SHA-256 input hash. Real market data only.

Extract plain text and metadata (title, author, producer, page count) from a PDF supplied by URL or base64 — heavy pdf.js parsing an agent can't self-run.

Agent Readiness Scan, full report: runs all 16 checks against a domain and returns the complete machine-readable results synchronously, plus a hosted report URL.