Every agent-payable API.

Paid x402 endpoint for multi-model AI voting and decision synthesis.

Paid x402 endpoint for multi-model AI voting and decision synthesis.

AI/agentic copilot exposure lookup for OT/ICS vendors. Pass vendor (Siemens, Schneider Electric, Rockwell Automation, ABB, Emerson, Honeywell, Yokogawa, GE Vernova, Omron, Mitsubishi Electric). Returns the vendor's documented AI/agentic copilot, autonomy level (advisory vs agentic — the key risk differentiator), access, and applicable MITRE ATLAS techniques. Hand-verified mapping, ATLAS IDs confirmed against the live atlas.mitre.org matrix. Deterministic, no LLM in the lookup path.

AI Gateway model list: available LLMs per tier with prices and caps. The FIRST LLM inference gateway payable in USDG on Robinhood Chain (also USDC on Base/Polygon/Arbitrum/Solana). Send {}.

ai-governance-brief: AI Governance Compliance Brief – LLM-analyzed digest of the last week's US Federal Register activity on artificial intelligence: enforcement actions and deadlines called out first, every citation grounded and independently verifiable. No query params required — just call it. Optional: days (lookback 1-30, default 7).

AI intent execution - natural language commands translated to API actions automatically

AI model pricing comparison table: what every AI model costs right now — GPT-5, GPT-4o, Claude 5, Claude Sonnet, Gemini 3 Pro, Llama 4, DeepSeek V4, Grok 4 and 2,000+ more. One normalized dataset of LLM token cost and inference pricing across OpenAI, Anthropic, Google and 70+ providers, refreshed hourly. Compare models by price, rank by cost, pick the cheapest model for any workload.

AI phone calls - automated voice conversations with AI agents, pay per minute with USDC

AI-powered sentiment analysis. Send text, get sentiment score + emotions. Paid via x402.

AI text generation via Claude. Prompt in, polished text out - drafting, rewriting, extraction and reasoning for agents. Pay per call with USDC (x402) or credits - archtools.dev

AI tweet drafting: generate, refine, and score tweet text in a 3-step flow.

Assesses how much a general-purpose AI agent (not a specialized ICS tool) lowers the barrier for an attacker to reach a vendor's OT-adjacent footprint. Grounded in Dragos's May 2026 water-utility precedent, not governance thresholds. Distinct from /ot/ai-exposure (vendor's own AI copilot). Input: vendor (required); product, internet_facing, auth_type, segmented (all optional; unknown caps tier at informational). DeepSeek-synthesized, ICD-203 language.

AI code review. Returns issues with severity, line numbers, fix suggestions. Focus on security, performance, readability, or bugs.

[3-LEG] AI tool and MCP chain, one tool (?entity=mammoth-ai): leading decay warnings, release cadence stalling and docs going dark -> current live or dead status from real DNS and GitHub checks -> realized lifecycle from launch to death with days alive (confirmation gate). A sequential chain, not one reading - confidence = how many legs are lit, in order. Sources: DNS, GitHub, package registries. Descriptive only, never a forecast or advice. No data -> 422 no_charge, not billed.

AMM price impact in bps for a swap input against reserves. Call when pre-trade impact checks for pool size vs order size. Returns impact bps and mid vs execution as deterministic JSON for $0.001 USDC via x402 on Base. First-party local math only—no RPC, live market feed, API keys, storage, or mediagen. Advisory only; the caller owns capital, risk, and production controls.

Decision procedure and verification schema for accepting a cryptographically signed AP2 payment mandate before settlement. Checks signature validity, nonce uniqueness, mandate scope against requested amount, expiry and session freshness, delegation chain depth, and parent agent authority. Returns PASS/FAIL with explicit rejection reasons for each gate.

Check one Base mainnet wallet or contract for ETH and official USDC balances, transaction nonce, and contract-bytecode evidence at a single resolved block.

Query validated eth_getLogs events from one Base mainnet contract using a required event signature and optional indexed topic filters across a bounded resolved block range.

Fetch and normalize public RSS or Atom feeds into stable structured JSON entries for agents and research workflows.

Validate EIP-712 typed structured data and derive its domain separator, message hash, and signing digest.

Clean CSV, TSV, JSON, JSON Lines, or YAML records with collision-safe header normalization, deterministic integrity hashes, and exact transformation counts.

Extract webpage metadata from one public URL: page title, meta description, canonical URL, headings, hreflang, icons, feeds, Open Graph, Twitter Cards, and JSON-LD Schema.org types, with redirect and response provenance plus privacy-safe, publisher-asserted Organization facts with field evidence.

Scan source code or configuration text for leaked API keys, tokens, and credentials without returning secret values.

Deterministically detect and redact PII and personal data in supplied text with overlap-safe matching for emails, phone numbers, validated IPv4 and IPv6 addresses, Luhn-valid payment cards, valid-checksum IBANs, and structurally valid US Social Security numbers.

Compare two texts and return structured line additions, removals, and a unified diff.

Validate and normalize an Ethereum or EVM wallet address, distinguish valid, absent, or invalid ERC-55 checksum casing, and identify the zero address without a network request.

Estimate gas for one Base mainnet transaction context at a resolved block, add a bounded caller-selected buffer, and preserve RPC rejection evidence without signing or broadcasting.

Inspect Base transaction status and receipt evidence in one call, including success, revert, or pending state, confirmations, actual gas fee, recognized calldata, bounded ERC-20-shaped transfers, and official Base USDC recognition for payment confirmation.

Convert caller-supplied CSV, TSV, JSON, JSON Lines (NDJSON), or YAML with optional root preservation, deterministic integrity hashes, JSON-encoded nested tabular cells, and explicit rejection of ambiguous duplicate keys or non-finite numbers.

Remove duplicate CSV, TSV, JSON, JSON Lines, or YAML records using selected identity fields and report the removed count.

Resolve an exact SEC company name, ticker, or CIK, then bundle recent filing signals, normalized issuer-reported XBRL facts, and Form 4 insider transactions into one bounded public-company evidence report with explicit section coverage and official-source provenance.

Get and inspect one historical Base mainnet block by exact number or a latest, safe, or finalized tag, returning its header timestamp, transaction count, gas use, base and blob fees, state and receipt roots, confirmations, and head-distance evidence.

Extract and classify links from one public page or safely crawl up to 10 same-origin pages into an agent-ready site map with page provenance, depth limits, and robots.txt enforcement.

Check a public domain's email authentication and anti-spoofing posture using MX, SPF, DMARC, caller-selected DKIM, MTA-STS, TLS-RPT, and BIMI DNS evidence.

Resolve 29 common ERC-20, ERC-165, ERC-721, ERC-1155, ERC-2612, and ERC-3009 selectors without a network lookup, or strictly decode arbitrary Ethereum or EVM calldata using a supplied Solidity signature.

Retrieve newest-first incoming and outgoing Circle USDC Transfer events for one address across a validated, bounded Base mainnet block range.

Repair caller-supplied malformed JSON by safely removing an outer Markdown fence, comments, single-quoted strings, unquoted identifier keys, Python literals, and trailing commas, with transformation hashes and strict rejection of duplicate keys or non-finite numbers.

Audit exact Python/PyPI, npm, Go, Maven, NuGet, crates.io, or RubyGems dependencies against OSV and return affected packages and vulnerabilities.

Create and generate a nested JSON Schema Draft 2020-12 contract by inferring field types and required fields from representative JSON, CSV, TSV, JSON Lines, or YAML records, with equivalent CSV/TSV numeric and null inference, input evidence, and non-enforcing observed bounds.

Classify software dependency licenses and flag packages that need commercial or legal review.

Inspect a domain's robots.txt crawl rules and XML sitemap health, availability, and URL count.

Search newest U.S. Federal Register document metadata by topic, agency, type, and publication date, returning bounded regulatory notices, rules, proposed rules, presidential documents, and links to FederalRegister.gov and official govinfo.gov PDFs.

Investigate a domain using parallel DNS, TLS certificate, RDAP (the standards-based successor to WHOIS), DNSSEC, SPF, and DMARC signals with factual findings and source provenance.

Compare JSON or YAML deterministically and return source hashes plus machine-readable additions, removals, and replacements by path with explicit truncation evidence.

Validate and audit an OpenAPI document for missing operation IDs, descriptions, responses, and consistency problems.

Profile CSV, TSV, JSON, JSON Lines, or YAML records for field types, nulls, uniqueness, and representative samples.

Measure caller-supplied source code with Python AST analysis or a deterministic lexical fallback, including per-function complexity, a SHA-256 fingerprint, density ratios, syntax status, and actionable maintainability signals without retaining or forwarding the code.

Extract structured table rows and columns from supplied HTML, DOCX, or CSV documents.

Identify frameworks, analytics, CDNs, servers, and other website technologies from public response signals.

Audit on-page technical SEO, score a public URL, and return prioritized, actionable issues for search optimization.