The active deepnets watchlist - high-volume tokens that passed the safety screen, with current safety data. Covers Solana, Robinhood Chain and Base; EVM entries carry `chain` and a 0x `mint`. Filter with `chain`.

MCP server security scan: probe any MCP endpoint's initialize handshake and tools/list and report whether it requires authentication, which protocol version it speaks, how many tools it exposes and which are not marked read-only. Use it before connecting an agent to an unknown MCP server. Input: url of the MCP endpoint.

AI video generation / text to video: a short clip from a text prompt with Google Veo, returned as base64 video bytes (or a GCS URI when large) with its MIME type, optionally with generated audio. Input: prompt; optional aspect_ratio (16:9 or 9:16), duration_seconds (4, 6 or 8), generate_audio.

Time-series forecasting: forecast any BigQuery table with Google's pretrained TimesFM model (AI.FORECAST), nothing to train. Point it at the table, timestamp column and value column and get forecast rows with bounds for the horizon you set, per series with id_cols. Use it for sales, traffic, demand or metric forecasts. Input: table, timestamp_col, data_col; optional horizon, id_cols.

Use when an agent asks "is this Base token safe?" before buying, holding or listing it. One scam/rug check read live from Base RPC + GoPlus: honeypot, buy/sell tax, hidden or reclaimable owner, pausable transfers, blacklist, holder concentration (sellable holders only), LP lock and upgradeable proxy. Returns a 0-100 score, flags and a GO/HOLD/STOP receipt. On established tokens (50k+ holders, $1M+ liquidity) admin controls are context, not risk.

🆕 Base Account spend permissions let an app or agent spend a scoped, recurring allowance from a wallet — the primitive behind autonomous agent payments on Base. This reconstructs a wallet's ACTIVE spend permissions from onchain approve/revoke events and flags the dangerous ones: unlimited allowance, no expiry, unrecognized spender. The Base-native, agent-era drain check that ERC-20 approval tools can't see.

Not 'is this address sanctioned' (that's sanctions) but 'has it DEALT with one' — screens a wallet's USDC counterparties (both directions) against the OFAC SDN list. Taint by association: receiving from or routing through a wallet that transacts with sanctioned addresses carries sanctions risk. Returns the sanctioned counterparties found. Covers direct counterparties; pair with fund-trace for the multi-hop funding chain. Not financial advice.

Company research report: what a company does, its products and anything notable, from the live web (official site and Wikipedia first) and recent GDELT news, every claim cited to a numbered source, thin or conflicting evidence disclosed. Use it for due diligence, sales prep and competitor research. Input: company name; optional max_sources. Structured firmographics in one cheap call: company.enrich.

Agents bridge across chains and get it wrong — bad route, an untrusted bridge, fees that eat the transfer. Returns the best cross-chain route via the LiFi aggregator: which bridge, how much arrives, est. time, gas + bridge fees in USD, and the ready-to-send tx. Chains: ethereum, base, arbitrum, optimism, polygon. Tokens by symbol (USDC/USDT/ETH/WETH/DAI) or a 0x address + amountUnits. A quote — re-quote with your own sender before executing; we never hold keys. Not financial advice.

Is this domain trustworthy, or is it a phishing site / typosquat / scam? Pull the reputation signals an analyst checks before clicking anything: domain age, cert issuance history, hosting reputation, DNS topology, tech-stack fingerprint, and page-content red flags. Different from a security audit - this is about whether the domain is what it claims to be.

What companies are going public? Recent S-1/IPO filings from EDGAR plus a web search for IPO news. IPO watch skill pack: one x402 payment runs 3 underlying tools (edgar-recent-ipos, search, search-news); partial-success per step.

Pull SEC filings, the latest close, historical prices, and macro context for a single ticker in one pass. Financial research skill pack: one x402 payment runs 6 underlying tools (stock-quote, stock-history, edgar-filings, edgar-company-facts, edgar-insider-trades, fred-series); partial-success per step.

Pull structured data out of any web page deterministically - articles to clean text, tables to JSON rows, specific elements via CSS selector - without writing regex against raw HTML. Structured scrape skill pack: one x402 payment runs 7 underlying tools (extract, render, html-select, html-table, html-strip, html-links, html-meta); partial-success per step.

Convert anything at a URL - HTML, PDF, or an image - to clean markdown. The 'I have a URL but it might be any content-type, give me markdown either way' workflow: HEAD-detect the content-type, branch to the right deterministic extractor (article extract for HTML, pdf-to-markdown for PDFs, OCR for images), and report token/word stats on the output so the caller can budget the result against an LLM context window.

Fetch a PDF from a URL, extract its text, and return a concise AI-generated summary - factual, no information added beyond what's in the document. Body: {"url":"https://…/file.pdf","maxWords":200?}. Uses the same OpenAI-compatible gateway as /v1/chat/completions internally; the model that actually served is disclosed in the response.

Triage a smart contract before an agent interacts with it: verified Solidity source, heuristic vulnerability scan, known-address check, function-selector resolution, and a read-only dry-run of the exact call you plan to make. Contract audit skill pack: one x402 payment runs 5 underlying tools (contract-source, solidity-scan, selector-lookup, address-label, tx-simulate); partial-success per step.

Person lookup / person enrichment API (alias of people-enrich). Resolve an email, name, domain, or company into a normalized person record with inferred name, free-email detection, MX records, and optional public company context. Public-data only; no private people databases or social scraping.

The 'is the economic backdrop you're modeling against still current?' pack. Pull the canonical macro signals - CPI year-over-year, unemployment, fed funds, the Treasury yield curve, a G10 FX dashboard, the Sahm Rule recession indicator, and the next scheduled economic releases - in one composed workflow. Seven egress tools, one composite snapshot the agent can cite before doing any forecast or investment math.

The 'who just filed / who just bought / what just IPO'd / what does the full-text search say' monitoring loop. Five EDGAR tools composed: full-text search for a keyword, surface recent filings on the matched companies, pull insider Form 4 transactions, pull 13F institutional holdings changes, and check the IPO calendar. Different from sec-filings-deep-dive (which goes deep on one company's earnings) - this is the wide-and-recent radar.

Has this company just reported, and what is being said about it? Recent SEC filings, the latest close, and current coverage in one call. Earnings watch skill pack: one x402 payment runs 3 underlying tools (stock-quote, search, edgar-filings); partial-success per step.