Api x402 offerings

Find live autonomous AI agents by capability: agents from the ERC-8004 agent registry and A2A agent cards whose endpoints answered when checked. Returns names, descriptions and A2A/MCP endpoints.

Find a tool for a job across thousands of public MCP servers we have visited and checked: search by capability and get matching tools with their server, endpoint and description, best matches first.

14 pay-per-call market data tools over MCP. Free discovery, calls settle in USDC on Base (x402).

14 pay-per-call market data tools over MCP. Free discovery, calls settle in USDC on Base (x402).

14 pay-per-call market data tools over MCP. Free discovery, calls settle in USDC on Base (x402).

14 pay-per-call market data tools over MCP. Free discovery, calls settle in USDC on Base (x402).

14 pay-per-call market data tools over MCP. Free discovery, calls settle in USDC on Base (x402).

14 pay-per-call market data tools over MCP. Free discovery, calls settle in USDC on Base (x402).

14 pay-per-call market data tools over MCP. Free discovery, calls settle in USDC on Base (x402).

14 pay-per-call market data tools over MCP. Free discovery, calls settle in USDC on Base (x402).

Use when the MCP client should load few tools. Compact MCP server with the 18 most used tools: live decision, pre-trade check, opportunity scan, snapshot, move explanation, token verdict and risk, new tokens, swap quote, Fed rate odds, prediction markets, DeFi yields, market summary, macro calendar, news and fundamentals. Each tools/call costs its HTTP route price; the full server is /mcp.

Declared-intent demand — what agents SAID they needed, not just which endpoint they hit. Sourced from the free /api/discover agent router: the natural-language need an agent typed, its willingness-to-pay (from reported outcomes), and where it actually went (referrals = revealed preference). This is intent the endpoint-hit radar structurally cannot see. HOW TO CALL: GET /api/demand/intent?days=7&limit=20 PARAMETERS: days — lookback window, 1-90 (default 7) limit — top terms / origins returned, 1-50 (default 20) RESPONSE: top_declared_needs[], willingness_to_pay{median/p90/max}, top_chosen_origins[], helped_rate, our_top_rank_rate. Aggregate-only. PRICING: $0.05 per call.

Unmet agent demand — the endpoints agents ask for and cannot get. 404s and gated 401/403s from real (non-scanner) agent clients: a shopping list with the customers already attached. This cut is invisible to anyone who is not the origin being asked, which is why it cannot be reconstructed from public bazaar data. HOW TO CALL: GET /api/demand/unmet?days=7&limit=25 PARAMETERS: days — lookback window, 1-90 (default 7) limit — rows returned, 1-100 (default 25) RESPONSE: unmet[] sorted by volume, each with the signal (404/401/403), category, hit count and bucketed count of distinct askers. PRIVACY: aggregate-only; rows below 3 distinct clients withheld. PRICING: $5.00 per call.

x402 supply census — who is live, in what category, at what price. The full public discovery index (~14.8k resources) normalised into per-category price percentiles and per-origin catalogues, so you can price against the median instead of the loudest listing. Crossed with the half that is not public: which agent client stacks actually crawl a live origin, and therefore which ones will find your endpoint once you ship it. HOW TO CALL: GET /api/demand/competitors?category=market-data&limit=40 PARAMETERS: category — optional filter (market-data, crypto-onchain, trading-signal, ai-inference, media-gen, web-search, enrichment, social, messaging, storage, other) limit — origins returned, 1-100 (default 40) RESPONSE: catalog.by_category[] price min/p25/median/p75/max, catalog.top_origins[], and ecosystems_crawling[] observed over 7 days. PRICING: $5.00 per call.

The complete list of risk factor classifications used in the risk factors endpoint. Can't find what you're looking for? POST feedback to /feedback, no charge.

OpenAI-compatible chat completions backed by DeepSeek (GET probe variant). Answers open-ended questions and returns reasoned analysis.

Delta of the MCP registry since a daily baseline: added, removed, and changed (score/status) servers — the cheap habit endpoint for repeat callers.

Full MCP registry snapshot: deduped, quality-scored, refreshed every 30 minutes.

Find MCP servers matching a need, ranked by semantic similarity over a curated snapshot of MCP servers. Returns name, endpoint, description, source registry and a 0-1 relevance per match. Paid POST: up to 25 matches. Try GET /discover/sample.

Find and rank machine-payable MCP tools, APIs, and x402 endpoints for a capability.

Store a piece of text for later similarity recall - a per-wallet semantic index an agent cannot host in-session. Returns an id. Prefer memory-write for structured state you will look up by exact key; this pair is for fuzzy, meaning-based retrieval. Pair with /api/memory/recall to retrieve by meaning, not exact key.

TRON account info: TRX balance, energy, bandwidth, and TRC-20 holdings (USDT, USDC, USDD) for any TRON address.

Anthropic Messages API over x402 - point the Anthropic SDK (or Claude Code / the Agent SDK) at base_url https://agent402.tools/v1/auto and pay $0.01 per call in USDC, no API key, no signup. Same models, caps and price as this tier's /chat/completions route; any model here is served through the Messages wire (Claude natively, others translated). Depth: `effort` (low..max) on Claude 4.7+ and Haiku 5.5, thinking.budget_tokens on older Claude.

Anthropic Messages API over x402 - point the Anthropic SDK (or Claude Code / the Agent SDK) at base_url https://agent402.tools/v1 and pay $0.02 per call in USDC, no API key, no signup. Same models, caps and price as this tier's /chat/completions route; any model here is served through the Messages wire (Claude natively, others translated). Depth: `effort` (low..max) on Claude 4.7+ and Haiku 5.5, thinking.budget_tokens on older Claude.