Development x402 offerings

Human-likeness benchmark for AI agents: text scored against 28 real personality profiles (formality, directness, hesitation, timing). Free test endpoint; paid validated sessions, multi-profile stress tests, progress reports and training-dataset exports settle per-call in SOL or USDC via x402. No API keys, no accounts. Referral program pays credits.

Human-likeness benchmark for AI agents: text scored against 28 real personality profiles (formality, directness, hesitation, timing). Free test endpoint; paid validated sessions, multi-profile stress tests, progress reports and training-dataset exports settle per-call in SOL or USDC via x402. No API keys, no accounts. Referral program pays credits.

Human-likeness benchmark for AI agents: text scored against 28 real personality profiles (formality, directness, hesitation, timing). Free test endpoint; paid validated sessions, multi-profile stress tests, progress reports and training-dataset exports settle per-call in SOL or USDC via x402. No API keys, no accounts. Referral program pays credits.

Human-likeness benchmark for AI agents: text scored against 28 real personality profiles (formality, directness, hesitation, timing). Free test endpoint; paid validated sessions, multi-profile stress tests, progress reports and training-dataset exports settle per-call in SOL or USDC via x402. No API keys, no accounts. Referral program pays credits.

Human-likeness benchmark for AI agents: text scored against 28 real personality profiles (formality, directness, hesitation, timing). Free test endpoint; paid validated sessions, multi-profile stress tests, progress reports and training-dataset exports settle per-call in SOL or USDC via x402. No API keys, no accounts. Referral program pays credits.

Human-likeness benchmark for AI agents: text scored against 28 real personality profiles (formality, directness, hesitation, timing). Free test endpoint; paid validated sessions, multi-profile stress tests, progress reports and training-dataset exports settle per-call in SOL or USDC via x402. No API keys, no accounts. Referral program pays credits.

Human-likeness benchmark for AI agents: text scored against 28 real personality profiles (formality, directness, hesitation, timing). Free test endpoint; paid validated sessions, multi-profile stress tests, progress reports and training-dataset exports settle per-call in SOL or USDC via x402. No API keys, no accounts. Referral program pays credits.

Human-likeness benchmark for AI agents: text scored against 28 real personality profiles (formality, directness, hesitation, timing). Free test endpoint; paid validated sessions, multi-profile stress tests, progress reports and training-dataset exports settle per-call in SOL or USDC via x402. No API keys, no accounts. Referral program pays credits.

Parse an expression and return the free variables it references, without evaluating it — so an agent can discover which inputs a formula needs before supplying values. A syntax error is a clean 400.

context-compress (session-less x402): you are overloaded and near the context/token limit. Returns a compression strategy that drops redundant tool output, collapses duplicate file reads, and promotes blockers — targeti…

tool-verify (session-less x402): you are about to call a tool or MCP server. Returns a pre-flight checklist — name matches the intended server, required headers/env present, arguments match schema, timeout/retry set, pa…

cascade-break (session-less x402): you made a mistake and it is getting worse with each change. Returns the halt protocol — drop to read-only, triage the last three edits, safely revert the harmful one, and force a pits…

scope-check (session-less x402): you are drifting into scope creep, unrequested refactors, or side quests. Returns an in-scope vs out-of-scope rubric and the one-sentence-goal reset to run before your next tool call. On…

pre-run-context (session-less x402): you are cold-starting and lack context before an expensive tool loop. Returns a pre-run brief — transport (stdio vs SSE), required env vars, schema caching, timeout/retry — plus sour…

mcp-wiring (session-less x402): you are blocked on MCP wiring — 401/403, PAT scope, stdio paths with spaces, SSE CORS, or env not reaching the subprocess. Returns the concierge wiring pack with the common failure patter…

content-analysis (multimodal, session-less x402): give it any public audio, voice note, podcast, PDF, or direct video file URL and get back structured content analysis in the model's own words -- a summary, ranked key p…

should-i-pay (session-less x402): you are about to spend USDC on an x402 endpoint. Returns a cashier decision tree — did proof pass, is the free sample sufficient, one-shot vs bar tab — and a pay/don't-pay default. One-…

Inspects MCP tools for readiness, risks, missing schemas, and marketplace opportunities.

MCP Registry Listing Writer — Writes the server.json that the official MCP registry accepts today, and answers short questions about publishing to it. Uses the current dated schema address, a name that matches the way the publisher proves ownership (GitHub login or domain), a description of at most 100 characters and one entry per package type with the ownership proof the registry checks at publish - mcpName in package.json for npm, the mcp-name line in the README for PyPI, NuGet and Cargo, a l…

Generate a runnable TypeScript MCP stdio server from a built-in OpenAPI 3.x contract using the stable Model Context Protocol SDK v1

Measured weekly data on Claude Code and coding agents: costs, plugins, MCP registry, npm, HN, issues

Measured weekly data on Claude Code and coding agents: costs, plugins, MCP registry, npm, HN, issues

Mock LLM completion (testnet). Authorizes up to $0.02; settlement charges $0.0001 per output token via Settlement-Overrides.

Compare Timestamped source search for API design discussion passages; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is calle…