PDF or picture in, structured JSON out, with a page and a position behind every field, plus every QR code and barcode decoded. Paid per page in USDC over x402. No signup, no API key.

Premium agentic endpoint for document-layout-analyzer-mcp.

Web & scraping

Compresses HTML, DOM, PDF, and JSON RAG documents by 85-97% into clean LLM Markdown.

Full reference for real-time IP scoring API, usage limits, authentication, examples and response schema.

Pay-per-call document reading for agents: convert a PDF, Word, Excel, OpenDocument, CSV, Apple Numbers, HTML, XML or image file (by public URL or base64) into clean Markdown you can reason over. One cent per document; you are only charged when a conversion is returned.

Congressional Documents — full-text search and retrieval over the official

Pay USDC, get instant AI summaries, action item extraction, and simplified explanations of any document or text.

Turn any document into structured data for AI agents — OCR, layout-to-Markdown, tables, key-value, invoice/receipt fields — from PDF/images in 100+ languages. Pay per call via x402 (USDC). No API keys.

Two endpoints, billed per page, paid in Nano (XNO). OCR: image to text in English, German and Swahili — 0.003 XNO per image (~0.1 US cent), answers in about one second; printed and typed text only, handwriting is not recognised. Document analysis: title, language, type, summary, key points, entities (people, organisations, places, dates, amounts) and open points as structured JSON — 0.009 XNO per

Extract structured text, summaries, or metadata from supplied document text or a public HTTPS document URL.

Reuse searchable private documents across agent sessions. Free base capacity; paid expansion.

Zoom enabled repair plan fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

Visible stock state repair plan fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

No accidental wildcard CORS repair plan fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed. -- reliability 63.02827835083008/100 per Paygent Discover

Author identity audit fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

About page discovery repair plan fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

Canonical change monitor plan fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

Validate up to ten JSON documents against JSON Schema draft-07 or 2020-12. Returns per-document validity and actionable errors with instance paths. Runs isolated with bounded time and memory; no remote schema loading or automatic data modification.

Verify a USCG-documented vessel by official number, IMO number, or name. Returns vessel name, official number, IMO, flag, service/type, tonnage, dimensions, build year and builder, hailing port, trade endorsements, and Certificate of Documentation status and expiry. Public-domain USCG 'Merchant Vessels of the United States' data. Does NOT identify vessel owners (owner data was removed from the ...

Convert PDF/Word/Excel/PowerPoint documents to Markdown. Agents pay per conversion with USDC on Base via x402.

Extract structured document data through Ausca's measured asynchronous document analysis service.

Regulatory change detection for AI compliance agents. Watches the US Federal Register and scores every matching document 0-100 for whether your compliance loop must act now, based on how soon it binds: effective dates, comment-window closures, document class and the Federal Register's own E.O. 12866 significance flag. Built loop-shaped: poll /watch cheaply for a stable state_hash, then pay for ...

Searches pre-indexed developer documentation across 10+ platforms (Shopify, Stripe, Cloudflare, OpenAI, Anthropic, etc.) using natural language queries and returns relevant content chunks with source URLs.

Provide an API origin, inline OpenAPI document, and optional target list. Receive JSON with ready, blocked, or unsupported mpp.dev and x402-list packages, including exact reasons, without submission or directory fees.

Audit which agent-discovery documents a host actually serves — robots.txt, llms.txt, openapi.json, the .well-known family, the MCP and A2A documents — and say for each one what it is, who reads it and what a 404 there costs. It also validates a pasted llms.txt or a pasted A2A agent card against the spec, and drafts an llms.txt from a sitemap. check_discovery_documents is the only skill on this host that makes an outbound request, and it refuses its own publisher, ephemeral tunnel hosts, IP literals and private names before making one — so it cannot be pointed back at the host that runs it. Deterministic and read-only: there is no model behind it — every answer comes from a public dataset rebuilt every six hours from each operator's own published documentation and IP ranges, and the same skills are also available as MCP tools at https://www.pathwren.workers.dev/mcp/doctor. No key, no signup, no quota. Independent and unaffiliated with any operator it documents.

Full text of one IRS Internal Revenue Bulletin document (Revenue Ruling, Revenue Procedure, Notice, Announcement, or Treasury Decision), 2003 to present. Get the id from GET /search?q=<keywords>. Use this when you need the complete, verbatim text of a specific IRS guidance document for tax research, not a summary.

Agent-native document and media services with explicit pricing and receipt-backed results.

The Epstein investigation document corpus — the documents themselves, plus

Which discovery documents does a host serve? llms.txt, agent card, owners.json, mcp.json.

AI-assisted, source-grounded technical-writing audit for public GitHub repositories: README readiness, documentation inventory, prioritized fixes, and a tailored README outline. Repository validation completes before the x402 payment gate.

Welcome to the official API documentation for Ethos Network. This documentation provides detailed information about the Ethos API endpoints,…

Convert one caller-supplied HTML document to Markdown. The HTML is sent in the JSON body and is not fetched from the network.

Highest assurance verdict: all checks run twice, spaced about a minute apart, and pass only if both passes pass, so a deliverable staged briefly cannot sneak through. Asynchronous: instant first pass result, webhook or free polling for the signed final document. Designed for the ERC-8183 evaluator role and escrow release evidence. $5.00 per verdict.

Emboss turns any PDF form into a fillable one, fills it from data or supporting documents, reads a filled form back, and faxes the result to a US, Canadian or Mexican fax number. It can make a flat PDF fillable, complete a form from data, fill a PDF form from data or from supporting context documents, batch fill forms from a spreadsheet, one row per output file, and send a finished PDF by fax and

Quick red-flag scan of a term sheet, SAFE, SHA, LOI, SPA or NDA (English or French text/HTML URL, or text up to 6000 chars): document type, heuristic risk, top 3 risky clauses quoted (participating or >1x preference, full ratchet, personal guarantee, redemption, drag-along, vetoes...) and why they matter. Keyword scan, no AI. Full AI review: POST /redflags.

Production public HTTPS-origin readiness audit. It checks non-intrusive agent-discovery documents and HTTP metadata, returning reproducible evidence and recommendations. 0.05 USDC per request on Base via x402.

Node4All provides everything you need to build payment-ready AI agents with x402, including step-by-step documentation, testing tools, code examples, and ready-to-use services.

Name a host and it GETs the documents an agent client reads BEFORE it dials anything, then says what each one answered and what a client does with that answer: /.well-known/oauth-protected-resource in BOTH forms — the root form everyone publishes and the RFC 9728 §3.1 insertion form a spec-following client actually requests for a resource served under a path — /.well-known/oauth-authorization-server, /.well-known/mcp, /.well-known/mcp.json, /mcp.json and /llms.txt. Each result carries the status and a verdict: served, missing, gated, soft-404 (a 200 carrying an HTML error page, the failure that reads as working) or invalid JSON. GET only. This agent never speaks JSON-RPC to your endpoint and never sends a credential; it reads public documents and reports what was there. A missing document is reported as missing, never as a vulnerability. Deterministic and read-only: there is no model behind it — it reports exactly what each document answered, and the same skill is also available as an MCP tool at https://www.pathwren.workers.dev/mcp/lint. No key, no signup, no quota. Independent and unaffiliated with any operator it documents. TO CALL IT: send `message/send` (v1.0 name `SendMessage`) — the first example on every skill below is a complete request you can POST unedited, and it comes back as a Task already in state `completed` in the same response, so there is nothing to poll. Nothing to hand over? The `whoami` skill takes no arguments and answers about you. Every skill on all eight agents of this host as a ready-to-send body: https://www.pathwren.workers.dev/a2a/example.json

Build SEC EDGAR index and document links from a CIK and accession number, and decode the accession number.

Provide one inline OpenAPI document or public OpenAPI URL. Receive a JSON buyer-readiness score, rule results, and concrete fixes for payment metadata, missing examples, descriptions, and HTTP 422 traps.

Detects words and lines of text in a photo or screenshot (JPEG or PNG at a URL) with Amazon Rekognition, up to 100 words. Suited to signs, product labels and UI text; for documents use /v1/ocr.

PDF to Markdown conversion and document intelligence.

Documentation for media infrastructure for the agentic internet.

Extract strict, JSON-Schema-valid typed JSON from a PNG, JPEG, or WebP document image. Failed extraction calls are not settled. Always-paid x402 V2 image API.

Hidden-instruction scanner for documents before an AI agent reads them: PDF (invisible render mode, white/microscopic/off-page/transparent text, annotations, metadata, JavaScript), DOCX/XLSX/PPTX (vanish/white text, hidden sheets/rows/slides, off-slide shapes, speaker notes, comments, remote templates, DDE), HTML and Markdown. allow|review|block plus visible-only safe_text.

One decompose call: scope documents in, a contract-grade work breakdown out.

A library of pay-per-call tools for agents: company records, sanctions and PEP screening, email, phone, IBAN and VAT checks, web page reading and document extraction. Pay with an API key or, on eligible tools, an x402 wallet with no signup. Live counts: https://api.strale.io/v1/platform/facts

Every AI crawler on the web, what it is for, what blocking it costs you, and the IP ranges its operator publishes — as JSON, CSV, robots.txt and regex. Ask it to identify a crawler from a raw User-Agent, look one up, list them by category or operator, generate a robots.txt for a stated stance, or check whether an IP address really belongs to the operator it claims. Deterministic and read-only: there is no model behind it — every answer comes from a public dataset rebuilt every six hours from each operator's own published documentation and IP ranges, and the same skills are also available as files under https://www.pathwren.workers.dev/ and as MCP tools at https://www.pathwren.workers.dev/mcp. No key, no signup, no quota. Independent and unaffiliated with any operator it documents.

One decompose call: scope documents in, a contract-grade work breakdown out.

Real-time web search for AI agents. Search the web for current and up-to-date information, news, facts, research, documentation, and sources beyond model training data. Returns ranked structured JSON results with title, URL, description, and position for web grounding, RAG retrieval, research, and fact-finding. Send query, optional limit, and optional freshness as URL parameters. Keyless x402 p...

Parse unstructured (German) PDF documents into any agent-defined JSON schema. Pay per call with USDC via x402.

CoverBureau: pay-per-call compliance checking for US certificates of insurance (ACORD 25). Needs NO document: give an NAIC number or carrier name plus a state, and get recognition status, financial-strength rating, and whether it meets your threshold. Use it when you have a carrier but no certificate; validate_coi already checks the carrier when you do. Carrier data is a seed dataset; each resp...

Document conversion and OCR for AI agents: PDF, Office docs, images to text.

Document conversion MCP server: PDF to Markdown, image OCR, spreadsheet parsing.

npm breaking changes between two versions of a package, before a package upgrade: the documented breaking changes per version, read from the real CHANGELOG, GitHub release notes and alpha/beta/rc notes, plus major version bumps, Node.js engine, ESM/CJS, exports and peer dependency changes, migration guide links and a verdict. Exact versions or a major ('4'); a source URL for every item. One cal...

Semantic search across 10 pre-indexed developer documentation platforms — Cloudflare, Stripe, Anthropic, OpenAI, Next.js, and more.

Paste access-log lines and get back who crawled you. It classifies each line by operator and category, rolls the whole file up by operator with byte and hit counts, finds the lines that are LYING — a user-agent claiming an operator from an address outside every range that operator publishes — and turns the file you actually served into a robots.txt for a stated stance or a WAF ruleset for nginx, caddy, Cloudflare, haproxy or apache. Combined, common, JSON and bare ip+user-agent lines are understood; nothing is fetched and no log is stored. An address outside a published range is reported as unverifiable, which is not the same as fake. Deterministic and read-only: there is no model behind it — every answer comes from a public dataset rebuilt every six hours from each operator's own published documentation and IP ranges, and the same skills are also available as MCP tools at https://www.pathwren.workers.dev/mcp/triage. No key, no signup, no quota. Independent and unaffiliated with any operator it documents.

Check OpenAPI 3.0 and 3.1 documents for duplicate operation IDs, broken local references and incomplete definitions. Structured reports over an x402 API.

Civitas network stats on Algorand: orgs whitelisted, consent requests, identities issued, and a status / document-type breakdown of consent requests.