A
licenseNot graded
qualityD
maintenanceEnables extracting clean Markdown from any webpage by paying $0.005 USDC per call via the x402 protocol, with automatic wallet-based payment settlement.
9 npm
MIT
x402 Web Tools
Server Details
Web/PDF to Markdown, transcription, paper search and citation checks. Pay per call in USDC via x402.
If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
- Status
- Healthy
- Uptime
- 69.6% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
A4.2/5.0
Scored across 9 tools
Disambiguation4/5
Most tools have clearly distinct purposes, but read_url and read_url_safe are obvious variants, and check_citation vs get_paper overlap on paper verification and retraction status. Descriptions clarify the boundaries, so confusion is limited.
Naming Consistency4/5
Names mostly follow a predictable verb_noun snake_case pattern (check_citation, get_paper, read_url, search_papers, transcribe_audio). The utility names health and ping deviate slightly but are conventional and readable.
Tool Count5/5
Nine tools is well-scoped for a read-only web and scholarly data service. Each tool has a clear role, including free health status and a paid ping for testing x402 payment flows.
Completeness4/5
The surface covers paper search, lookup, citation verification, URL/PDF reading, audio transcription, and service checks. Minor gaps include no batch operations, no reference-list extraction, and no general web search, but core read-only workflows are covered.
Available Tools
9 toolscheck_citationAInspect
Check whether a cited paper really exists (catch hallucinated or mistyped references) and whether it has been retracted. Give a doi, or a title with optional year and first_author. Returns exists, verdict (verified | found | doi_exists_metadata_mismatch | uncertain | not_found), confidence (high/medium/low) with a note on what matched, is_retracted (OpenAlex is_retracted + Crossref/Retraction Watch notices) and the best match. Data: OpenAlex (CC0, openalex.org) with Crossref REST (crossref.org) for retraction notices and as fallback. Upstream errors are not charged. Costs $0.002 USDC per check via x402.
| Name | Required | Description | Default |
|---|---|---|---|
| doi | No | DOI of the cited work (preferred if known) | |
| year | No | Publication year as cited (optional) | |
| title | No | Title of the cited work (used when no DOI is given; also cross-checked against a DOI) | |
| first_author | No | First author's name or surname as cited (optional) |
get_paperAInspect
Look up one scholarly work by DOI (10.xxxx/..., doi.org URL), arXiv id (arXiv:1706.03762) or OpenAlex work id (W...). Returns title, authors, year, venue, DOI, citation count, references count, open-access PDF link, abstract, OpenAlex id and a retraction flag (OpenAlex is_retracted plus Crossref/Retraction Watch notices). Data: OpenAlex (CC0, openalex.org) with Crossref REST (crossref.org) for retraction notices and as fallback. Not-found and upstream errors are not charged. Costs $0.002 USDC per lookup via x402.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | DOI, doi.org URL, arXiv:id or OpenAlex work id |
healthAInspect
Free health check. Returns service status, version, tool prices, network and the plain-HTTP x402 endpoints.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
pingAInspect
Paid connectivity test: returns ok and a server timestamp. Use it to check that your x402 payment flow works end to end. Costs $0.001 USDC per call via x402.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
read_pdfAInspect
Fetch a public PDF (max 10 MB) and convert it to Markdown with Cloudflare Workers AI toMarkdown. Returns title (if detected), url, markdown, word_count. Same URL safety rules as read_url. Failed conversions are not charged. Costs $0.006 USDC per call via x402.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Public http(s) URL of a PDF file |
read_urlAInspect
Fetch a public web page and return its main content as clean Markdown (readability extraction): title, url, final_url, markdown, word_count. HTML, plain text, Markdown, JSON and XML. Static fetch only (no JavaScript rendering). Respects robots.txt, blocks private/loopback/metadata hosts, max 3 MB / 15 s, no logins or paywall bypass. For PDFs use read_pdf. Failed reads are not charged. Costs $0.002 USDC per call via x402.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Public http(s) URL to read |
read_url_safeAInspect
Same as read_url plus a heuristic prompt-injection check: flags hidden/invisible text, instruction-like phrases ("ignore previous instructions", role reassignment, secret exfiltration, chat-template tokens), suspicious HTML comments and zero-width/Unicode-tag characters. Returns injection_check {flagged, risk none|low|medium|high, signals}. Heuristic, not a guarantee. Failed reads are not charged. Costs $0.003 USDC per call via x402.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Public http(s) URL to read |
search_papersAInspect
Search scholarly papers (OpenAlex index of 250M+ works). Returns up to 25 results with title, authors, year, venue, DOI, citation count, open-access PDF link, abstract (reconstructed from OpenAlex's inverted index; may be null when the publisher withholds it) and OpenAlex id. Optional from_year / to_year / open_access_only filters. Data: OpenAlex (CC0, openalex.org) with Crossref REST (crossref.org) for retraction notices and as fallback. Upstream errors are not charged. Costs $0.005 USDC per search via x402.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Number of results, 1-25 (default 10) | |
| query | Yes | Search terms (title, abstract and full-text relevance search) | |
| to_year | No | Latest publication year (inclusive) | |
| from_year | No | Earliest publication year (inclusive) | |
| open_access_only | No | Only open-access works (default false) |
transcribe_audioAInspect
Transcribe a public direct audio file URL (mp3, wav, m4a, ogg/opus, flac; max 25 MB and 10 minutes, checked from the file header before transcription) with Whisper (@cf/openai/whisper-large-v3-turbo) on Cloudflare Workers AI. Returns text, language, duration, segments with timestamps, optional SRT/VTT subtitles. YouTube/TikTok/Instagram and other page URLs are rejected. Failed transcriptions and files with no detected speech are not charged. Costs $0.01 USDC per file via x402.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Direct public URL of an audio file | |
| language | No | Optional ISO language hint, e.g. en, ur, es (auto-detected if omitted) | |
| subtitles | No | Also return SRT and/or WebVTT subtitles (default none) | |
| include_words | No | Include word-level timestamps in segments (default false) |
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
9 tool updates
- First observed
check_citation - First observed
get_paper - First observed
health - First observed
ping - First observed
read_pdf - First observed
read_url - First observed
read_url_safe - First observed
search_papers - First observed
transcribe_audio
Related MCP Connectors
Web pages to Markdown, metadata and small crawls for agents. Free daily calls, then USDC x402/MPP.
Turn any public web page into clean Markdown. Pay-per-call via x402: 0.005 USDC on Base.
Search, URL-to-markdown, change detection, live data, x402 trust tools. USDC pay-per-call.
Pay-per-call web reader (Markdown/RAG chunks) and agent utilities; x402 USDC on Base.
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables AI agents to fetch any public web page as clean Markdown, retrieve page metadata (title, description, canonical URL, OpenGraph/Twitter cards, JSON-LD), and crawl a page plus up to four linked same-site pages. Calls are paid per use in USDC via x402/MPP with no API key or account, and invalid inputs or unfetchable pages are never charged.3MIT
- AlicenseNot gradedqualityCmaintenanceEnables extracting clean, structured markdown from any URL—stripping nav, ads, and scripts—for RAG pipelines and AI research agents, with pay-per-call micropayments via x402.MIT
- AlicenseAqualityBmaintenancePay-per-use clean web reader for AI agents. URL in, markdown plus metadata out, in milliseconds. Settled per-call in USDC over x402 — no signup, no API keys.1102 npm3MIT
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd
Glama MCP Gateway
Add one secure layer between your agents and this server.