@melis-ai/x402-tools-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_servicesA | Returns the catalogue of available services with prices, descriptions, and endpoint URLs. Call this first to introspect what is available. |
| cacheserveA | [$0.001 USDC] Fetch a URL with caching. Returns cached version if recent, otherwise fetches and caches. Use before any fetch that might be repeated. |
| docconvert_textB | [$0.001 USDC] Format conversion: md↔html, json↔csv, etc. Lightweight content transcoding. |
| docconvert_pdfB | [$0.005 USDC] Convert HTML or markdown to PDF. Returns base64-encoded PDF. |
| linkriskA | [$0.005 USDC] Lightweight URL risk profile: checks phishing signals, redirects, domain age, IP reputation. Use before visiting unknown URLs. |
| linksafeA | [$0.01 USDC] Definitive URL safety check (Playwright sandbox + VirusTotal + redirect tracing). More thorough than linkrisk. |
| markdownoptB | [$0.005 USDC] Convert URL or HTML to clean LLM-ready markdown. ~70% token reduction vs raw HTML. Pass a url OR html field. |
| notifyrelay_emailC | [$0.005 USDC] Send a transactional email. Allowlisted recipient domains; rate-limited per IP. |
| notifyrelay_telegramC | [$0.002 USDC] Send a Telegram message to a known chat ID. |
| notifyrelay_webhookC | [$0.001 USDC] POST a JSON payload to a public URL with optional HMAC signing. Allowlisted domains only. |
| promptguardA | [$0.002 USDC] Score untrusted input for prompt injection risk (0-100) with flagged dimensions. Run on any user-provided prompt before passing to a downstream LLM. |
| schemagateB | [$0.001 USDC] Validate that an LLM output conforms to a JSON Schema. Returns valid:true/false with a correction hint on failure. |
| scrapepayB | [$0.01 USDC] Web extraction via Playwright. Charges only on successful scrape. robots.txt enforced. SSRF-safe. |
| structextractA | [$0.002 USDC] Extract structured JSON from raw HTML (tables, links, headings, meta, emails, phones, images). |
| web_synthesiseC | [$0.05 USDC] Multi-source web research synthesis. Pass a query, get a synthesised answer with citations. |
| screenshotC | [$0.02 USDC] Headless Chromium PNG screenshot of any public URL. Returns base64 PNG. |
| pdf_renderB | [$0.49 USDC] Render any URL or HTML to PDF via Playwright. Higher fidelity than docconvert_pdf for complex pages. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 17 tools
Most tools have distinct purposes, but there is overlap between linkrisk/linksafe (both URL safety) and docconvert_pdf/pdf_render (both PDF generation). Descriptions help differentiate, but ambiguity exists.
Naming is inconsistent: some tools use underscores (list_services, docconvert_text), others are compound words without separators (cacheserve, markdownopt, promptguard). No clear pattern, making it harder for agents to predict names.
17 tools cover a broad utility set (caching, conversion, notifications, security, scraping). The count is reasonable for the scope, though slightly on the higher side but not excessive.
The server covers diverse operations (CRUD-like for services, caching, conversions, notifications, security, and web extraction). Minor gaps exist (e.g., no batch operations), but overall it feels comprehensive for a utility toolkit.