Prototype · Preview: every server in the official registry, synced every 30 minutes. Reviews and accounts come in a later step.
PopNx MCPMCP servers for people who use AI · explained in plain words

Lumen Agent Utilities

by Dansgit2bversion 1.4.0i★ –iRuns in the cloud
Registry nameio.github.Dansgit2b/lumenworks-decoder

Install

Overview

Description from the maker (original English)

x402 agent tools: calldata/EIP-712/x402 decoders, web→MD, ENS, DNS, PubMed, arXiv, SEC, weather

PopNx MCP’s three pillars

These three are never merged into one score: opinions, measurements and popularity are different things.

What you can do with it

We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.

  • Connection: Runs in the cloud
  • Transport: Streamable HTTP
  • Category: Clinics & health

Install

Pick the AI app you use, then copy the settings.

Before you install

  • Basic checks: 1 of 1 passed
  • Runs on the maker’s server: what you ask it goes through their server.
  • The registry lists no key to fill in.

You need

Which app do you use?

Pick your app above. We remember it, so next time the button says “Install in …”.

Works in Claude on the web, desktop and mobile:

  1. Open Settings → Connectors
  2. Press Add custom connector
  3. Paste the address below and press Add
  4. If it asks you to sign in, sign in with the maker
SettingsConnectors1+ Add2https://…3
https://lumenworks-x402-decoder.onrender.com/mcp

Run this in your terminal

claude mcp add --transport http lumenworks-decoder https://lumenworks-x402-decoder.onrender.com/mcp

Open in Cursor

Or copy the settings yourself

Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "lumenworks-decoder": {
      "url": "https://lumenworks-x402-decoder.onrender.com/mcp"
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

Open in VS Code

Or copy the settings yourself

Paste into .vscode/mcp.json in your project

{
  "servers": {
    "lumenworks-decoder": {
      "type": "http",
      "url": "https://lumenworks-x402-decoder.onrender.com/mcp"
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

ChatGPT connects only to servers on the internet:

  1. Open ChatGPT on the web → Settings → Connectors (Apps)
  2. Press Create or Add (some plans need Developer mode under Advanced first)
  3. Paste the address below, give it a name and save
  4. If it asks you to sign in, sign in with the maker
SettingsConnectors1+ Create2https://…3
https://lumenworks-x402-decoder.onrender.com/mcp

Menu names can differ slightly by plan and over time.

Your choice stays on this device in a cookie; no account needed.

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

What it can do

We have not read this server’s tool list yet; we check endpoints in rotation.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 6, 2026

  • ✓ Pass

    Maker matches the repo

    The registry name was verified with the GitHub account Dansgit2b, which owns the repo

  • … Not checked yet

    Still maintained

    We have not read this repo from GitHub yet

  • … Not checked yet

    Has a licence

    We have not read this repo from GitHub yet

  • … Not checked yet

    Endpoint responds

    Not checked yet; we check endpoints in rotation

  • … Not checked yet

    Sign-in with OAuth

    Not checked yet; we check endpoints in rotation

  • … Not checked yet

    No hidden instructions in tool descriptions

    Not checked yet; we read the tool list when we check the endpoint

Compared with others in Clinics & healthi

  • More stars than 0% of the other 859 servers in this category
  • Published to the registry more recently than 54% of the other 859 servers in this category
  • Basic checks equal to or better than 100% of the other 859 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is Lumen Agent Utilities safe?

It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

The registry does not list a required key, though some servers ask you to sign in on first use.

Does it run on my computer or in the cloud?

It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.

Is it still maintained?

The GitHub repo last changed –, and the latest version (1.4.0) reached the registry 27 days ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.

What can I use instead?

In the same category: Mirobody, FHIR MCP Server, Google Health MCP

Alternatives

Servers in the same category from other makers, sorted by stars.

Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

Mirobody

by thetahealth

Lab results to LOINC codes and UCUM units, symptoms and diagnoses to ICPC-3. Offline, no API key.

Runs on your computer★ 1,408Apache-2.0Updated 5 days ago
Install

MCP server providing seamless access to FHIR APIs for AI tools and healthcare applications

Runs on your computer★ 137Apache-2.0Updated 8 days ago
Install

Google Health MCP

by davidmosiah

Privacy-first unofficial Google Health API v4 MCP server for health, sleep, activity, HR agents

Runs on your computer★ 79MITUpdated 4 months ago
Install

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

Lumen Works Agent API (x402)

Two listings on one origin:

  • Lumen Pre-Sign Check: POST /v1/tx/explain ($0.002). Use before signing any EVM transaction or EIP-712 message; returns {summary[], flags[], verdict} with looks_ok | review | do_not_sign_unless_intended. Agent policy: abort on do_not_sign_unless_intended, escalate review. Informational, not a security guarantee; looks_ok does not mean safe; no simulation. Accuracy set and known limits: ACCURACY.md. MCP: /mcp/presign.
  • Lumen Agent Utilities: every other route below. MCP: /mcp.

Trust terms: no signup; free tier 20 calls/hour/IP under /v1/free/...; GET/HEAD on any paid path returns the 402 quote (it never settles); not charged when a call errors, because the x402 middleware settles only after the handler returns a status below 400. Input schemas and real example outputs (examples.json, captured live by test/capture-examples.mjs) are in each route's Bazaar extension and in /openapi.json, validated with node test/validate-bazaar.mjs .

Stats: /v1/stats has anonymous aggregates only (UA family, daily unique counts from salted daily-rotating IP hashes, 30-day retention). They persist across deploys when STATS_GIST_ID + STATS_GIST_TOKEN (a gist-only token) are set; otherwise they are kept in memory.

Pay-per-call agent utilities, 0.001–0.002 USDC per call on Base mainnet via x402 (exact scheme, PayAI public facilitator). Author: Dan (Dansgit2b). Early-stage, unaudited.

Endpoint (POST JSON)What
/v1/x402/lint {header}decode + lint x402 PAYMENT-REQUIRED/SIGNATURE/RESPONSE
/v1/eip712/decode {typedData}domain separator, digest, risk notes
/v1/calldata/decode {data, signature?}selector, openchain/4byte lookup, decoded args
/v1/web/markdown {url, fullPage?, maxChars?} — $0.001public page → clean Markdown (Readability) + metadata. No JS rendering.
/v1/web/unfurl {url} — $0.001final URL, status, title, description, OG image, canonical, favicon
/v1/evm/address {address} (0x or ENS) — $0.002Ethereum+Base: ENS + records, EOA/contract/7702, balances, USDC/USDT, ERC-20 info (public RPC)
/v1/domain/lookup {domain} — $0.002DNS (DoH) A/AAAA/MX/NS/TXT/CAA, SPF/DMARC, RDAP registrar/created/expiry, age

Free tier: same paths under /v1/free/... (20/hour/IP). Discovery: /, /.well-known/x402, /openapi.json, /llms.txt. payTo: 0xee9790cB3960952F585379F831a89b4e00B4029A.

End-to-end proof (local run, 2026-10-10): paid call settled on Base, tx 0xff4af45df7caeef958b77700e96ba94e5ed37d3bac6e8cf40d6528a9497d77d4.

Deploy: Render (render.yaml, free plan) or any Docker host (Dockerfile). Set PUBLIC_BASE to the public origin. No secrets needed (server only receives payments). License MIT.

MCP server

Remote MCP (streamable HTTP, stateless JSON): https://lumenworks-x402-decoder.onrender.com/mcp, with tools x402_lint, eip712_decode, calldata_decode, web_markdown, url_unfurl, evm_address_lookup and domain_lookup. Free tier: 20 tool calls/hour/IP. After that the tool returns the x402 payment requirements for the matching paid HTTP endpoint (0.001–0.002 USD).

Celo

When X402_CELO_API_KEY (from the x402.celo.org dashboard) is set, every paid route also accepts USA₮ and USDC on Celo (eip155:42220), settled through Celo's hosted facilitator at api.x402.celo.org.

Free x402 payment safety check

POST /v1/x402/safety-check (MCP tool x402_payment_safety_check) — deterministic pre-payment check. Body: {url?, method?, payment_required?, expected_pay_to?, expected_network?, max_price_usdc?, listed_price_usdc?, facilitator_url?, client_config?}. We fetch the unpaid 402 (SSRF-guarded) and return ok | review | do_not_pay with checks: HTTPS/health/latency, payTo validity/checksum/mismatch, unknown asset/network, price vs your cap and the listed price, timeout/replay window, multiple payTo, unknown facilitator, missing spend caps / idempotency in your client config. Nothing is stored; inputs that look like private keys are rejected. 30/hour/IP.

Planned (not built): continuous monitoring with alerts on price/payTo/asset changes. Free waitlist: POST /v1/monitoring/waitlist {endpoint_url, contact?} (5/hour/IP). No date promised; stored in memory/logs only on a free host, so it may be lost on restart.

Stats

GET /v1/stats — anonymous in-memory counters since last restart: calls per endpoint, unpaid 402s vs paid settlements (conversion), coarse user-agent buckets. No IPs or bodies stored.

v1.3: explain-before-you-sign + public-data tools

Endpoint (POST)PriceMCP toolUpstream (free, no key)
/v1/tx/explain0.002explain_before_signcalldata (openchain/4byte) + EIP-712, risk flags
/v1/pubmed/search0.001pubmed_searchNCBI E-utilities
/v1/arxiv/search0.001arxiv_searcharXiv API
/v1/sec/filings0.001sec_filingsSEC EDGAR (set SEC_USER_AGENT with a contact email per SEC policy)
/v1/weather/forecast0.001weather_forecastOpen-Meteo (CC BY 4.0)
/v1/polymarket/markets0.001polymarket_marketsPolymarket Gamma (read-only data)

Free tier: /v1/free/ or MCP, 20 calls/hour/IP.

Facilitators

If CDP_API_KEY_ID and CDP_API_KEY_SECRET are set, Coinbase's CDP facilitator is used first. Settlements through it are what get the service indexed in the x402 Bazaar. The PayAI facilitator stays registered as the fallback. Without CDP keys, PayAI handles everything, as before.

Ask PopNx