MCP.Market

AgentPay — Pay-per-call AI Microservices MCP server

online · 100% uptime
by agentpay.help·help.agentpay/agentpay·v1.3.2
No reviews yet

34 pay-per-call AI and data tools over x402; USDC on Base; no API keys.

C65/100grade C
Write a reviewRun it
What users say
No reviews yet
Be the first
Safety scan
C65/100

full report

Adoption
New

0 stars

Reviews

Write one

Nobody has reviewed AgentPay — Pay-per-call AI Microservices yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

AgentPay — Pay-per-call AI Microservices tools (34, 3 write)

write = sends, deletes, buys or posts
  • ad-copyFree

    Ad copy generator - platform-tuned marketing copy (Google/Meta/LinkedIn) with headlines, descriptions, CTAs and A/B variants. 15+ yrs media/ad-sales expertise baked in ($0.10 USDC per call)

  • agent-reputationFree

    Agent reputation score - endpoint trustworthiness ($0.01 USDC per call)

  • batchFree

    Batch endpoint - run up to 10 paid service calls in ONE request and one payment (services: summarize, sentiment, extract, translate). Cheaper and faster than paying per call ($0.05 USDC per call)

  • buy-creditswrite actionFree

    Prepaid credit pack - one $5 USDC x402 payment mints 600 call-credits (1 credit = $0.01, usable on every endpoint via X-AgentPay-Token; saves 20% vs pay-per-call) ($5 USDC per call)

  • buy-credits-prowrite actionFree

    Pro credit pack - $20 USDC mints 2600 call-credits (+30% bonus) usable on every endpoint via X-AgentPay-Token ($20 USDC per call)

  • buy-credits-starterwrite actionFree

    Starter credit pack - $1 USDC mints 115 call-credits (+15% bonus) usable on every endpoint via X-AgentPay-Token ($1 USDC per call)

  • classify-insuranceFree

    Insurance lead classifier — intent, urgency, line of business, confidence ($0.02 USDC per call)

  • code-reviewFree

    AI code review — bugs, security, performance, quality score ($0.05 USDC per call)

  • content-safetyFree

    Content security scan - PII, toxicity, bias ($0.02 USDC per call)

  • crypto-priceFree

    Real-time crypto prices - BTC, ETH, SOL + more ($0.005 USDC per call)

  • deep-researchFree

    PREMIUM deep research - multi-source web research into a cited markdown report ($0.25 USDC per call)

  • defi-yieldsFree

    DeFi yield data - APY, TVL, protocol info ($0.01 USDC per call)

  • eth-gasFree

    Ethereum gas prices - rapid/fast/standard/slow in gwei plus ETH spot price ($0.003 USDC per call)

  • extractFree

    Structured field extraction — key-value pairs from emails, forms, documents ($0.03 USDC per call)

  • geocodeFree

    Geocode place names to lat/lon; reverse geocode coordinates to addresses ($0.005 USDC per call)

  • image-describeFree

    Vision AI - describe any image from URL ($0.03 USDC per call)

  • insurance-analysisFree

    Full insurance analysis bundle — classification + field extraction + summary in one call ($0.10 USDC per call)

  • lead-scoreFree

    Lead scoring - score inbound leads 0-100 with intent, urgency, budget signals and recommended next action. Built for insurance/ad-sales funnels ($0.08 USDC per call)

  • legal-lookupFree

    Legal/regulatory lookup - company registration ($0.03 USDC per call)

  • market-intelFree

    Macro/economic snapshot - GDP, inflation, rates ($0.02 USDC per call)

  • memoryFree

    Persistent key-value memory scoped to your wallet - agents remember across runs ($0.005 USDC per call)

  • news-feedFree

    Real-time news feed - headlines by topic ($0.005 USDC per call)

  • on-chain-eventsFree

    Decoded on-chain events - recent transfers ($0.01 USDC per call)

  • prediction-marketFree

    Polymarket prediction market odds - live probabilities for any topic ($0.01 USDC per call)

  • sanctions-screenFree

    OFAC/EU sanctions screening - entity check ($0.02 USDC per call)

  • sentimentFree

    Sentiment analysis — positive/negative/neutral with emotions and keywords ($0.02 USDC per call)

  • summarizeFree

    AI text summarization — crisp 250-word summary of any text up to 20k chars ($0.01 USDC per call)

  • threat-intelFree

    CVE/threat intelligence - vulnerability lookup, severity ($0.02 USDC per call)

  • token-safetyFree

    Token safety check - rug pull risk, honeypot detection, liquidity analysis ($0.02 USDC per call)

  • translateFree

    Text translation — translate to any language ($0.03 USDC per call)

  • wallet-riskFree

    Wallet risk screening - OFAC sanctions, scam flags, tx patterns ($0.02 USDC per call)

  • weather-dataFree

    Weather data - current conditions and forecast ($0.005 USDC per call)

  • web-scrapeFree

    Extract clean text from any URL - agents read web pages ($0.01 USDC per call)

  • web-searchFree

    Web search - top results for any query with title, url, snippet ($0.01 USDC per call)

Public scan report

scanner v0.1.10 · 2026-10-30 · same rubric, same numbers if you re-run it

1 high1 low
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 1187ms20/20
  • Tool poisoning34 tool descriptions checked15/15
  • Auth qualityopen endpoint exposes 3 write-action tools with no auth3/15
  • Maintenanceno repository listed3/15
  • Maintainer identityendpoint served from the registry-verified namespace domain8/10

Findings (2)

  • highWrite-action tools reachable without authenticationauth.open-write
  • lowNo source repository listedmaint.no-repo
Overall 65/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How AgentPay — Pay-per-call AI Microservices compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
65/100
higher than 20% of 48,255 servers
Tools
34
the typical server has 7
Tools that change things
9%
typical: 0%. Fewer write tools means less an agent can break
Uptime
100%
of our recent checks; the typical remote server answers 100%
Response time
98 ms
faster than 85% of 30,031 servers

What its tools let an agent do: 29 read · 1 create · 4 change

Release history: 3 versions in the registry since 2026-08-28, latest 2026-10-29, typically one every 32 days.

Install AgentPay — Pay-per-call AI Microservices in Claude Code, Cursor or VS Code

claude mcp add --transport http agentpay https://agentpay.help/mcp
Add to Cursor

What the publisher says

From the AgentPay — Pay-per-call AI Microservices repository's README, as published. We do not edit it. Read it on GitHub

AgentPay — agentpay.help

Machine-payable AI microservices via the 402 Payment Required protocol (x402 / MPP)

No accounts. No API keys. No OAuth. Pay per call in USDC on Base.

AgentPay is an open-source reference implementation of the Machine Payments Protocol — wrapping local AI models behind an HTTP 402 paywall so that AI agents (and humans) can pay for compute on a per-request basis using stablecoins.

Built with Express 5, @x402/express, and Ollama-served Gemma models. Live on Base mainnet with the PayAI facilitator.

Table of Contents

  • Quick Start
  • Architecture
  • Services & Pricing
  • MCP Server
  • Tech Stack
  • Deployment
  • API Reference
  • Configuration
  • Contributing
  • License

Quick Start

Prerequisites

  • Node.js ≥ 20
  • Ollama running locally with the required model pulled
  • A wallet private key (for receiving payments)

1. Clone & install

git clone https://github.com/ronaldanton/x402-shop.git
cd x402-shop
npm install

2. Pull the AI model

ollama pull gemma3:1b
# Or use a larger model for better quality:
# ollama pull gemma4:31b-cloud

3. Configure

cp .env.example .env
# Edit .env — set SELLER_ADDRESS to your wallet address

4. Start the server

npm start
# AgentPay listening on :4021
#   payTo:   0xYourWalletAddress
#   network: eip155:84532 (Base Sepolia testnet)
#   facilitator: https://x402.org/facilitator

5. Test a paid request

# Unpaid request → HTTP 402 (paywall)
curl -s -o /dev/null -w "%{http_code}" -X POST https://agentpay.help/v1/summarize \
  -H 'Content-Type: application/json' \
  -d '{"text":"Machine Payments Protocol lets AI agents pay for API calls using the HTTP 402 status code."}'
# → 402

# Automated test (requires buyer wallet with USDC)
npm run test:402

6. Buy a service (buyer client)

# Set your buyer private key in .env
echo "BUYER_PK=0xYourPrivateKey" >> .env

# Run the buyer script
npm run buyer -- /v1/summarize ./payload.json

Architecture

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

AgentPay — Pay-per-call AI Microservices: common questions

Is AgentPay — Pay-per-call AI Microservices MCP server safe?
With care: it is graded C, so read the findings first (65/100). Read the AgentPay — Pay-per-call AI Microservices safety report
How do I install AgentPay — Pay-per-call AI Microservices?
It runs remotely at agentpay.help. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does AgentPay — Pay-per-call AI Microservices need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is AgentPay — Pay-per-call AI Microservices maintained?
The last commit was 48 days ago (2026-09-17). The latest release is v1.3.2.
Is AgentPay — Pay-per-call AI Microservices up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
How does AgentPay — Pay-per-call AI Microservices compare with other MCP servers?
safety score 65/100 (higher than 20% of 48,255 servers); tools 34 (the typical server has 7); tools that change things 9% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.