AI & Machine Learning
agentpay.help
Provides AI-powered text summarization, sentiment analysis, structured field extraction, translation, and insurance lead classification.
ENDPOINT 1
https://agentpay.help/mcp
MCP server metadata
- Name
- agentpay
- Version
- 1.0.0
AgentPay exposes pay-per-call AI microservices settled in USDC on Base mainnet via the x402 (HTTP 402) protocol. Each tool maps to one HTTP endpoint. Tools list their price in USD; payment is handled automatically when this server holds a funded wallet, otherwise the tool returns the payment challenge for the caller to sign.
Known tools 28
summarizeAI text summarization — crisp 250-word summary of any text up to 20k chars ($0.01 USDC per call)
Inferred read-onlyclassify-insuranceInsurance lead classifier — intent, urgency, line of business, confidence ($0.02 USDC per call)
Inferred read-onlysentimentSentiment analysis — positive/negative/neutral with emotions and keywords ($0.02 USDC per call)
Inferred read-onlyextractStructured field extraction — key-value pairs from emails, forms, documents ($0.03 USDC per call)
Inferred read-onlycode-reviewAI code review — bugs, security, performance, quality score ($0.05 USDC per call)
Inferred read-onlyinsurance-analysisFull insurance analysis bundle — classification + field extraction + summary in one call ($0.10 USDC per call)
Inferred read-onlytoken-safetyToken safety check - rug pull risk, honeypot detection, liquidity analysis ($0.02 USDC per call)
Inferred read-onlywallet-riskWallet risk screening - OFAC sanctions, scam flags, tx patterns ($0.02 USDC per call)
Inferred read-onlyweb-scrapeExtract clean text from any URL - agents read web pages ($0.01 USDC per call)
Inferred read-onlythreat-intelCVE/threat intelligence - vulnerability lookup, severity ($0.02 USDC per call)
Inferred read-onlyagent-reputationAgent reputation score - endpoint trustworthiness ($0.01 USDC per call)
Inferred read-onlyweb-searchWeb search - top results for any query with title, url, snippet ($0.01 USDC per call)
Inferred read-onlymemoryPersistent key-value memory scoped to your wallet - agents remember across runs ($0.005 USDC per call)
Inferred read-onlygeocodeGeocode place names to lat/lon; reverse geocode coordinates to addresses ($0.005 USDC per call)
Inferred read-onlyeth-gasEthereum gas prices - rapid/fast/standard/slow in gwei plus ETH spot price ($0.003 USDC per call)
Inferred read-onlyprediction-marketPolymarket prediction market odds - live probabilities for any topic ($0.01 USDC per call)
Inferred read-onlydeep-researchPREMIUM deep research - multi-source web research into a cited markdown report ($0.25 USDC per call)
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.agentpay]
url = "https://agentpay.help/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"agentpay": {
"type": "http",
"url": "https://agentpay.help/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: agentpay
Remote MCP URL: https://agentpay.help/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"agentpay": {
"url": "https://agentpay.help/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"agentpay": {
"type": "http",
"url": "https://agentpay.help/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "agentpay",
"transport": "streamable-http",
"url": "https://agentpay.help/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.