Pay-per-call web tools for agents (extract, summarize, ask, JSON) via x402 USDC on Base.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Ask Claude Haiku a question. $0.01 USDC via x402.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http utility https://mortal01.xyz/mcp
Ask Claude Haiku a question. $0.01 USDC via x402.
| Argument | Type | Description |
|---|---|---|
| prompt* |
| string |
| system | string |
{
"type": "object",
"required": [
"prompt"
],
"properties": {
"prompt": {
"type": "string"
},
"system": {
"type": "string"
}
}
}Fetch a public URL and return clean readable text, title and links. Costs $0.005 USDC (x402, Base). Pass payment in X-PAYMENT header on the /mcp request, or call GET https://mortal01.xyz/extract?url= with an x402 client.
| Argument | Type | Description |
|---|---|---|
| url* | string |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string"
}
}
}Fetch a URL and return an AI summary with key points. $0.02 USDC via x402.
| Argument | Type | Description |
|---|---|---|
| url* | string | |
| length | string |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string"
},
"length": {
"enum": [
"short",
"long"
],
"type": "string"
}
}
}Extract structured JSON from free text given a JSON schema string. $0.02 USDC via x402.
| Argument | Type | Description |
|---|---|---|
| text* | string | |
| schema | string |
{
"type": "object",
"required": [
"text"
],
"properties": {
"text": {
"type": "string"
},
"schema": {
"type": "string"
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 11, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.