Consumable B2B leads, clean Markdown, e-com pricing, and SDK metadata for AI agents via MCP.
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.
Fetches live, real-time B2B buying intent signals, new tech launches from Show HN, tech stacks, domains, and hiring flags. Cost: $0.010 USDC via x402.
Maximum lead signals to return (1-25)
Filter category: all, ai, devtools, saas, fin, ecommerce
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 agentfuel402 https://agentfuel402.ak10082247.workers.dev/mcp
Fetches live, real-time B2B buying intent signals, new tech launches from Show HN, tech stacks, domains, and hiring flags. Cost: $0.010 USDC via x402.
| Argument | Type | Description |
|---|---|---|
| limit | integer | Maximum lead signals to return (1-25) |
| category | string | Filter category: all, ai, devtools, saas, fin, ecommerce |
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"default": 10,
"description": "Maximum lead signals to return (1-25)"
},
"category": {
"type": "string",
"default": "all",
"description": "Filter category: all, ai, devtools, saas, fin, ecommerce"
}
}
}Fetches any public URL, strips noise, sanitizes prompt injection attempts, and returns clean LLM Markdown and token counts. Cost: $0.005 USDC via x402.
| Argument | Type | Description |
|---|---|---|
| url* | string | Public URL to fetch, clean, and convert to LLM Markdown |
| strip_images | boolean | Whether to strip image markdown tags |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Public URL to fetch, clean, and convert to LLM Markdown"
},
"strip_images": {
"type": "boolean",
"default": false,
"description": "Whether to strip image markdown tags"
}
}
}Fetches live price, currency, in-stock boolean, and SKU variants from any Shopify or Schema.org product URL. Cost: $0.005 USDC via x402.
| Argument | Type | Description |
|---|---|---|
| url* | string | Shopify / WooCommerce / Schema.org product URL |
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Shopify / WooCommerce / Schema.org product URL"
}
}
}Queries live PyPI and npm registries to verify latest stable package versions, release notes, and breaking change warnings. Cost: $0.005 USDC via x402.
| Argument | Type | Description |
|---|---|---|
| package* | string | Package name on PyPI or npm (e.g. fastapi, viem, langchain) |
| ecosystem | string |
{
"type": "object",
"required": [
"package"
],
"properties": {
"package": {
"type": "string",
"description": "Package name on PyPI or npm (e.g. fastapi, viem, langchain)"
},
"ecosystem": {
"enum": [
"pypi",
"npm"
],
"type": "string",
"default": "pypi"
}
}
}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 8, 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.