Paid AI-agent tools ranked by real on-chain spend, wash trading filtered out. Updated daily.
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.
The ranking of one category: sellers by 30-day spend from real buyers, with buyers, paid calls, median price per call, chains, and links.
A category slug from categories, such as web-search
Keep only sellers whose median price per call is at most this, in USD
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 ranking https://agents.agentcharts.xyz/mcp
The ranking of one category: sellers by 30-day spend from real buyers, with buyers, paid calls, median price per call, chains, and links.
| Argument | Type | Description |
|---|
| category* | string | A category slug from categories, such as web-search |
| max_price | number | Keep only sellers whose median price per call is at most this, in USD |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"category"
],
"properties": {
"category": {
"type": "string",
"description": "A category slug from categories, such as web-search"
},
"max_price": {
"type": "number",
"description": "Keep only sellers whose median price per call is at most this, in USD"
}
}
}The categories of paid agent tools, with the slug each other tool takes.
No arguments.
{
"type": "object",
"properties": {}
}One ranked seller by its domain: category, rank, 30-day numbers, the last weeks, and links.
| Argument | Type | Description |
|---|---|---|
| domain* | string | The seller's domain, such as exa.ai |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"domain"
],
"properties": {
"domain": {
"type": "string",
"description": "The seller's domain, such as exa.ai"
}
}
}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 10, 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.