Verified AI-agent tool catalog with pricing: search, voice, MCP, automation and data APIs.
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.
About this catalog: coverage, item count, last update, and usage terms.
This tool takes no arguments.
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 agentstack https://agentstackdata.com/mcp
About this catalog: coverage, item count, last update, and usage terms.
No arguments.
{
"type": "object",
"properties": {}
}Compare two or more tools side by side on key specs and price.
| Argument | Type | Description |
|---|---|---|
| names* | array |
{
"type": "object",
"required": [
"names"
],
"properties": {
"names": {
"type": "array",
"items": {
"type": "string"
}
}
}
}Get the full verified record for one tool by name.
| Argument | Type | Description |
|---|---|---|
| name* | string |
{
"type": "object",
"required": [
"name"
],
"properties": {
"name": {
"type": "string"
}
}
}List the catalog categories with item counts.
No arguments.
{
"type": "object",
"properties": {}
}Search the Agent Stack Data verified catalog of tools. Returns a compact ranked shortlist with prices and links.
| Argument | Type | Description |
|---|---|---|
| limit | number | |
| query | string | What the user is looking for, e.g. "voice API" or "quiet inverter" |
| category | string |
{
"type": "object",
"properties": {
"limit": {
"type": "number"
},
"query": {
"type": "string",
"description": "What the user is looking for, e.g. \"voice API\" or \"quiet inverter\""
},
"category": {
"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 4, 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.