Read-only catalog of agent skills, plugins and MCP servers, with agreement against human experts.
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.
Get one pack by slug, including its EU AI Act checklist and verification block if any.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http catalog https://measuredagents.com/mcp
Get one pack by slug, including its EU AI Act checklist and verification block if any.
| Argument | Type | Description |
|---|---|---|
| slug* | string |
{
"type": "object",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string"
}
}
}List catalog packs. Optional filters: profession, platform, status (listed|submitted|verified), tier (pilot|verified|verified+|reference).
| Argument | Type | Description |
|---|---|---|
| tier | string | |
| status | string | |
| platform | string | |
| profession | string |
{
"type": "object",
"properties": {
"tier": {
"type": "string"
},
"status": {
"type": "string"
},
"platform": {
"type": "string"
},
"profession": {
"type": "string"
}
}
}List professions with their decision types and AI Act high-risk flag.
No arguments.
{
"type": "object",
"properties": {}
}Full-text search over pack name, vendor and summary.
| Argument | Type | Description |
|---|---|---|
| query* | string |
{
"type": "object",
"required": [
"query"
],
"properties": {
"query": {
"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.