get_model
Pack: huggingface · Connect: https://pipeworx.io/mcp (see Connect below for a single-pack URL)
No MCP client? Call it directly: GET https://gateway.pipeworx.io/v1/tools/get_model for the schema, then POST the same URL with its arguments for the data.
Detailed model info — config, tags, downloads, files at root.
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
repo_id | string | yes | |
revision | string | no | Branch/commit/tag (default main) |
Example call
Arguments
{
"repo_id": "bert-base-uncased"
}
curl
curl -X POST https://gateway.pipeworx.io/huggingface/mcp \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"get_model","arguments":{"repo_id":"bert-base-uncased"}}}'
TypeScript (@pipeworx/sdk)
import { Pipeworx } from '@pipeworx/sdk';
const pipeworx = new Pipeworx();
const result = await pipeworx.call('get_model', {
"repo_id": "bert-base-uncased"
});
More examples
{
"repo_id": "meta-llama/Llama-2-7b",
"revision": "main"
}
Response shape
Full JSON Schema
{
"type": "object",
"description": "Detailed model repository information including config, tags, downloads"
}
Connect
Add this to your MCP client config — every tool in the catalog, including this one — or use one-click install buttons:
{
"mcpServers": {
"pipeworx": {
"url": "https://pipeworx.io/mcp"
}
}
}
Connect to just the huggingface pack
{
"mcpServers": {
"huggingface": {
"url": "https://gateway.pipeworx.io/huggingface/mcp"
}
}
}
See Getting Started for client-specific install steps.