MCP Tool: llm

Basic Information

Tool Name:	llm_models
Asset Name:	LLM Models
Description:	Discover model operations from v/models/, grouped by serving provider, with CALLER-RELATIVE readiness. Returns provider defaults and recommendations as catalog paths, compatible model-id lists, and detailed operation entries. Hosted readiness means YOUR secret store or the venue environment supplies the conventional key (never returned); Ollama readiness is live reachability.
Adapter:	langchain
Asset Hash:	`0x76d5bda9af08a25daef1aa9c8811612bd2feddad8e14e58bf5aec9859b266533`

Input

Property	Type	Description
`provider`	string	Optional serving-profile filter, such as openai, anthropic, gemini, deepseek, xai, mistral, openrouter or ollama

Output

Type: object

Schema: <code>{ "description": "{providers: [{op, provider, keySecret?, ready, default, recommended?, defaultModel, recommendations?, models:[id], entries:[{op,id,name,tags?,budget?,options?,aliases?}], installedModels?, url?, note?}]} — prefer configuring llmOperation to an entry op; caller model/url/apiKey values remain ordinary overrides." }</code>

MCP Tool Usage Examples

This tool can be called via the MCP (Model Context Protocol) endpoint. Here are examples of how to use it:

JSON-RPC Call Example:

POST to https://venue-1.covia.ai/mcp

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "llm_models",
    "arguments": {
      "input": "your input here"
    }
  }
}

cURL Example:

curl -X POST https://venue-1.covia.ai/mcp \\
  -H "Content-Type: application/json" \\
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
      "name": "llm_models",
      "arguments": {
        "input": "your input here"
      }
    }
  }'

Python Example:

import requests
import json

url = "https://venue-1.covia.ai/mcp"
payload = {
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
        "name": "llm_models",
        "arguments": {
            "input": "your input here"
        }
    }
}

response = requests.post(url, json=payload)
result = response.json()
print(result)

JavaScript/Node.js Example:

const fetch = require('node-fetch');

const url = 'https://venue-1.covia.ai/mcp';
const payload = {
    jsonrpc: '2.0',
    id: 1,
    method: 'tools/call',
    params: {
        name: 'llm_models',
        arguments: {
            input: 'your input here'
        }
    }
};

fetch(url, {
    method: 'POST',
    headers: {
        'Content-Type': 'application/json'
    },
    body: JSON.stringify(payload)
})
.then(response => response.json())
.then(data => console.log(data));

Asset Metadata

{
	"name": "LLM Models",
	"description": "Discover model operations from v/models/, grouped by serving provider, with CALLER-RELATIVE readiness. Returns provider defaults and recommendations as catalog paths, compatible model-id lists, and detailed operation entries. Hosted readiness means YOUR secret store or the venue environment supplies the conventional key (never returned); Ollama readiness is live reachability.",
	"dateCreated": "2026-07-17T00:00:00Z",
	"operation": {
		"adapter": "langchain:models",
		"toolName": "llm_models",
		"input": {
			"type": "object",
			"properties": {
				"provider": { "type": "string", "description": "Optional serving-profile filter, such as openai, anthropic, gemini, deepseek, xai, mistral, openrouter or ollama" }
			}
		},
		"output": {
			"description": "{providers: [{op, provider, keySecret?, ready, default, recommended?, defaultModel, recommendations?, models:[id], entries:[{op,id,name,tags?,budget?,options?,aliases?}], installedModels?, url?, note?}]} — prefer configuring llmOperation to an entry op; caller model/url/apiKey values remain ordinary overrides."
		}
	}
}

Tool Details: llm_models