MCP Tool: agent

Basic Information

Tool Name:	agent_context
Asset Name:	Agent Context
Description:	Render the exact L3 input (messages + tools + model) an agent would receive on a fresh transition, as pretty-printed JSON. Includes system prompt, context entries, harness tools (with typed schemas when outputs is set), and base tools. Pass an optional task to see the complete first-iteration message vector including the synthesised goal.
Adapter:	agent
Asset Hash:	`0x293ab928deac5685382a8ef55d0fc53c4a275584ed4fead2ea2996e3437522ce`

Input

Property	Type	Description
`agentId`*	string	Agent name to inspect
`task`	any	Optional task input — if provided, a goal user message is synthesised and appended to the messages, showing the complete first-iteration context

Output

Type: string

Schema: <code>{ "type": "string", "description": "Pretty-printed JSON of the L3 input: {messages, tools, model}" }</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-3.covia.ai/mcp

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

cURL Example:

curl -X POST https://venue-3.covia.ai/mcp \\
  -H "Content-Type: application/json" \\
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
      "name": "agent_context",
      "arguments": {
        "input": "your input here"
      }
    }
  }'

Python Example:

import requests
import json

url = "https://venue-3.covia.ai/mcp"
payload = {
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
        "name": "agent_context",
        "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-3.covia.ai/mcp';
const payload = {
    jsonrpc: '2.0',
    id: 1,
    method: 'tools/call',
    params: {
        name: 'agent_context',
        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": "Agent Context",
	"description": "Render the exact L3 input (messages + tools + model) an agent would receive on a fresh transition, as pretty-printed JSON. Includes system prompt, context entries, harness tools (with typed schemas when outputs is set), and base tools. Pass an optional task to see the complete first-iteration message vector including the synthesised goal.",
	"dateCreated": "2026-04-12T00:00:00Z",
	"operation": {
		"adapter": "agent:context",
		"toolName": "agent_context",
		"input": {
			"type": "object",
			"properties": {
				"agentId": { "type": "string", "description": "Agent name to inspect" },
				"task": { "description": "Optional task input — if provided, a goal user message is synthesised and appended to the messages, showing the complete first-iteration context" }
			},
			"required": ["agentId"]
		},
		"output": {
			"type": "string",
			"description": "Pretty-printed JSON of the L3 input: {messages, tools, model}"
		}
	}
}

Tool Details: agent_context