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": "agent_session_read",
"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": "agent_session_read",
"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": "agent_session_read",
"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: 'agent_session_read',
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": "Read Past Agent Session",
"description": "Reads a bounded, model-safe transcript projection. An agent may omit agentId to inspect itself; an owner or authorised caller supplies agentId. Omit sessionId for the newest visible session. The caller's current session, missing sessions and sessions hidden by venue policy all return exactly {found:false}. Tool scratch, diagnostics and unanswered turns are omitted.",
"dateCreated": "2026-08-24T00:00:00Z",
"operation": {
"adapter": "agent:sessionRead",
"readOnly": true,
"toolName": "agent_session_read",
"default": {
"maxTurns": 20,
"maxChars": 8000
},
"input": {
"type": "object",
"properties": {
"agentId": { "type": "string", "description": "Optional target agent id or g/<id> path. Omit only from that agent's own execution context. Reading an explicit target requires agent read access." },
"sessionId": { "type": "string", "description": "Optional 16-byte hex session id, with or without a 0x prefix. Omit to read the newest visible session." },
"maxTurns": { "type": "integer", "minimum": 1, "maximum": 100, "description": "Maximum newest projected turns. Default 20." },
"maxChars": { "type": "integer", "minimum": 1, "maximum": 100000, "description": "Maximum total content characters. A single oversized turn is truncated. Default 8000." }
}
},
"output": {
"type": "object",
"required": ["found"],
"properties": {
"found": { "type": "boolean" },
"sessionId": { "type": "string" },
"title": { "type": "string" },
"created": { "type": "integer" },
"updated": { "type": "integer" },
"turnCount": { "type": "integer", "description": "Total turns in the safe projection, before response bounds." },
"messages": { "type": "array", "items": { "type": "object" } },
"truncated": { "type": "boolean" }
}
}
}
}