execute_program
Execute Python programs that call multiple MCP tools in sequence, handling loops, conditional logic, and data aggregation while keeping intermediate results local to reduce latency.
Instructions
Execute a Python program with access to MCP tools as async functions. Tool calls within the script are dispatched to their respective MCP servers. Only stdout (from print statements) is returned — intermediate tool results do not enter the conversation context. Use this when a task involves 3+ tool calls, loops, filtering, aggregation, or conditional logic based on intermediate results. For single tool calls, call the tool directly. All tool functions require await.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"code": "<code>"
},
"name": "execute_program"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| code | Yes | Python code to execute. MCP tools are available as async functions using their namespaced names (e.g., mcp__financial_data__query_financials). Use `await` for all tool calls. Use `print()` to produce output. |