π The fast, Pythonic way to build MCP servers and clients.
Document resource limits for MontySandboxProvider
Jeremiah Lowin75d6e2fc109d
diff --git a/docs/servers/transforms/code-mode.mdx b/docs/servers/transforms/code-mode.mdxindex 2a6db4921..df4e094ba 100644--- a/docs/servers/transforms/code-mode.mdx+++ b/docs/servers/transforms/code-mode.mdx@@ -138,6 +138,30 @@ mcp = FastMCP()```+### Resource Limits++The default `MontySandboxProvider` can enforce execution limits on sandboxed code β timeouts, memory caps, recursion depth, and more. Without limits, LLM-generated scripts can run indefinitely.++```python+from fastmcp.experimental.transforms import CodeMode, MontySandboxProvider++mcp.add_transform(CodeMode(+ sandbox_provider=MontySandboxProvider(+ limits={"max_duration_secs": 10, "max_memory": 50_000_000},+ ),+))+```++All keys are optional β omit any to leave that dimension uncapped:++| Key | Type | Description |+|---|---|---|+| `max_duration_secs` | `float` | Maximum wall-clock execution time |+| `max_memory` | `int` | Memory ceiling in bytes |+| `max_allocations` | `int` | Cap on total object allocations |+| `max_recursion_depth` | `int` | Maximum recursion depth |+| `gc_interval` | `int` | Garbage collection frequency |+### Custom Sandbox ProvidersThe default `MontySandboxProvider` uses [pydantic-monty](https://github.com/pydantic/pydantic-monty) for sandboxed execution. You can replace it with any object implementing the `SandboxProvider` protocol: