Skip to main content

​
fastmcp.experimental.transforms.code_mode

​
Classes

​
SandboxProvider

Interface for executing LLM-generated Python code in a sandbox. WARNING: The code parameter passed to run contains untrusted, LLM-generated Python. Implementations MUST execute it in an isolated sandbox — never with plain exec(). Use MontySandboxProvider (backed by pydantic-monty) for production workloads. Methods:

​
run

​
MontySandboxProvider

Sandbox provider backed by pydantic-monty. Args:
  • limits: Resource limits for sandbox execution. Supported keys: max_feed_duration_secs (float), max_turn_duration_secs (float), max_memory (int), max_recursion_depth (int), and gc_interval (int). Time, memory, and GC limits are optional; omit a key to disable it. Recursion depth defaults to Monty’s standard maximum of 1,000. Duration limits measure sandbox execution time, excluding time waiting on host callbacks. The feed limit covers the whole execution; the turn limit resets after each host round trip. Unsupported keys raise ValueError rather than being silently ignored.
When the argument is omitted entirely, a conservative baseline is applied (max_feed_duration_secs=30, max_memory=100 MB) so the out-of-box configuration is not unbounded. Pass limits=None to disable configurable time, memory, and GC limits, or a dict to set your own. Monty’s standard recursion limit still applies. Methods:

​
run

Discovery tool factory that searches the catalog by query. Args:
  • search_fn: Async callable (tools, query) -> matching_tools. Defaults to BM25 ranking.
  • name: Name of the synthetic tool exposed to the LLM.
  • default_detail: Default detail level for search results. "brief" returns tool names and descriptions only. "detailed" returns compact markdown with parameter schemas. "full" returns complete JSON tool definitions.
  • default_limit: Maximum number of results to return. The LLM can override this per call. None means no limit.

​
GetSchemas

Discovery tool factory that returns schemas for tools by name. Args:
  • name: Name of the synthetic tool exposed to the LLM.
  • default_detail: Default detail level for schema results. "brief" returns tool names and descriptions only. "detailed" renders compact markdown with parameter names, types, and required markers. "full" returns the complete JSON schema.

​
GetTags

Discovery tool factory that lists tool tags from the catalog. Reads tool.tags from the catalog and groups tools by tag. Tools without tags appear under "untagged". Args:
  • name: Name of the synthetic tool exposed to the LLM.
  • default_detail: Default detail level. "brief" returns tag names with tool counts. "full" lists all tools under each tag.

​
ListTools

Discovery tool factory that lists all tools in the catalog. Args:
  • name: Name of the synthetic tool exposed to the LLM.
  • default_detail: Default detail level. "brief" returns tool names and one-line descriptions. "detailed" returns compact markdown with parameter schemas. "full" returns the complete JSON schema.

​
CodeMode

Transform that collapses all tools into discovery + execute meta-tools. Discovery tools are composable via the discovery_tools parameter. Each is a callable that receives catalog access and returns a Tool. By default, Search and GetSchemas are included for progressive disclosure: search finds candidates, get_schema retrieves parameter details, and execute runs code. The execute tool is always present and provides a sandboxed Python environment with call_tool(name, params) in scope. Methods:

​
transform_tools

​
get_tool