microsoft/semantic-kernel · error · FunctionExecutionException

Failed to call prompt '{prompt_name}'.

Error message

Failed to call prompt '{prompt_name}'.

What it means

Thrown by MCPPluginBase.get_prompt (mcp.py:640) as a FunctionExecutionException, wrapping any non-McpError exception raised by self.session.get_prompt. McpError instances are re-raised unchanged (structured MCP errors); transport/timeout/serialization failures are wrapped with the prompt_name for context.

Source

Thrown at python/semantic_kernel/connectors/mcp.py:640

            raise FunctionExecutionException(f"Failed to call tool '{tool_name}'.") from ex

    async def get_prompt(self, prompt_name: str, **kwargs: Any) -> list[ChatMessageContent]:
        """Call a prompt with the given arguments."""
        if not self.session:
            raise KernelPluginInvalidConfigurationError(
                "MCP server not connected, please call connect() before using this method."
            )
        if not self.load_prompts_flag:
            raise KernelPluginInvalidConfigurationError(
                "Prompts are not loaded for this server, please set load_prompts=True in the constructor."
            )
        try:
            prompt_result = await self.session.get_prompt(prompt_name, arguments=kwargs)
            return [_mcp_prompt_message_to_kernel_content(message) for message in prompt_result.messages]
        except McpError:
            raise
        except Exception as ex:
            raise FunctionExecutionException(f"Failed to call prompt '{prompt_name}'.") from ex

    def added_to_kernel(self, kernel: Kernel) -> None:
        """Add the plugin to the kernel."""
        self.kernel = kernel


# region: MCP Plugin Implementations


class MCPStdioPlugin(MCPPluginBase):
    """MCP stdio server configuration."""

    def __init__(
        self,
        name: str,
        command: str,
        *,
        load_tools: bool = True,

View on GitHub (pinned to c028a0c7dc)

Solutions

1. Inspect the chained __cause__ for the underlying error.
2. Increase request_timeout if the prompt is slow to render.
3. Verify kwargs match the prompt's declared arguments (see _get_parameter_dict_from_mcp_prompt).
4. Catch FunctionExecutionException separately from McpError to distinguish transport errors from structured server errors.

Example fix

# before
await plugin.get_prompt("summary", text=obj)  # non-serializable arg

# after
try:
    await plugin.get_prompt("summary", text=str(obj))
except FunctionExecutionException as ex:
    log.error("prompt failed: %s", ex.__cause__)

# confirm prompt args match the prompt's declared arguments before calling
def prompt_args_valid(args: dict, prompt_arguments: list) -> bool:
    names = {a.name for a in (prompt_arguments or [])}
    return set(args.keys()) <= names

import json

def args_are_json_serializable(args: dict) -> bool:
    try:
        json.dumps(args)
        return True
    except TypeError:
        return False

from semantic_kernel.exceptions.function_exceptions import FunctionExecutionException
from mcp.shared.exceptions import McpError

try:
    await plugin.get_prompt("summary", text="x")
except McpError:
    raise
except FunctionExecutionException as ex:
    log.error("get_prompt failed: %r", ex.__cause__)
    # check timeout / arg serialization, then retry

When it happens

Trigger: The MCP server's get_prompt raised a non-MCP exception, the network failed, request_timeout elapsed, or the prompt arguments could not be serialized. Originates at mcp.py:636-641.

Common situations: Network drop mid-call; timeout too short for a prompt that triggers heavy server work; argument schema mismatch; server process crashed during prompt rendering.

Related errors

• Failed to call tool '{tool_name}'.
• Timeout waiting for OAuth callback
• Unsupported content type: {type(content)}
• Failed to enter context manager.
• Prompts are not loaded for this server, please set load_prom

AI-assisted analysis of microsoft/semantic-kernel@c028a0c7dc (2026-08-13). Data as JSON: /api/errors/c16c84eb5c4025b8. Report an issue: GitHub.