microsoft/semantic-kernel · error · KernelPluginInvalidConfigurationError

Prompts are not loaded for this server, please set load_prom

Error message

Prompts are not loaded for this server, please set load_prompts=True in the constructor.

What it means

Thrown by MCPPluginBase.get_prompt (mcp.py:631) as a KernelPluginInvalidConfigurationError when load_prompts_flag is False. The plugin only discovers and registers MCP prompts during connect() if load_prompts=True; with it disabled, get_prompt refuses because no prompts were loaded.

Source

Thrown at python/semantic_kernel/connectors/mcp.py:631

        if not self.load_tools_flag:
            raise KernelPluginInvalidConfigurationError(
                "Tools are not loaded for this server, please set load_tools=True in the constructor."
            )
        try:
            return _mcp_call_tool_result_to_kernel_contents(await self.session.call_tool(tool_name, arguments=kwargs))
        except McpError:
            raise
        except Exception as ex:
            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

View on GitHub (pinned to c028a0c7dc)

Solutions

Construct with load_prompts=True if you intend to call prompts: MCPStdioPlugin(..., load_prompts=True).
If prompts were intentionally disabled, do not call get_prompt; use call_tool instead.
Re-create the plugin with the correct flags rather than toggling load_prompts_flag after init.
Remember the constructor default is load_prompts=True; this only fires when you explicitly disabled it.

Example fix

# before
plugin = MCPStdioPlugin(..., load_prompts=False)
await plugin.get_prompt("greet")

# after
plugin = MCPStdioPlugin(..., load_prompts=True)

Defensive patterns

Strategy: validation

Validate before calling

def can_call_prompts(plugin) -> bool:
    return getattr(plugin, "load_prompts_flag", False)

Type guard

def plugin_supports_prompts(plugin) -> bool:
    return bool(getattr(plugin, "load_prompts_flag", False))

Try / catch

from semantic_kernel.exceptions.kernel_exceptions import KernelPluginInvalidConfigurationError

try:
    await plugin.get_prompt("greet")
except KernelPluginInvalidConfigurationError as ex:
    if "Prompts are not loaded" in str(ex):
        plugin = MCPStdioPlugin(..., load_prompts=True)

Prevention

Construct with load_prompts=True whenever you intend to call prompts.
Remember the default is True; this only fires when you disabled prompts.
Do not call get_prompt on a tools-only plugin.
Re-create the plugin with correct flags rather than toggling load_prompts_flag.

When it happens

Trigger: Constructing the plugin with load_prompts=False (e.g. tools-only) and then calling get_prompt. Guard at mcp.py:630-633, after the session check.

Common situations: Setting load_prompts=False for a tools-only integration, then later needing a prompt; copy-pasting config; misunderstanding that load_prompts gates get_prompt, not just auto-loading.

Related errors

AI-assisted analysis of microsoft/semantic-kernel@c028a0c7dc (2026-08-13). Data as JSON: /api/errors/217ff7db1d5b40eb. Report an issue: GitHub.