PrefectHQ/fastmcp · error

PromptsAsTools requires a FastMCP server instance, not a {ty

Error message

PromptsAsTools requires a FastMCP server instance, not a {type(provider).__name__}. The generated tools route through the server's middleware chain at runtime for auth and visibility. Pass your FastMCP server: PromptsAsTools(mcp)

What it means

PromptsAsTools is a transform that exposes a server's prompts as callable tools; because the generated tools route through the server's middleware chain (auth, visibility) at runtime, it requires an actual FastMCP instance. Passing any other Provider raises TypeError at construction.

Source

Thrown at fastmcp_slim/fastmcp/server/transforms/prompts_as_tools.py:64

    middleware, and visibility apply automatically.

    This transform should be applied to a FastMCP server instance, not
    a raw Provider, because the generated tools need the server's
    middleware chain for auth and visibility filtering.

    Example:
        ```python
        mcp = FastMCP("Server")
        mcp.add_transform(PromptsAsTools(mcp))
        # Now has list_prompts and get_prompt tools
        ```
    """

    def __init__(self, provider: Provider) -> None:
        from fastmcp.server.server import FastMCP

        if not isinstance(provider, FastMCP):
            raise TypeError(
                "PromptsAsTools requires a FastMCP server instance, not a"
                f" {type(provider).__name__}. The generated tools route through"
                " the server's middleware chain at runtime for auth and"
                " visibility. Pass your FastMCP server: PromptsAsTools(mcp)"
            )
        self._provider = provider

    def __repr__(self) -> str:
        return f"PromptsAsTools({self._provider!r})"

    async def list_tools(self, tools: Sequence[Tool]) -> Sequence[Tool]:
        """Add prompt tools to the tool list."""
        return [
            *tools,
            self._make_list_prompts_tool(),
            self._make_get_prompt_tool(),
        ]

View on GitHub (pinned to 1f02114297)

Solutions

1. Pass the FastMCP server instance: PromptsAsTools(mcp)
2. If you intended to transform a plain provider, mount it into a FastMCP server first and pass that server
3. Review the transform's signature — it accepts only FastMCP

Example fix

// before
PromptsAsTools(my_provider)
// after
PromptsAsTools(mcp)  # mcp is your FastMCP server

from fastmcp.server.server import FastMCP
assert isinstance(mcp, FastMCP), "PromptsAsTools needs a FastMCP server"

def is_fastmcp(obj) -> bool:
    from fastmcp.server.server import FastMCP
    return isinstance(obj, FastMCP)

try:
    t = PromptsAsTools(mcp)
except TypeError as e:
    logger.error("bad transform arg: %s", e)

When it happens

Trigger: PromptsAsTools(some_provider) where some_provider is not a FastMCP server — e.g., passing a Provider, a transform, or a mounted provider.

Common situations: Confusing PromptsAsTools with providers that accept Provider arguments; wiring transforms in a pipeline and passing the wrong object.

Related errors

• messages[{i}] must be Message, got {type(item).__name__}. Us
• messages must be str or list[Message], got {type(messages)._
• messages[{i}] must be Message or str, got {type(item).__name
• Prompt must return str, list[Message], or PromptResult, got
• Expected Prompt or @prompt-decorated function, got {type(pro

AI-assisted analysis of PrefectHQ/fastmcp@1f02114297 (2026-08-29). Data as JSON: /api/errors/fc193ef70fc59371. Report an issue: GitHub.