BerriAI/litellm · error · ValueError

url or spec_path is required for HTTP/SSE transport

Error message

url or spec_path is required for HTTP/SSE transport

What it means

Pydantic model_validator (validate_transport_fields) on the MCP server registration type rejecting an HTTP or SSE transport server that declares neither a 'url' nor a 'spec_path'. Remote MCP servers need an endpoint to connect to (directly or via a discovered spec), so the registration is refused before the server enters the registry. It is the HTTP/SSE counterpart of the stdio command/args checks in the same validator.

Source

Thrown at litellm/proxy/_types.py:1392

    @classmethod
    def validate_transport_fields(cls, values):
        if isinstance(values, dict):
            transport: Final = values.get("transport")
            if transport == MCPTransport.stdio:
                if not values.get("command"):
                    raise ValueError("command is required for stdio transport")
                if not values.get("args"):
                    raise ValueError("args is required for stdio transport")
                # Validate command against allowlist to prevent arbitrary execution
                base_command: Final = os.path.basename(values["command"])
                if base_command not in MCP_STDIO_ALLOWED_COMMANDS:
                    raise ValueError(
                        f"Command '{values['command']}' is not in the allowed commands list "
                        f"for stdio transport. Allowed commands: {sorted(MCP_STDIO_ALLOWED_COMMANDS)}"
                    )
            elif transport in [MCPTransport.http, MCPTransport.sse]:
                if not values.get("url") and not values.get("spec_path"):
                    raise ValueError("url or spec_path is required for HTTP/SSE transport")
        return values

    @model_validator(mode="before")
    @classmethod
    def validate_credentials_requirements(cls, values):
        """Validate credentials when provided.

        auth_value is optional — users may configure it dynamically
        (e.g. via per-request headers or OAuth2 flows) instead of
        storing a static value at server creation time.
        """
        return values

    @model_validator(mode="before")
    @classmethod
    def validate_dcr_bridge_auth_type(cls, values):
        if not isinstance(values, dict) or not values.get("dcr_bridge"):
            return values

View on GitHub (pinned to 77b7c6c40c)

Solutions

  1. Provide url or spec_path for HTTP/SSE transport.

Example fix

url='https://mcp.example.com/sse'
Defensive patterns

Strategy: validation

When it happens

Trigger: Thrown at litellm/proxy/_types.py:1392 when the library encounters an invalid state.

Common situations: See trigger scenarios.


AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/2ac96bf93ed67ef6. Report an issue: GitHub.