microsoft/autogen · error · ValueError

name is required for call_tool

Error message

name is required for call_tool

What it means

Inside McpActor.call(), when type == 'call_tool' the args dict must contain a 'name' key; args.get('name') returning None triggers ValueError('name is required for call_tool'). The actor needs the tool name to route the command to the MCP server's tools/call method.

Source

Thrown at python/packages/autogen-ext/src/autogen_ext/tools/mcp/_actor.py:113

            self._active = True
            self._actor_task = asyncio.create_task(self._run_actor())

    async def call(self, type: str, args: McpActorArgs | None = None) -> McpFuture:
        if not self._active:
            raise RuntimeError("MCP Actor not running, call initialize() first")
        if self._actor_task and self._actor_task.done():
            raise RuntimeError("MCP actor task crashed", self._actor_task.exception())
        fut: asyncio.Future[McpFuture] = asyncio.Future()
        if type in {"list_tools", "list_prompts", "list_resources", "list_resource_templates", "shutdown"}:
            await self._command_queue.put({"type": type, "future": fut})
            res = await fut
        elif type in {"call_tool", "read_resource", "get_prompt"}:
            if args is None:
                raise ValueError(f"args is required for {type}")
            name = args.get("name", None)
            kwargs = args.get("kargs", {})
            if type == "call_tool" and name is None:
                raise ValueError("name is required for call_tool")
            elif type == "read_resource":
                uri = kwargs.get("uri", None)
                if uri is None:
                    raise ValueError("uri is required for read_resource")
                await self._command_queue.put({"type": type, "uri": uri, "future": fut})
            elif type == "get_prompt":
                if name is None:
                    raise ValueError("name is required for get_prompt")
                prompt_args = kwargs.get("arguments", None)
                await self._command_queue.put({"type": type, "name": name, "args": prompt_args, "future": fut})
            else:  # call_tool
                await self._command_queue.put({"type": type, "name": name, "args": kwargs, "future": fut})
            res = await fut
        else:
            raise ValueError(f"Unknown command type: {type}")
        return res

    async def close(self) -> None:

View on GitHub (pinned to 027ecf0a37)

Solutions

1. Include the tool name: args={'name': '<tool>', 'kargs': {<tool arguments>}}.
2. Check spelling/case of the 'name' key — it must be exactly 'name'.
3. Use the adapter/workbench layer (e.g. McpToolAdapter) which supplies the name from the discovered tool object.

Example fix

# before
await actor.call("call_tool", args={"kargs": {"query": "hello"}})

# after
await actor.call("call_tool", args={"name": "search", "kargs": {"query": "hello"}})

if cmd == "call_tool" and not args.get("name"):
    raise ValueError("call_tool requires args['name']")

When it happens

Trigger: Calling actor.call('call_tool', args={...}) where the dict has 'kargs' but no 'name', or the key is misspelled ('tool_name', 'tool').

Common situations: Building the args dict by hand and copying parameter names from MCP protocol JSON (which uses 'name' at top level but people confuse it with tool arguments); passing the tool's parameters directly instead of wrapping them under 'kargs' plus a 'name' key.

Related errors

• args is required for {type}
• name is required for get_prompt
• Failed to call MCP tool
• Invalid server URL configuration
• uri is required for read_resource

AI-assisted analysis of microsoft/autogen@027ecf0a37 (2026-08-15). Data as JSON: /api/errors/5fc63a9fcac9e0eb. Report an issue: GitHub.