MCPTOOLSET issue on connecting new mcp server with google ADK

[sonicxz]

Describe the bug

1. On Connecting MCP server, I saw this issue
   pydantic_core._pydantic_core.ValidationError: 2 validation errors for LlmAgent tools.0.callable

2. sometimes below one
   Input should be callable [type=callable_type, input_value=<google.adk.tools.mcp_too...t object at 0x11d6469d0>, input_type=MCPToolset]
   For further information visit https://errors.pydantic.dev/2.11/v/callable_type
   tools.0.is-instance[BaseTool]

Also seeing below error more promienantly
3. {"error": "Function playwright_agent is not found in the tools_dict."}

To Reproduce
Steps to reproduce the behavior:

1. Install '...'
   google-adk==1.2.1
   litellm==1.72.2
   openai==1.75.0
   python-dotenv==1.1.0

python 3.11

and below is my agent.py file, rest is same as per the tutorial of google-adk

import os
from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import MCPToolset, StdioServerParameters

from contextlib import AsyncExitStack
import logging

from dotenv import load_dotenv

load_dotenv()

logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

def create_playwright_agent():
    """Creates the agent responsible for executing browser tests via MCP."""
    # In a real implementation, you would fetch tools from the MCP server here.

    logging.info("--- Playwright Into Action ---")

    tool = MCPToolset(
            connection_params=StdioServerParameters(
                command='npx',
                args=[
                    "@playwright/mcp@latest",
                ],
            ),
            # You can filter for specific Maps tools if needed:
            # tool_filter=['get_directions', 'find_place_by_id']
        )

    return LlmAgent(
        name="playwright_agent",
        model=os.getenv("GEMINI_AGENT_MODEL_NAME"),  # A model good for tool use
        description="Executes a structured JSON test plan using Playwright tools from an MCP server.",
        instruction=(
            "You are a browser automation expert. You will receive a JSON object with a test plan. "
            "Execute each step in the plan sequentially using the provided Playwright tools. "
            "Log the outcome of each step and return a list of result dictionaries."
        ),
        tools=[
            MCPToolset(
                connection_params=StdioServerParameters(
                    command='npx',
                    args=[
                        "-y",
                        "@modelcontextprotocol/server-google-maps",
                    ],
                    # Pass the API key as an environment variable to the npx process
                    # This is how the MCP server for Google Maps expects the key.
                    env={
                        "GOOGLE_MAPS_API_KEY":  *****''
                    }
                ),
                # You can filter for specific Maps tools if needed:
                # tool_filter=['get_directions', 'find_place_by_id']
            )
    ],
    ) 

root-agents.py file

import os
from dotenv import load_dotenv
from google.adk.agents import Agent
from automation_web_agent.agents.playwright.agent import create_playwright_agent
from automation_web_agent.models.llm.llm_model import get_llm_model
from automation_web_agent.config.logging_config import setup_logging


from google.adk.tools.mcp_tool.mcp_toolset import MCPToolset

from google.adk.tools.mcp_tool.mcp_toolset import MCPToolset, SseServerParams
from contextlib import AsyncExitStack
import logging


# Setup logging configuration
setup_logging()

# --- Configure Logging ---
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

load_dotenv()

# Gemini API Key (Get from Google AI Studio: https://aistudio.google.com/app/apikey)
os.environ["GOOGLE_API_KEY"] = os.getenv("GEMINI_KEY")

# 1. Create the specialized agents that will form the team.
tester = create_playwright_agent()

def  create_root_agent():
    """
    Creates and configures the main RootAgent and its team of sub-agents.
    """
    logging.info("--- Building the Agent Team ---")

    # 2. Create the RootAgent, passing the other agents as sub-agents.
    root_agent_v1 = Agent(
        name="test_orchestrator_root_agent",
        model=get_llm_model(),  # A powerful model for orchestration
        description="A master agent that orchestrates a team of specialized testing agents to fulfill a user's request.",
        instruction=(
            "You are the project manager of a testing team. Your goal is to completely fulfill the user's test request. "
            "1. To understand and plan the request, delegate to the 'refine_prompt_agent'. "
            "2. To execute the plan in a browser, delegate the plan to the 'playwright_agent'. "
            "3. To summarize the execution results, delegate the results to the 'report_generator_agent'. "
            "Follow this workflow: Plan -> Execute -> Report. Do not respond to the user until the final report is ready."
        ),
        sub_agents=[tester]
    )

    logging.info("--- Agent Team Assembled Successfully ---")
    return root_agent_v1

root_agent = create_root_agent()

2. Run 'adk web'
3. Open 'terminal to see this error'

Expected behavior
To run MCP server and see the agent working

Desktop (please complete the following information):

• OS: [e.g. iOS] MacOs 15.1.1
• Python version(python -V): python 3.11
• ADK version(pip show google-adk): 1.2.1

Additional context
I tried with many other MCP's but still seeing same issue

Any help would be really appreciated

[Himanshu-Tyagi-Indium]

are you able to connect with playwright MCP server now, can you please help me, i am getting below error.

tools created successfully
fetched 25 tools from the server successfully.
2025-06-11 19:11:59,650 - INFO - google_llm.py:83 - Sending out request, model: gemini-2.0-flash, backend: ml_dev, stream: False
2025-06-11 19:11:59,658 - INFO - google_llm.py:89 -
LLM Request:

System Instruction:
Help user to navigate to the user requested URL and take the acreenshot.
Use the following tool to navigate to the webpage and take the screenshot.
- browser_navigate
- browser_snapshot

    Once you take the snapshot, save it into the D:\Google-ADK\screenshot folder.

You are an agent. Your internal name is "browser_automation_agent".

Contents:
{"parts":[{"text":"can you navigate to https://www.google.com/"}],"role":"user"}

Functions:
browser_close: {} -> None
browser_resize: {'width': {'description': 'Width of the browser window', 'type': <Type.NUMBER: 'NUMBER'>}, 'height': {'description': 'Height of the browser window', 'type': <Type.NUMBER: 'NUMBER'>}} -> None
browser_console_messages: {} -> None
browser_handle_dialog: {'accept': {'description': 'Whether to accept the dialog.', 'type': <Type.BOOLEAN: 'BOOLEAN'>}, 'promptText': {'description': 'The text of the prompt in case of a prompt dialog.', 'type': <Type.STRING: 'STRING'>}} -> None
browser_file_upload: {'paths': {'description': 'The absolute paths to the files to upload. Can be a single file or multiple files.', 'items': {'type': <Type.STRING: 'STRING'>}, 'type': <Type.ARRAY: 'ARRAY'>}} -> None
browser_install: {} -> None
browser_press_key: {'key': {'description': 'Name of the key to press or a character to generate, such as ArrowLeft or a', 'type': <Type.STRING: 'STRING'>}} -> None
browser_navigate: {'url': {'description': 'The URL to navigate to', 'type': <Type.STRING: 'STRING'>}} -> None
browser_navigate_back: {} -> None
browser_navigate_forward: {} -> None
browser_network_requests: {} -> None
browser_pdf_save: {'filename': {'description': 'File name to save the pdf to. Defaults to page-{timestamp}.pdf if not specified.', 'type': <Type.STRING: 'STRING'>}} -> None
browser_take_screenshot: {'raw': {'description': 'Whether to return without compression (in PNG format). Default is false, which returns a JPEG image.', 'type': <Type.BOOLEAN: 'BOOLEAN'>}, 'filename': {'description': 'File name to save the screenshot to. Defaults to page-{timestamp}.{png|jpeg} if not
specified.', 'type': <Type.STRING: 'STRING'>}, 'element': {'description': 'Human-readable element description used to obtain permission to screenshot the element. If not provided, the screenshot will be taken of viewport. If element is provided, ref must be provided too.', 'type': <Type.STRING: 'STRING'>}, 'ref': {'description': 'Exact target element reference from the page snapshot. If not provided, the screenshot will be taken of viewport. If ref is
provided, element must be provided too.', 'type': <Type.STRING: 'STRING'>}} -> None
browser_snapshot: {} -> None
browser_click: {'element': {'description': 'Human-readable element description used to obtain permission to interact with the element', 'type': <Type.STRING: 'STRING'>}, 'ref': {'description': 'Exact target element reference from the page snapshot', 'type': <Type.STRING: 'STRING'>}} -> None
browser_drag: {'startElement': {'description': 'Human-readable source element description used to obtain the permission to interact with the element', 'type': <Type.STRING: 'STRING'>}, 'startRef': {'description': 'Exact source element reference from the page snapshot', 'type': <Type.STRING: 'STRING'>},
'endElement': {'description': 'Human-readable target element description used to obtain the permission to interact with the element', 'type': <Type.STRING: 'STRING'>}, 'endRef': {'description': 'Exact target element reference from the page snapshot', 'type': <Type.STRING: 'STRING'>}} -> None
browser_hover: {'element': {'description': 'Human-readable element description used to obtain permission to interact with the element', 'type': <Type.STRING: 'STRING'>}, 'ref': {'description': 'Exact target element reference from the page snapshot', 'type': <Type.STRING: 'STRING'>}} -> None
browser_type: {'element': {'description': 'Human-readable element description used to obtain permission to interact with the element', 'type': <Type.STRING: 'STRING'>}, 'ref': {'description': 'Exact target element reference from the page snapshot', 'type': <Type.STRING: 'STRING'>}, 'text': {'description': 'Text to type into the element', 'type': <Type.STRING: 'STRING'>}, 'submit': {'description': 'Whether to submit entered text (press Enter after)', 'type': <Type.BOOLEAN: 'BOOLEAN'>}, 'slowly': {'description': 'Whether to type one character at a time. Useful for triggering key handlers in the page. By default entire text is filled in at once.', 'type': <Type.BOOLEAN: 'BOOLEAN'>}} -> None
browser_select_option: {'element': {'description': 'Human-readable element description used to obtain permission to interact with the element', 'type':
<Type.STRING: 'STRING'>}, 'ref': {'description': 'Exact target element reference from the page snapshot', 'type': <Type.STRING: 'STRING'>}, 'values': {'description': 'Array of values to select in the dropdown. This can be a single value or multiple values.', 'items': {'type': <Type.STRING: 'STRING'>}, 'type': <Type.ARRAY: 'ARRAY'>}} -> None
browser_tab_list: {} -> None
browser_tab_new: {'url': {'description': 'The URL to navigate to in the new tab. If not provided, the new tab will be blank.', 'type': <Type.STRING: 'STRING'>}} -> None
browser_tab_select: {'index': {'description': 'The index of the tab to select', 'type': <Type.NUMBER: 'NUMBER'>}} -> None
browser_tab_close: {'index': {'description': 'The index of the tab to close. Closes current tab if not provided.', 'type': <Type.NUMBER: 'NUMBER'>}} ->
None
browser_generate_playwright_test: {'name': {'description': 'The name of the test', 'type': <Type.STRING: 'STRING'>}, 'description': {'description': 'The description of the test', 'type': <Type.STRING: 'STRING'>}, 'steps': {'description': 'The steps of the test', 'items': {'type': <Type.STRING: 'STRING'>}, 'type': <Type.ARRAY: 'ARRAY'>}} -> None
browser_wait_for: {'time': {'description': 'The time to wait in seconds', 'type': <Type.NUMBER: 'NUMBER'>}, 'text': {'description': 'The text to wait for', 'type': <Type.STRING: 'STRING'>}, 'textGone': {'description': 'The text to wait for to disappear', 'type': <Type.STRING: 'STRING'>}} -> None

2025-06-11 19:11:59,686 - INFO - models.py:7466 - AFC is enabled with max remote calls: 10.
2025-06-11 19:12:01,758 - INFO - _client.py:1740 - HTTP Request: POST https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent "HTTP/1.1 400 Bad Request"
2025-06-11 19:12:01,780 - ERROR - fast_api.py:637 - Error in event_generator: 400 INVALID_ARGUMENT. {'error': {'code': 400, 'message': 'Invalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[0].parameters': Cannot find field.\nInvalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[1].parameters': Cannot find field.\nInvalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[2].parameters': Cannot find field.\nInvalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[3].parameters': Cannot find field.\nInvalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[4].parameters': Cannot find field.\nInvalid JSON payload received. Unknown name "additional_properties" at
'tools[0].function_declarations[5].parameters': Cannot find field.\nInvalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[6].parameters': Cannot find field.\nInvalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[7].parameters': Cannot find field.\nInvalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[8].parameters': Cannot find field.\nInvalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[9].parameters': Cannot find field.\nInvalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[10].parameters': Cannot find field.\nInvalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[11].parameters': Cannot find field.\nInvalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[12].parameters': Cannot find field.\nInvalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[13].parameters': Cannot find field.\nInvalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[14].parameters': Cannot find field.\nInvalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[15].parameters': Cannot find field.\nInvalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[16].parameters': Cannot find field.\nInvalid JSON payload received. Unknown name
"additional_properties" at 'tools[0].function_declarations[17].parameters': Cannot find field.\nInvalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[18].parameters': Cannot find field.\nInvalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[19].parameters': Cannot find field.\nInvalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[20].parameters': Cannot find field.\nInvalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[21].parameters': Cannot find field.\nInvalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[22].parameters': Cannot find field.\nInvalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[23].parameters': Cannot find field.\nInvalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[24].parameters': Cannot find field.', 'status': 'INVALID_ARGUMENT', 'details': [{'@type': 'type.googleapis.com/google.rpc.BadRequest', 'fieldViolations': [{'field': 'tools[0].function_declarations[0].parameters', 'description': 'Invalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[0].parameters': Cannot find field.'}, {'field': 'tools[0].function_declarations[1].parameters', 'description': 'Invalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[1].parameters': Cannot find field.'}, {'field': 'tools[0].function_declarations[2].parameters', 'description': 'Invalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[2].parameters': Cannot find field.'}, {'field': 'tools[0].function_declarations[3].parameters', 'description': 'Invalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[3].parameters': Cannot find field.'}, {'field': 'tools[0].function_declarations[4].parameters', 'description': 'Invalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[4].parameters': Cannot
find field.'}, {'field': 'tools[0].function_declarations[5].parameters', 'description': 'Invalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[5].parameters': Cannot find field.'}, {'field': 'tools[0].function_declarations[6].parameters', 'description': 'Invalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[6].parameters': Cannot find field.'}, {'field': 'tools[0].function_declarations[7].parameters', 'description': 'Invalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[7].parameters': Cannot find field.'}, {'field': 'tools[0].function_declarations[8].parameters', 'description': 'Invalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[8].parameters': Cannot find field.'}, {'field': 'tools[0].function_declarations[9].parameters', 'description': 'Invalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[9].parameters': Cannot find field.'}, {'field': 'tools[0].function_declarations[10].parameters', 'description': 'Invalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[10].parameters': Cannot find field.'}, {'field': 'tools[0].function_declarations[11].parameters', 'description': 'Invalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[11].parameters': Cannot find field.'}, {'field': 'tools[0].function_declarations[12].parameters', 'description': 'Invalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[12].parameters': Cannot find field.'}, {'field': 'tools[0].function_declarations[13].parameters', 'description': 'Invalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[13].parameters': Cannot find field.'},
{'field': 'tools[0].function_declarations[14].parameters', 'description': 'Invalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[14].parameters': Cannot find field.'}, {'field': 'tools[0].function_declarations[15].parameters', 'description': 'Invalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[15].parameters': Cannot find field.'}, {'field': 'tools[0].function_declarations[16].parameters', 'description': 'Invalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[16].parameters': Cannot find field.'}, {'field': 'tools[0].function_declarations[17].parameters', 'description': 'Invalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[17].parameters': Cannot find field.'}, {'field': 'tools[0].function_declarations[18].parameters', 'description': 'Invalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[18].parameters': Cannot find field.'}, {'field': 'tools[0].function_declarations[19].parameters', 'description': 'Invalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[19].parameters': Cannot find field.'}, {'field': 'tools[0].function_declarations[20].parameters', 'description': 'Invalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[20].parameters': Cannot find field.'}, {'field': 'tools[0].function_declarations[21].parameters', 'description': 'Invalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[21].parameters': Cannot find field.'}, {'field': 'tools[0].function_declarations[22].parameters', 'description': 'Invalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[22].parameters': Cannot find field.'}, {'field': 'tools[0].function_declarations[23].parameters', 'description': 'Invalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[23].parameters': Cannot find field.'}, {'field': 'tools[0].function_declarations[24].parameters', 'description': 'Invalid JSON payload received. Unknown name "additional_properties" at 'tools[0].function_declarations[24].parameters': Cannot find field.'}]}]}}
Traceback (most recent call last):
File "D:\Anaconda\envs\playwright_env\Lib\site-packages\google\adk\cli\fast_api.py", line 626, in event_generator
async for event in runner.run_async(
File "D:\Anaconda\envs\playwright_env\Lib\site-packages\google\adk\runners.py", line 197, in run_async
async for event in invocation_context.agent.run_async(invocation_context):
File "D:\Anaconda\envs\playwright_env\Lib\site-packages\google\adk\agents\base_agent.py", line 141, in run_async
async for event in self._run_async_impl(ctx):
File "D:\Anaconda\envs\playwright_env\Lib\site-packages\google\adk\agents\llm_agent.py", line 232, in _run_async_impl
async for event in self._llm_flow.run_async(ctx):
File "D:\Anaconda\envs\playwright_env\Lib\site-packages\google\adk\flows\llm_flows\base_llm_flow.py", line 231, in run_async
async for event in self._run_one_step_async(invocation_context):
File "D:\Anaconda\envs\playwright_env\Lib\site-packages\google\adk\flows\llm_flows\base_llm_flow.py", line 257, in _run_one_step_async
async for llm_response in self._call_llm_async(
File "D:\Anaconda\envs\playwright_env\Lib\site-packages\google\adk\flows\llm_flows\base_llm_flow.py", line 470, in _call_llm_async
async for llm_response in llm.generate_content_asyn

[0skat]

@Himanshu-Tyagi-Indium
@sonicxz
I was having the same issue and updated the google-adk package to the latest 1.6.1 and that allowed me to finally connect to an MCP. this had been an issue for a while. Hopefully this helps

[2020-abhilash]

I tried updating google-adk to the latest 1.6.1 and it still gives me the same error. It seems that the JSON that is passed in the request body to the LLM is not syntactically correct. The below portion (copied from the comment above) seems weird to me.

{'description': 'Width of the browser window', 'type': <Type.NUMBER: 'NUMBER'>}

Currently I'm completely blocked from integrating a very important MCP Server into my Agent! Is there a fix for this that is in progress already?

[abhayJava]

I am also blocked., Even with google-adk version 1.6.1 or latest it still fails

2025-08-03 18:25:53,399 - ERROR - agent.py:156 - Unexpected error during module level initialization: 2 validation errors for LlmAgent tools.0.callable Input should be callable [type=callable_type, input_value=<google.adk.tools.mcp_too...t object at 0x168c282f0>, input_type=MCPToolset] For further information visit https://errors.pydantic.dev/2.11/v/callable_type tools.0.is-instance[BaseTool] Input should be an instance of BaseTool [type=is_instance_of, input_value=<google.adk.tools.mcp_too...t object at 0x168c282f0>, input_type=MCPToolset] For further information visit https://errors.pydantic.dev/2.11/v/is_instance_of Traceback (most recent call last): File "/Users/a0k0eyw/Documents/genai-code/instavibe-bootstrap/agents/platform_mcp_client/agent.py", line 151, in <module> asyncio.run(initialize()) ~~~~~~~~~~~^^^^^^^^^^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages/nest_asyncio.py", line 30, in run return loop.run_until_complete(task) ~~~~~~~~~~~~~~~~~~~~~~~^^^^^^ File "/Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages/nest_asyncio.py", line 98, in run_until_complete return f.result() ~~~~~~~~^^ File "/Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/asyncio/futures.py", line 199, in result raise self._exception.with_traceback(self._exception_tb) File "/Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/asyncio/tasks.py", line 304, in __step_run_and_handle_result result = coro.send(None) File "/Users/a0k0eyw/Documents/genai-code/instavibe-bootstrap/agents/platform_mcp_client/agent.py", line 127, in initialize root_agent, exit_stack = await get_agent_async() ^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/a0k0eyw/Documents/genai-code/instavibe-bootstrap/agents/platform_mcp_client/agent.py", line 62, in get_agent_async root_agent = LlmAgent( model=llm_model, # Adjust model name if needed based on availability ...<50 lines>... tools=[tools], ) File "/Library/Frameworks/Python.framework/Versions/3.13/lib/python3.13/site-packages/pydantic/main.py", line 253, in __init__ validated_self = self.__pydantic_validator__.validate_python(data, self_instance=self) pydantic_core._pydantic_core.ValidationError: 2 validation errors for LlmAgent tools.0.callable Input should be callable [type=callable_type, input_value=<google.adk.tools.mcp_too...t object at 0x168c282f0>, input_type=MCPToolset] For further information visit https://errors.pydantic.dev/2.11/v/callable_type tools.0.is-instance[BaseTool] Input should be an instance of BaseTool [type=is_instance_of, input_value=<google.adk.tools.mcp_too...t object at 0x168c282f0>, input_type=MCPToolset]

[GWeale]

I tried to reproduce on a clean env with the latest line and couldn’t. Agent construction with MCPToolset works on my side.

Python 3.13.5 (venv)
google-adk 1.10.0 (pulls google-genai 1.29.0, mcp 1.12.4)

The Pydantic error (“tools.0.callable” / “is-instance[BaseTool]”) appears tied to older google-adk (e.g., 1.2.x). Current versions accept MCPToolset in tools.
The Gemini 400 INVALID_ARGUMENT about “additional_properties” is same as with older tool-schema translation; fixed in newer google-adk + google-genai.
“Function playwright_agent is not found in the tools_dict.” looks like it is trying to call an agent name as a tool. Tools are functions exposed by the MCP server (e.g., browser_navigate, browser_snapshot), not the agent’s name. Can you make sure prompts/tool calls reference the MCP functions, not playwright_agent.

Can you confirm if upgrading to:
google-adk >= 1.10.0
google-genai >= 1.27 (pulled automatically by adk 1.10.0)
mcp >= 1.8.0 resolves the issue on your side?

[refugedesigns]

Still facing this issue of invalid JSON Payload recieved using google-adk 1.12.0 latest version and fastmcp 2.11.3. Please has anyone solved this, I am using google adk agent and fast mcp and connecting with server sent events