MewCPMewCP
  • AstheTech
  • Contact Us
  • Documentation
  • MewCP Auth API
Have a question?
  • ✉ Contact us - our dev team will reach out as soon as possible

© 2026 MewCP. All rights reserved.

githubx
Getting Started
Connect AI Apps
Frameworks & SDKs
    Vercel AI SDKGoogle ADKCrewAILangChain PythonLangChain TypeScriptLangGraphOpenAI Agents SDKClaude SDKPython MCP ClientTypeScript MCP Client
Authentication
Auth API Guides
powered by Zudoku
Frameworks & SDKs

Google ADK

Install

TerminalCode
pip install google-adk

Connect

Code
import asyncio from google.adk.tools.mcp_tool import MCPToolset from google.adk.tools.mcp_tool.mcp_session_manager import StreamableHTTPConnectionParams MEWCP_API_KEY = "API_KEY" async def main(): toolset = MCPToolset( connection_params=StreamableHTTPConnectionParams( url="https://gateway.mewcp.com/personal/mcp", headers={"Authorization": f"Bearer {MEWCP_API_KEY}"}, ) ) tools = await toolset.get_tools() print("Available tools:", [t.name for t in tools]) # -> ["search", "get_schema", "list_accounts", "call_tool"] await toolset.close() asyncio.run(main())

You get four tools rather than the tools of each app. Your agent uses them to reach every app you have connected. See How MewCP works.


Call a tool directly

Code
call_tool = next(t for t in tools if t.name == "call_tool") result = await call_tool.run_async( args={ "server_maskedId": "google-calendar", "tool_name": "list_events", "args": { "calendar_id": "primary", "time_min": "2026-01-15T00:00:00Z", "time_max": "2026-01-16T00:00:00Z", }, }, tool_context=None, ) print(result)

If you have connected more than one account for the same app, add "alias": "work" to select one.


Use with an LLM agent

Pass the toolset to an LlmAgent and ADK calls tools automatically based on the model's decisions:

Code
from google.adk.agents import LlmAgent from google.adk.tools.mcp_tool import MCPToolset from google.adk.tools.mcp_tool.mcp_session_manager import StreamableHTTPConnectionParams toolset = MCPToolset( connection_params=StreamableHTTPConnectionParams( url="https://gateway.mewcp.com/personal/mcp", headers={"Authorization": f"Bearer {MEWCP_API_KEY}"}, ) ) agent = LlmAgent( model="gemini-2.0-flash", name="assistant", instruction="You are a helpful assistant with access to the user's connected apps.", tools=[toolset], )

B2B: per-user credential routing

To route calls for different audience members, use a header_provider callable instead of static headers:

Code
MCPToolset( connection_params=StreamableHTTPConnectionParams( url="https://gateway.mewcp.com/personal/mcp", ), header_provider=lambda ctx: { "Authorization": f"Bearer {MEWCP_API_KEY}", "x-mewcp-enduser-id": ctx.session.state["user_id"], }, )

Where to find your values

ValueWhere to get it
API_KEYDashboard -> API Keys
Connected appsDashboard -> Servers
Last modified on October 15, 2026
Vercel AI SDKCrewAI
On this page
  • Install
  • Connect
  • Call a tool directly
  • Use with an LLM agent
  • B2B: per-user credential routing
  • Where to find your values