For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Login
HomeDocsAPI ReferenceMCP ServerChat SDKsRelease Notes
HomeDocsAPI ReferenceMCP ServerChat SDKsRelease Notes
  • Introduction
    • Overview
    • Getting started
      • Claude Desktop
      • ChatGPT
      • Gemini CLI
      • Google ADK
      • Other MCP clients
      • Connecting multiple Agents
    • Authentication
    • Data privacy
    • Built-in prompts
    • FAQ
    • Troubleshooting
  • Tools
    • Overview
    • get_ada_configuration
    • get_ada_metric
    • get_available_filters
    • get_conversations
    • get_conversation
    • search_knowledge
    • search_coaching
    • get_improvement_guide
    • list_entities
    • propose_change
    • get_test_cases
    • get_test_runs
    • get_test_run_quota
    • send_feedback
  • Prompt library
    • Overview
    • Improvement recommendations
    • Quick health checks
    • Create visualizations
    • Diagnose performance issues
    • Identify optimization opportunities
    • Review configuration
    • Search knowledge and coaching
    • Test agent responses
    • Deep-dive analysis
Login
LogoLogo
On this page
  • Requirements
  • Configuration
  • Endpoint
  • Common issues
IntroductionGetting started

Google ADK

Was this page helpful?
Previous

Other MCP clients

Next
Built with
The Google Agent Development Kit (ADK) is intended for programmatic agent development and backend integrations. For interactive use, see Gemini CLI.

The Google Agent Development Kit (ADK) can connect to Ada’s MCP server using the MCPToolset class. This enables programmatic access to Ada’s MCP tools within ADK-based agents.

Ada’s MCP server currently supports JSON-RPC 2.0 over HTTP at the /api/mcp endpoint. Server-Sent Events (SSE) streaming is not available.

Requirements

  • Python 3.10 or later.

  • Google ADK installed:

    $pip install google-adk
  • An API key generated from Config > PLATFORM > API keys in your Ada dashboard.

Configuration

  1. Generate an API key from Config > PLATFORM > API keys in your Ada dashboard.

  2. Set your Ada API key as an environment variable:

    $export ADA_API_KEY=your_api_key_here
  3. Connect to Ada’s MCP server:

    1import asyncio
    2import os
    3from google.adk.toolsets import MCPToolset
    4
    5async def main():
    6 ada_toolset = await MCPToolset.from_server(
    7 connection_params={
    8 "url": "https://acme-corp.ada.support/api/mcp",
    9 "headers": {
    10 "Authorization": f"Bearer {os.environ['ADA_API_KEY']}"
    11 }
    12 }
    13 )
    14
    15 tools = ada_toolset.get_tools()
    16 print(f"Loaded {len(tools)} Ada MCP tools")
    17
    18asyncio.run(main())
  4. Replace acme-corp.ada.support with your Ada instance domain (see Authentication).

  5. Ensure ADA_API_KEY is set in your environment before running the script.

Endpoint

Ada’s MCP server is exposed at the /api/mcp endpoint and routed by subdomain.

  • Production: https://<your-subdomain>.<your-ada-domain>/api/mcp
  • Local development: http://<subdomain>.localhost:8000/api/mcp

Common issues

401 Unauthorized

  • Ensure your API key is valid.
  • Verify the Authorization header is formatted as Bearer <key>.

405 Method Not Allowed

  • Ensure you are sending POST requests to /api/mcp.
  • SSE (GET streaming) is not supported.