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
  • Connection endpoints
  • Clients known to work
  • Transport
IntroductionGetting started

Other MCP clients

Was this page helpful?
Previous

Connecting multiple Agents

Next
Built with

Ada’s MCP server is compatible with any AI assistant or tool that supports the Model Context Protocol. The Claude Desktop, ChatGPT, Gemini CLI, and Google ADK walk-throughs cover the most common clients, but the same connection URLs work with other MCP-compatible tools.

Connection endpoints

MethodURL
OAuthhttps://<your-ada-instance-domain>/api/mcp/oauth
API keyhttps://<your-ada-instance-domain>/api/mcp

See Authentication for details.

Clients known to work

  • Cursor — configure through Cursor’s MCP settings. Both OAuth and API key work.
  • VS Code — configure through MCP extensions that support remote MCP servers.
  • Custom integrations — any MCP client implementation can point at the connection URLs above.

Transport

Ada’s MCP server uses JSON-RPC 2.0 over HTTP at the /api/mcp endpoint. Server-Sent Events (SSE) streaming is not currently supported. Clients that require local-process MCP can use the mcp-remote bridge via npx, as shown in the Claude Desktop and Gemini CLI walk-throughs.