Skip to main content

​
Overview

Enginy MCP lets you connect an AI assistant to your Enginy workspace so it can look things up, summarize what it finds, and help you prepare work inside Enginy. If you are in sales ops, rev ops, or another non-technical role, start with Claude or ChatGPT first — the AI assistant you already chat in day to day. No terminal or config file required. The hosted resource server is:
Behind the scenes, Enginy MCP uses a hosted remote MCP server and a browser sign-in flow. Its tools are generated from Enginy’s public API, which helps keep MCP aligned with the rest of the product.

MCP Overview

Learn how the hosted server, OAuth flow, OpenAPI-derived tools, and workspace policy model fit together.

Claude & Claude Code

Connect Claude (claude.ai) for most teams, or Claude Code if your team prefers the CLI.

Client support matrix

Compare supported interfaces, setup shapes, and caveats — each client links to its own dedicated setup page.

Custom & other MCP clients

Connect a bridge or a homegrown MCP client not covered by a dedicated page.

Supported tools

See what Enginy MCP can do today, how the tool surface is generated, and what is not guaranteed yet.

Example prompts

Use practical prompts for Claude, Codex, Cursor, Gemini CLI, Microsoft 365 Copilot, ChatGPT developer mode, and other MCP clients.

Scopes and policy

Review scope groups, policy ceilings, and how Enginy maps MCP permissions onto OpenAPI routes.

FAQ / known limitations

Get quick answers about current limitations and what assumptions are unsafe to make.

​
When to use MCP instead of direct HTTP

  • Use MCP when you want an AI assistant to work inside Enginy for you, without building a custom integration.
  • Use direct HTTP when an engineer is building a fixed product integration against specific Enginy API endpoints.

​
Fastest path for Claude

This is the recommended first setup for most teams — no terminal required.
  1. In Enginy, enable MCP for the workspace and allow https://claude.ai/api/mcp/auth_callback.
  2. In Claude, go to Customize → Connectors (Team/Enterprise: an Owner adds it via Organization Settings → Connectors), click +, choose Add custom connector, and paste:
  1. Authenticate in the browser and approve the requested scopes.
  2. Turn the connector on for your chat via the + button → Connectors.
  3. Run mcp_whoami to confirm the granted client ID, user, and scopes.
Prefer the terminal? See Claude Code for the CLI setup instead.
The full MCP documentation lives in the dedicated MCP tab, not only in this quick-start guide.