Crazy Egg MCP
Official hosted Crazy Egg MCP server, documented on the Crazy Egg support site. It lets AI assistants (Claude, ChatGPT, Cursor, VS Code, Windsurf, Gemini CLI, Perplexity, Microsoft Copilot Studio) start and drive conversations with the Crazy Egg "harness" and retrieve results. The connection acts as the logged-in Crazy Egg user, with that user's permissions; the provider recommends connecting a limited-permission (e.g. read-only) user.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Endpoint
Hosted endpoint · transport streamable-http
Connect
This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):
For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:
If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:
Tools
ce_chat_start— Starts a new Crazy Egg harness chat, creating a conversation. Returns a chatId that must be passed to all subsequent chat tools.ce_chat_message— Sends a user message to an existing chat.ce_chat_poll— Polls a chat for progress updates; returns new completed entries after the cursor plus active_step. Call repeatedly until processing_status is "idle".ce_chat_list— Lists Crazy Egg chats for a harness, to discover chatIds.ce_chat_retrieve— Retrieves the full history for an existing chat.ce_chat_list_steps— Lists all steps for an existing chat.ce_chat_get_latest_step— Gets only the latest step for an existing chat.ce_harness_request— Makes a raw HTTP request to the Crazy Egg harness API directly (e.g. /chats, /files/:id/download-url). Intended for advanced use cases.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.