mcpField
Z
Zealoop

Zealoop

Remote
zealoop.comBusiness & Marketing0Updated 1w ago
RepositoryVisit website

About Zealoop

Zealoop is a remote MCP server for configuring and testing the AI support agent on a website. It helps teams manage support knowledge, behavior, chat widget setup, and deployment from an AI coding agent.

Key features

  1. 01Manage knowledge sources, tables, and rows
  2. 02Write procedures, actions, and segments
  3. 03Configure and verify the chat widget
  4. 04Simulate and batch-test the agent
  5. 05Publish, restore, and review analytics

Use cases

  1. 01Add website content to support knowledge
  2. 02Install and check a site's chat widget
  3. 03Test support behavior before launch

MCP support

The remote MCP server lets AI coding agents manage a Zealoop support agent. It exposes tools for workspace status, knowledge, guidance, widget setup, testing, publishing, analytics, and conversation search.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://api.zealoop.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

Zealoop MCP server

Connect your AI coding agent to Zealoop, the AI support agent for your website. Your agent can set up and tune your support agent for you: add knowledge, write procedures and actions, add the chat widget to your site, and test it before customers see it.

This is a remote MCP server. There is nothing to install or run.

https://api.zealoop.com/mcp

Transport: Streamable HTTP. Auth: OAuth 2.1 (your client opens a browser and you sign in to Zealoop).

Connect

Claude Code

claude mcp add zealoop --transport http https://api.zealoop.com/mcp

Cursor, Windsurf, VS Code, and other MCP clients: add a server with the URL above. Clients that support OAuth sign you in automatically.

What your agent can do

  • Check workspace status and get install instructions for your site's framework
  • Change the chat widget's look, and verify the widget is live on your site after your agent adds it to your code
  • Add and resync knowledge sources, tables and rows
  • Write procedures, actions and segments, and update the agent's guidance
  • Run simulations and batch tests before anything goes live
  • Publish, unpublish and restore agent configs (publishing needs your confirmation)
  • Read analytics and search past conversations

Links

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.