# Elfsight AI Chatbot

Give an AI agent access to Elfsight AI Chatbot conversations, leads, analytics and knowledge content. It can also add answers to the knowledge base.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 2
- Author: elfsight
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/elfsight/ai-chatbot-mcp
- Updated: 2026-10-23
- HTML: https://affpapa.org/en/nevibecode/mcp/elfsight-ai-chatbot

## What it does

Use the server to search chat history, inspect leads and review widget analytics. The agent can look up existing knowledge and find questions that the chatbot could not answer; it can then add an answer to the knowledge base. Ask it to investigate a conversation or check what visitors ask about a topic.

Elfsight hosts the remote server, so there is no local build or service to run. Connection uses OAuth: sign in to Elfsight and approve the access request. The agent can reach AI Chatbot widgets across the account, not other Elfsight products. Lead contact fields are masked, but messages retain what visitors typed, so they may still contain personal details.

Searches for conversations and leads return up to 100 items per request, while a conversation lookup can include up to 500 recent messages. `answer_knowledge_gap` writes to the knowledge base; the other listed tools read data. In Claude Code, add the connection with `claude mcp add --transport http elfsight-ai-chatbot https://mcp.elfchatbot.com/mcp`, then authenticate from `/mcp`.

## Requirements
- Remote server: `https://mcp.elfchatbot.com/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http ai-chatbot https://mcp.elfchatbot.com/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add elfsight-ai-chatbot --url https://mcp.elfchatbot.com/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "elfsight-ai-chatbot": {
            "url": "https://mcp.elfchatbot.com/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "elfsight-ai-chatbot": {
            "type": "http",
            "url": "https://mcp.elfchatbot.com/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http elfsight-ai-chatbot https://mcp.elfchatbot.com/mcp
```

## When to use it
- search chat history for a topic
- review widget analytics
- find leads that need follow-up
- spot questions missing from the knowledge base
- add an answer to close a knowledge gap

## Example prompts
- Find conversations about shipping from last week.
- Show this week's new leads that I haven't reviewed.
- Add an answer for this question to the knowledge base and close the gap.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 392262
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33989
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81163
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119231
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47577
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43902

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md