# Elfsight AI Chatbot MCP server

> Read conversations, leads, knowledge base and analytics of your Elfsight AI Chatbot widgets, and answer knowledge gaps.

- Listing: https://mcp.tc/i/elfsight-ai-chatbot
- Connect: use the server's own URL `https://widget-data.service.elfsight.com/mcp/ai_chat` (OAuth sign-in at the server); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: OAuth sign-in
- Category: [CRM, Sales & Support](https://mcp.tc/c/crm-sales)
- Vendor: Elfsight
- Homepage: <https://elfchatbot.com/>
- Repository: <https://github.com/elfsight/ai-chatbot-mcp>

## About

Connects to your Elfsight AI Chatbot widgets so an assistant can list widgets, read analytics, search conversations, review leads, search the knowledge base and find questions the chatbot could not answer. One tool writes: it adds an answer to the knowledge base and closes a gap.

The server is hosted by Elfsight at a Streamable HTTP endpoint. Users sign in to Elfsight through OAuth in the browser and approve access; no key is needed. Access covers the AI Chatbot widgets on that account only. Lead contact fields are masked unless full contacts are requested.

## What it can do

- List the AI Chatbot widgets on your account
- Get analytics over 7, 30 or 90 day windows
- Search conversations and read a full conversation
- List leads, with contact fields masked by default
- Search the knowledge base
- List knowledge gaps visitors asked about
- Add an answer to the knowledge base to close a gap

## Example prompts

- "Which AI Chatbot widgets do I have?"
- "How did my AI Chatbot perform over the last 30 days?"
- "List the new leads from this week that I haven't reviewed yet."
- "What do visitors ask that my assistant can't answer?"

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport http elfsight-ai-chatbot https://widget-data.service.elfsight.com/mcp/ai_chat
```

2. Start Claude Code, type `/mcp`, pick **elfsight-ai-chatbot** and choose **Authenticate**. A browser window opens for the Elfsight sign-in.

Add `--scope user` to make it available in every project, not just this one.

### Claude Desktop

1. Open **Customize → Connectors**, click **+ Add**, then **Add custom connector**.

2. Name it **Elfsight AI Chatbot** and paste this URL:

```url
https://widget-data.service.elfsight.com/mcp/ai_chat
```

3. Click **Add**, then **Connect**, and sign in when Elfsight asks.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

### claude.ai

1. Open the connector form on claude.ai. This button fills in the name and URL for you:

[Add to claude.ai](<https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=Elfsight%20AI%20Chatbot&connectorUrl=https%3A%2F%2Fwidget-data.service.elfsight.com%2Fmcp%2Fai_chat>) (opens connector settings)

2. Check that the URL reads `https://widget-data.service.elfsight.com/mcp/ai_chat` and click **Add**.

3. Click **Connect** and sign in when Elfsight asks.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.

### ChatGPT

1. On chatgpt.com, go to **Plugins**, select **+**, then **Add custom MCP server**.

2. Enter a name for the server.

3. Under **Connection**, paste `https://widget-data.service.elfsight.com/mcp/ai_chat` as the server URL, then for authentication choose **OAuth**. ChatGPT sends you to Elfsight to sign in.

4. Check **I understand and want to continue**, then select **Create as a plugin**.

Whether you can add a custom MCP server depends on your ChatGPT plan and your workspace permissions (in Business workspaces, admins and owners can).

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=elfsight-ai-chatbot&config=eyJ1cmwiOiJodHRwczovL3dpZGdldC1kYXRhLnNlcnZpY2UuZWxmc2lnaHQuY29tL21jcC9haV9jaGF0In0%3D>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

```json
{
  "mcpServers": {
    "elfsight-ai-chatbot": {
      "url": "https://widget-data.service.elfsight.com/mcp/ai_chat"
    }
  }
}
```

Cursor shows **Needs authentication** next to the server. Click the button beside it to sign in.

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=elfsight-ai-chatbot&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fwidget-data.service.elfsight.com%2Fmcp%2Fai_chat%22%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"elfsight-ai-chatbot","type":"http","url":"https://widget-data.service.elfsight.com/mcp/ai_chat"}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

```json
{
  "servers": {
    "elfsight-ai-chatbot": {
      "type": "http",
      "url": "https://widget-data.service.elfsight.com/mcp/ai_chat"
    }
  }
}
```

VS Code asks you to sign in the first time the server starts.

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

```json
{
  "mcpServers": {
    "elfsight-ai-chatbot": {
      "serverUrl": "https://widget-data.service.elfsight.com/mcp/ai_chat"
    }
  }
}
```

2. Refresh the MCP server list in Cascade and sign in when asked.

Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.

### Codex

```bash
codex mcp add elfsight-ai-chatbot --url https://widget-data.service.elfsight.com/mcp/ai_chat
codex mcp login elfsight-ai-chatbot
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

```toml
[mcp_servers.elfsight-ai-chatbot]
url = "https://widget-data.service.elfsight.com/mcp/ai_chat"
```

### Gemini CLI

```bash
gemini mcp add --transport http elfsight-ai-chatbot https://widget-data.service.elfsight.com/mcp/ai_chat
```

Then, inside Gemini CLI, run `/mcp auth elfsight-ai-chatbot` to sign in.

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.

```json
{
  "mcpServers": {
    "elfsight-ai-chatbot": {
      "type": "http",
      "url": "https://widget-data.service.elfsight.com/mcp/ai_chat"
    }
  }
}
```

Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.

Client only starts local servers? Bridge it with `npx -y mcp-remote https://widget-data.service.elfsight.com/mcp/ai_chat`.

## Details

- Server version: 1.0.0
- Last checked: 2026-11-18 (reachable, asks for credentials)
- Listed: 2026-10-13
- Updated: 2026-10-13

---
Source: https://mcp.tc/i/elfsight-ai-chatbot (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report
