# ClerkChat

Controls ClerkChat customer support agents, documents, messaging channels, and analytics from your coding assistant.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: clerkchatco-public
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/clerkchatco-public/clerkchat-mcp
- Updated: 2026-10-18
- HTML: https://affpapa.org/en/nevibecode/mcp/clerkchat

## What it does

ClerkChat operates as a hosted remote service with no local binaries to run. The assistant connects via Streamable HTTP to `https://mcp.clerkchat.co/mcp` using OAuth 2.1 with PKCE. During authorization, you select which workspaces the client can access.

Tools allow sending knowledge files like PDF, Markdown, CSV, and XLSX up to 8 MiB directly through the protocol. You can link communication channels such as WhatsApp, Telegram, or Slack, inspect message history, take over customer threads, and track automation leads.

Write tools accept idempotency keys to stop duplicate execution during network retries. External API credentials and bot tokens remain write-only, so the server never prints them back into tool outputs.

## Requirements
- Remote server: `https://mcp.clerkchat.co/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http clerkchat https://mcp.clerkchat.co/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add clerkchat --url https://mcp.clerkchat.co/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "clerkchat": {
            "url": "https://mcp.clerkchat.co/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "clerkchat": {
            "type": "http",
            "url": "https://mcp.clerkchat.co/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http clerkchat https://mcp.clerkchat.co/mcp
```

## When to use it
- train a support agent on PDF and spreadsheet documents
- connect messaging channels like WhatsApp and Telegram
- take over live customer conversations and send replies
- export leads collected by workflow automations

## Example prompts
- List all customer support agents in my ClerkChat workspace
- Train the Store support agent on `pricing.pdf` and check source status
- Find unread WhatsApp conversations from today and draft replies

## 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