# ToughTongue AI

This MCP server lets a coding agent create voice-agent scenarios, inspect session analytics, place SIP calls, and schedule meeting bots.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 6
- Author: tough-tongue
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/tough-tongue/toughtongue-skills
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/mcp/toughtongue-ai

## What it does

Tough Tongue AI gives a coding agent access to a hosted MCP endpoint at `https://api.toughtongueai.com/api/public/mcp`. Through it, the agent can create and revise Scenarios, work with voice agents and meeting bots, retrieve session data, and turn scores or transcripts into coaching reports. It can also build browser demo flows and Agent Desktop apps.

The package contains Markdown skills, reference material, MCP configuration, and an icon. There are no hooks, scripts, or executable files. Authentication uses OAuth in a browser rather than an API key. Browser OAuth is therefore required before the server can carry out actions.

## Requirements
- Remote server: `https://api.toughtongueai.com/api/public/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http mcp https://api.toughtongueai.com/api/public/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add toughtongue-ai --url https://api.toughtongueai.com/api/public/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "toughtongue-ai": {
            "url": "https://api.toughtongueai.com/api/public/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "toughtongue-ai": {
            "type": "http",
            "url": "https://api.toughtongueai.com/api/public/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http toughtongue-ai https://api.toughtongueai.com/api/public/mcp
```

## When to use it
- draft a practice scenario for a negotiation
- retrieve scores and transcripts from sessions
- turn team findings into a coaching report
- refine a voice agent after reviewing calls
- prepare a meeting bot

## Example prompts
- Create a practice scenario for an enterprise pricing negotiation.
- Review the latest Enterprise Discovery Call sessions and report the main improvement areas.
- Find why the onboarding voice agent ends calls early and revise its scenario.

## Similar
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16730
- [labelhead-artist-momentum](https://affpapa.org/en/nevibecode/mcp/labelhead-artist-momentum.md) — MCP server · ★ 107701
- [Agent Skills Search Server](https://affpapa.org/en/nevibecode/mcp/agent-skills-search-server.md) — MCP server · ★ 26673
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23283
- [Nhost](https://affpapa.org/en/nevibecode/mcp/nhost.md) — MCP server · ★ 9369
- [PraisonAI](https://affpapa.org/en/nevibecode/mcp/praisonai.md) — MCP server · ★ 9298

---
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