Skip to main content
Glama
README.md
# ProofBase MCP Server

An MCP (Model Context Protocol) server for generating realistic customer testimonials using AI. Part of the ProofBase testimonial management ecosystem.

## Features

- **AI-Powered Generation**: Uses Claude to create authentic-sounding testimonials
- **Customizable Tone**: Choose between professional, casual, or enthusiastic styles
- **Flexible Output**: Includes customer name, role, company, avatar, and rating
- **Metric Support**: Optionally include specific metrics for credibility

## Installation

```bash
npm install proofbase-mcp
```

Or install from source:

```bash
git clone <repo>
cd mcp-servers/proofbase-mcp
npm install
npm run build
```

## Configuration

Set your Anthropic API key:

```bash
export ANTHROPIC_API_KEY=your-key-here
```

## Usage with Claude Desktop

Add to your Claude Desktop configuration (`claude_desktop_config.json`):

```json
{
  "mcpServers": {
    "proofbase": {
      "command": "node",
      "args": ["/path/to/proofbase-mcp/dist/index.js"],
      "env": {
        "ANTHROPIC_API_KEY": "your-key-here"
      }
    }
  }
}
```

## Available Tools

### generate_testimonial

Generate a realistic customer testimonial.

**Inputs:**

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `product_name` | string | ✅ | Name of the product |
| `customer_type` | string | ✅ | Type of customer (e.g., "SaaS founder", "Marketing manager") |
| `outcome` | string | ✅ | Key benefit to highlight (e.g., "increased conversions") |
| `tone` | string | ❌ | One of: "professional", "casual", "enthusiastic" (default: professional) |
| `include_metrics` | boolean | ❌ | Whether to include specific numbers (default: true) |

**Example Output:**

```json
{
  "name": "Sarah Chen",
  "role": "Head of Marketing",
  "company": "Flowstate",
  "avatar": "SC",
  "text": "ProofBase completely transformed how we showcase customer love. Our conversion rate jumped 34% after adding the wall of love to our landing page.",
  "rating": 5
}
```

## Example Usage

```
User: Generate a testimonial for ProofBase from a startup founder who saw increased conversions

Tool Call: generate_testimonial
{
  "product_name": "ProofBase",
  "customer_type": "startup founder",
  "outcome": "increased conversions",
  "tone": "enthusiastic"
}

Result:
{
  "name": "Marcus Johnson",
  "role": "Founder & CEO",
  "company": "Launchpad.io",
  "avatar": "MJ",
  "text": "Game-changer! We added ProofBase testimonials to our landing page and saw a 47% lift in signups within the first week. The setup was ridiculously easy.",
  "rating": 5
}
```

## Development

```bash
# Install dependencies
npm install

# Run in development mode
npm run dev

# Build for production
npm run build

# Run tests
npm test
```

## Testing

```bash
# Run unit tests
npm test

# Test the server manually
echo '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' | node dist/index.js
```

## License

MIT

TDQS

A3.9/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of confusion or overlap between tools. The tool's purpose is clearly defined and distinct by default.

Naming Consistency5/5

A single tool inherently has consistent naming, as there are no other tools to compare against. The name 'generate_testimonial' follows a clear verb_noun pattern.

Tool Count2/5

One tool is too few for a server named 'ProofBase MCP Server', which suggests a broader scope related to social proof or testimonials. A single tool feels thin and limited for this apparent domain.

Completeness2/5

The server's name implies a domain of social proof or testimonials, but with only a generation tool, there are significant gaps. Missing operations like retrieving, updating, deleting, or managing testimonials make the surface severely incomplete for the inferred purpose.