Skip to main content
Glama
automatikstudio

ProofBase MCP Server

by automatikstudio
OverviewSchemaSourceRelated ServersScoreDiscussionsAdmin
JavaScript
Remote

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

npm install proofbase-mcp

Or install from source:

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

Configuration

Set your Anthropic API key:

export ANTHROPIC_API_KEY=your-key-here

Usage with Claude Desktop

Add to your Claude Desktop configuration (claude_desktop_config.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:

{
  "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

# Install dependencies
npm install

# Run in development mode
npm run dev

# Build for production
npm run build

# Run tests
npm test

Testing

# Run unit tests
npm test

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

License

MIT

Available Tools

1 tool
generate_testimonialA

Generate a realistic customer testimonial for a product. Creates a fictional but believable testimonial with customer details, suitable for social proof.

ParametersJSON Schema
NameRequiredDescriptionDefault
product_nameYesName of the product the testimonial is for
customer_typeYesType of customer (e.g., 'SaaS founder', 'Marketing manager', 'Freelance designer')
outcomeYesThe key benefit or outcome to highlight (e.g., 'increased conversions', 'saved time', 'better customer engagement')
toneNoTone of the testimonial (default: professional)
include_metricsNoWhether to include specific metrics/numbers (default: true)

TDQS

A4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses key behavioral traits: the testimonial is 'fictional but believable' and includes 'customer details', which clarifies it's not real data. However, it doesn't mention potential limitations like length, format, or whether it might generate repetitive content, leaving some gaps in transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the core purpose and followed by additional context. Every sentence earns its place: the first defines the action and output, the second clarifies realism and use case. There's no redundancy or unnecessary information, making it highly efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (5 parameters, no output schema, no annotations), the description is fairly complete. It covers the purpose, output nature, and use case. However, it lacks details on the return format (e.g., text structure) and doesn't fully compensate for the absence of annotations, such as disclosing if there are rate limits or quality constraints.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, so the baseline is 3. The description adds value by contextualizing the parameters: it implies that 'customer details' are generated based on inputs like 'customer_type', and 'outcome' relates to 'key benefit or outcome'. This enhances understanding beyond the schema, though it doesn't detail exact mappings or examples.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with specific verbs ('generate', 'creates') and resources ('realistic customer testimonial', 'fictional but believable testimonial with customer details'). It distinguishes the output as 'suitable for social proof', which adds context about its intended use case. Since there are no sibling tools, full differentiation isn't needed.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context by mentioning 'suitable for social proof', suggesting it's for marketing or presentation purposes. However, it doesn't provide explicit guidance on when to use this tool versus alternatives (e.g., real testimonials, other content generation tools) or any prerequisites. With no sibling tools, this is adequate but not comprehensive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev1.0.0
    • First observedgenerate_testimonial
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

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.

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors