CTP MCP Server
Enables AI-powered generation of production-ready CTP (ConveniencePro Tool Protocol) tools from natural language descriptions, including tool definitions, implementations, tests, and TypeScript validation.
README
CTP MCP Server
MCP server for AI-powered CTP tool generation - describe a tool, get production-ready code.
Overview
The CTP MCP Server is a Model Context Protocol server that helps developers create ConveniencePro Tool Protocol (CTP) tools quickly and easily. Simply describe what tool you want to build, and the MCP server generates complete, production-ready code including:
- Tool definitions following the CTP specification
- Implementation code (client-side or server-side)
- Complete test suites
- TypeScript types and validation
Features
- AI-Powered Generation: Describe your tool in natural language
- Complete Scaffolding: Get definition, implementation, and tests
- CTP Validation: Ensures generated tools follow the specification
- Duplicate Detection: Checks for similar existing tools
- Template-Based: Consistent, best-practice code generation
- Type-Safe: Full TypeScript support
Installation
npm install -g @conveniencepro/ctp-mcp-server
Or use directly with npx:
npx @conveniencepro/ctp-mcp-server
Usage with Claude Desktop
Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"ctp-tools": {
"command": "npx",
"args": ["-y", "@conveniencepro/ctp-mcp-server"]
}
}
}
Available Tools
ctp_create_tool
Generate a complete CTP tool from a natural language description.
Parameters:
description(required): Natural language description of what the tool should doname(optional): Tool name (auto-generated if not provided)category(optional): Tool categoryexecutionMode(optional): Where the tool runs (client,server, orboth)
Example:
Create a tool that converts YAML to JSON
ctp_validate_tool
Validate a tool definition against the CTP specification.
Parameters:
definition(required): The tool definition object to validate
ctp_generate_implementation
Generate implementation code from a tool definition.
Parameters:
definition(required): The tool definitionexecutionMode(optional): Execution mode (clientorserver)
ctp_generate_tests
Generate a test suite for a CTP tool.
Parameters:
definition(required): The tool definitionimplementation(optional): The tool implementation code
ctp_search_duplicates
Search for existing tools with similar functionality.
Parameters:
description(required): Description of the tool to search forcategory(optional): Category to narrow search
Example Workflow
-
Search for duplicates:
Use ctp_search_duplicates to check if a "markdown to HTML converter" already exists -
Generate the tool:
Use ctp_create_tool with description: "Convert Markdown text to HTML" -
Review generated files:
src/tools/markdown-to-html-definition.ts- Tool definitionsrc/tools/markdown-to-html.ts- Implementationsrc/tools/__tests__/markdown-to-html.test.ts- Tests
-
Implement the logic: Replace the placeholder implementation with actual logic
-
Test and deploy:
npm test npm run build
Generated Code Structure
// Tool Definition
export const markdownToHtmlDefinition: ToolDefinition = {
id: 'markdown-to-html',
name: 'Markdown to HTML',
description: 'Convert Markdown text to HTML',
category: 'converters',
// ... full specification
};
// Implementation
export const markdownToHtmlFn: ToolFunction<MarkdownToHtmlResult> = (params) => {
// Your implementation here
};
// Tests
describe('Markdown to HTML', () => {
it('should convert markdown to HTML', () => {
// Generated tests
});
});
Development
# Clone the repository
git clone https://github.com/titan-alpha/ctp-mcp-server.git
cd ctp-mcp-server
# Install dependencies
npm install
# Build
npm run build
# Run locally
npm start
Architecture
ctp-mcp-server/
├── src/
│ ├── index.ts # MCP server entry point
│ ├── tools/ # MCP tool implementations
│ │ ├── create-tool.ts # Tool scaffolding
│ │ ├── validate-tool.ts # Validation
│ │ ├── generate-*.ts # Code generators
│ │ └── search-*.ts # Duplicate detection
│ ├── templates/ # Handlebars templates
│ │ ├── tool-definition.hbs
│ │ ├── client-implementation.hbs
│ │ └── test-suite.hbs
│ └── utils/ # Utilities
│ ├── template-engine.ts
│ ├── string-utils.ts
│ └── ai-analyzer.ts
└── dist/ # Compiled output
Contributing
Contributions are welcome! Please see the CTP repository for contribution guidelines.
License
MIT
Links
Related Packages
- @conveniencepro/ctp-core - Core types and validation
- @conveniencepro/ctp-runtime - Execution runtime
- @conveniencepro/ctp-sdk - Embeddable SDK
- @conveniencepro/ctp-examples - Example tools
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.