OSP Marketing Tools for Node.js

A suite of tools for technical marketing content creation, optimization, and product positioning based on Open Strategy Partners' methodologies.

A comprehensive suite of tools for technical marketing content creation, optimization, and product positioning based onOpen Strategy Partners' proven methodologies. This is a TypeScript implementation of the MCP server for OSP Marketing Tools.

Generate structuredOSP product value mapsthat effectively communicate your product's worth and positioning. This tool provides:

ApplyOSP's semantic editing codesfor comprehensive content review. This system provides:

{ "mcpServers": { "ai_think_gate": { "command": "npx", "args": [ "-y", "@trishchuk/osp-marketing-tools-mcp" ] } } }

# Clone the repository git clone https://github.com/x51xxx/osp-marketing-tools-mcp.git cd osp-marketing-tools-mcp # Install dependencies npm install # Build the project npm run build

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

{ "mcpServers": { "osp_marketing_tools": { "command": "node", "args": [ "path/to/osp-marketing-tools-mcp/dist/index.js" ] } } }

Note for Windows users: Make sure to replacepath/to/osp-marketing-tools-mcpwith the actual path to theosp-marketing-tools-mcpdirectory on your computer. For example, if you cloned the repository toC:\Users\YourName\Documents\osp-marketing-tools-mcp, theargsline should look like this:

"args": ["C:\\Users\\YourName\\Documents\\osp-marketing-tools-mcp\\dist\\index.js"]

Also, remember to use double backslashes\\instead of single backslashes\in the path.

Running the server in stdio mode (for Claude Desktop, Cursor, etc.)

This will start a web server on port 3000 (configurable via PORT environment variable) that exposes the MCP API via Server-Sent Events (SSE).

Once the server is running in HTTP/SSE mode, you can access the web interface athttp://localhost:3000/which provides an interactive demo of the available tools.

- health_check- Server health status and resource availability check
- get_editing_codes- OSP Editing Codes documentation and usage protocol for semantic content review
- get_writing_guide- OSP Writing Guide with principles for creating high-quality technical content
- get_meta_guide- OSP Meta Information Generator for web content metadata optimization
- get_value_map_positioning_guide- OSP Product Value Map Generator for effective product positioning
- get_on_page_seo_guide- OSP On-Page SEO Guide for comprehensive content optimization

- edit-content- Review content using OSP editing codes for improved quality and clarity
- generate-meta- Generate optimized metadata for web content with proper keyword placement
- generate-value-map- Create a structured OSP value map for product positioning
- apply-writing-guide- Apply OSP writing principles to create technical content
- optimize-seo- Apply on-page SEO strategies to optimize content for search

To use the OSP editing codes to review content, simply send this prompt to Claude (after configuring the MCP server):

Review this technical content using OSP editing codes: Kubernetes is a container orchestration platform. It handles deploying applications and scaling them as needed. There's lots of things it can do. It's really good. You should use it for your applications to make them more resilient.

Generate an OSP value map for [Product Name] focusing on [target audience] with the following key features: [list features] Example: Generate an OSP value map for CloudDeploy focusing on DevOps engineers with these key features: - Automated deployment pipeline - Infrastructure as code support - Real-time monitoring - Multi-cloud compatibility

The server provides a JavaScript client example that demonstrates how to connect to the MCP server using Server-Sent Events (SSE). When you run the server in HTTP/SSE mode, you can access the demo athttp://localhost:3000/.

Here's a simple example of how to connect to the SSE endpoint programmatically:

// Connect to SSE endpoint const source = new EventSource('http://localhost:3000/sse'); let sessionId; // Listen for session ID source.addEventListener('sessionId', (event) => { sessionId = JSON.parse(event.data).sessionId; console.log(Connected with session ID: ${sessionId}); }); // Listen for tool responses source.addEventListener('toolResponse', (event) => { const response = JSON.parse(event.data); console.log('Tool response:', response); }); // Call a tool async function callTool(name, args = {}) { const response = await fetch(http://localhost:3000/messages?sessionId=${sessionId}, { method: 'POST', headers: { 'Content-Type': 'application/json', }, body: JSON.stringify({ jsonrpc: '2.0', id: Date.now().toString(), method: 'tools/call', params: { name: name, arguments: args } }) }); return response.json(); }

# Run in development mode (stdio) npm run dev # Run in development mode (HTTP/SSE) npm run dev:sse

osp-marketing-tools-mcp/ ├── prompts/ # Markdown resources from OSP tools ├── public/ # Static web files for HTTP server │ └── index.html # SSE client demo interface ├── src/ │ ├── utils/ # Utility functions │ │ └── contentReader.ts │ ├── tools/ # MCP tool implementations │ │ └── index.ts │ ├── prompts/ # MCP prompt templates │ │ └── index.ts │ ├── resources/ # MCP resource implementations │ │ └── index.ts │ ├── index.ts # Main entry point (stdio) │ └── http.ts # HTTP/SSE server ├── dist/ # Compiled JavaScript (generated) ├── package.json └── tsconfig.json

This software is based on the content creation and optimization methodologies developed byOpen Strategy Partners. It implements their LLM-enabled marketing tools and professional content creation frameworks.

For more information and original resources, visit:
- The OSP Writing and Editing Guide
- Editing Codes Quickstart Guide
- OSP Free Resources

Connect AI tools like Claude, Cursor, and Codex directly to your CitedSpy workspace with the Model Context Protocol (MCP). Once connected, your AI assistant can read your brands, prompts, runs, citations, and analytics - and create prompts or trigger runs - without you copying data back and forth. You can ask for your AI visibility dashboard in plain language, find your weakest prompts and engines, create and edit tracking prompts from chat, trigger fresh runs across engines, pull citations, mentions, and reports into your AI workflow