
Cosmic MCP Server
A production-ready Model Context Protocol server for interacting with Cosmic headless CMS, providing comprehensive tools for managing objects, types, and media in your Cosmic bucket.
README
Cosmic MCP Server
A robust, production-ready Model Context Protocol (MCP) server for interacting with the Cosmic headless CMS. This server provides a comprehensive set of tools for creating, reading, updating, and deleting objects, types, and media in your Cosmic bucket.
✨ Features
- Comprehensive Toolset: Full CRUD operations for Cosmic objects, object types, and media.
- Robust Architecture: Built with a clean, three-layer architecture (Server, Services, Repositories).
- Strongly Typed: Written in TypeScript with strict validation using Zod for all inputs.
- Production-Ready: Includes centralized logging, rate-limiting, and graceful error handling.
- Easy to Configure: Simple setup using a
.env
file for your Cosmic credentials. - Extensible: Designed to be easily extended with new tools and services.
🚀 Getting Started
Prerequisites
1. Installation
Clone the repository and install the dependencies:
git clone https://github.com/patgpt/cosmic-mcp.git
cd cosmic-mcp
bun install
2. Configuration
Copy the example environment file and fill in your Cosmic bucket credentials. You can find these in your Cosmic dashboard under Bucket > Settings > API Keys.
cp .env.example .env
Your .env
file should look like this:
# .env
COSMIC_BUCKET_SLUG="your-bucket-slug"
COSMIC_READ_KEY="your-read-key"
COSMIC_WRITE_KEY="your-write-key"
DEBUG="false" # Set to "true" for verbose logging
3. Running the Server
Start the MCP server using the following command:
bun start
The server will connect and be ready to receive requests from any MCP-compatible client.
4. Using with MCP Clients
For VS Code (using Claude Dev extension)
Add this configuration to your VS Code settings or Claude Dev configuration:
{
"mcp": {
"servers": {
"Cosmic": {
"type": "stdio",
"command": "npx",
"args": ["-y", "cosmic-mcp"],
"env": {
"COSMIC_BUCKET_SLUG": "your-bucket-slug",
"COSMIC_READ_KEY": "your-read-key",
"COSMIC_WRITE_KEY": "your-write-key",
"DEBUG": "false"
}
}
}
}
}
For Cursor
Add this configuration to your .cursor/mcp.json
file:
{
"mcpServers": {
"Cosmic": {
"command": "npx",
"args": ["-y", "cosmic-mcp"],
"env": {
"COSMIC_BUCKET_SLUG": "your-bucket-slug",
"COSMIC_READ_KEY": "your-read-key",
"COSMIC_WRITE_KEY": "your-write-key",
"DEBUG": "false"
}
}
}
}
Alternative: Local Development
If you're developing locally or prefer to use the local version:
For VS Code:
{
"mcp": {
"servers": {
"Cosmic": {
"type": "stdio",
"command": "node",
"args": ["path/to/cosmic-mcp/dist/server.js"],
"env": {
"COSMIC_BUCKET_SLUG": "your-bucket-slug",
"COSMIC_READ_KEY": "your-read-key",
"COSMIC_WRITE_KEY": "your-write-key",
"DEBUG": "true"
}
}
}
}
}
For Cursor:
{
"mcpServers": {
"Cosmic": {
"command": "node",
"args": ["path/to/cosmic-mcp/dist/server.js"],
"env": {
"COSMIC_BUCKET_SLUG": "your-bucket-slug",
"COSMIC_READ_KEY": "your-read-key",
"COSMIC_WRITE_KEY": "your-write-key",
"DEBUG": "true"
}
}
}
}
Note: Replace
your-bucket-slug
,your-read-key
, andyour-write-key
with your actual Cosmic bucket credentials. You can find these in your Cosmic dashboard under Bucket > Settings > API Keys.
🛠️ Available Tools
This MCP server exposes the following tools. All tools are designed to be called by an AI agent or other MCP client.
Tool Name | Description |
---|---|
list_objects |
List objects, with optional filtering by type, status, and pagination. |
get_object |
Get a specific object by its ID or by its slug and type. |
create_object |
Create a new object. |
update_object |
Update an existing object. |
delete_object |
Delete an object. |
list_object_types |
List all available object types in the bucket. |
search_objects |
Perform a text-based search across objects. |
upload_media |
Upload a media file. |
list_media |
List all media files, with pagination. |
delete_media |
Delete a media file by its ID. |
For detailed input schemas for each tool, please refer to the 📚 Documentation or the src/manifest.ts
file.
📚 Documentation
Comprehensive documentation is available at https://patgpt.github.io/cosmic-mcp/
The documentation includes:
- Getting Started Guide - Complete setup and installation instructions
- Configuration Reference - All configuration options and environment variables
- Tools API Documentation - Detailed reference for all available tools
- AI Assistant Prompts - Example prompts for effective AI interaction
- MCP Client Setup - Configuration for VS Code, Cursor, and other MCP clients
Local Documentation
You can also run the documentation locally:
# Install dependencies
npm install
# Start the documentation server
npm run docs:dev
# Build the documentation
npm run docs:build
🧪 Running Tests
This project is set up with tests to ensure reliability.
# Run all tests
bun test
🤝 Contributing
Contributions are welcome! If you have a suggestion or find a bug, please open an issue to discuss it.
Please see our CONTRIBUTING.md for detailed guidelines on how to contribute to this project, including:
- Development setup and workflow
- Code style and standards
- Testing requirements
- Pull request process
- Release process
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
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.
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.
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.

E2B
Using MCP to run code via e2b.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.