DevHub
chính thứcManage and utilize website content within the DevHub CMS platform
DevHub CMS MCP
A Model Context Protocol (MCP) integration for managing content in the DevHub CMS system.
Installation
You will need the uv package manager installed on your local system.
Manual configuration of Claude Desktop
To use this server with the Claude Desktop app, add the following configuration to the "mcpServers" section of your claude_desktop_config.json:
{
"mcpServers": {
"devhub_cms_mcp": {
"command": "uvx",
"args": [
"devhub-cms-mcp"
],
"env": {
"DEVHUB_API_KEY": "YOUR_KEY_HERE",
"DEVHUB_API_SECRET": "YOUR_SECRET_HERE",
"DEVHUB_BASE_URL": "https://yourbrand.cloudfrontend.net"
}
}
}
}
After updating the config, restart Claude Desktop.
Manual configuration for Cursor
This MCP can also be used in cursor with a similar configuration from above added to your Cursor global environment or to individual projects.
Examples here
Installing via Claude Code
Claude Code's command line supports MCP installs.
You can add the devhub-cms-mcp by updating the environment variables below
claude mcp add devhub-cms-mcp \
-e DEVHUB_API_KEY=YOUR_KEY_HERE \
-e DEVHUB_API_SECRET=YOUR_SECRET_HERE \
-e DEVHUB_BASE_URL=https://yourbrand.cloudfrontend.net \
-- uvx devhub-cms-mcp
Installing via Smithery
To install DevHub CMS MCP for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @devhub/devhub-cms-mcp --client claude
Local development
Clone the repo (or your fork)
git clone [email protected]:devhub/devhub-cms-mcp.git
Manual configuration of Claude Desktop
To use this server with the Claude Desktop app for local development, add the following configuration to the "mcpServers" section of your claude_desktop_config.json:
{
"mcpServers": {
"devhub_cms_mcp": {
"command": "uv",
"args": [
"--directory",
"/YOUR/LOCAL/PATH/devhub-cms-mcp/",
"run",
"main.py"
],
"env": {
"DEVHUB_API_KEY": "YOUR_KEY_HERE",
"DEVHUB_API_SECRET": "YOUR_SECRET_HERE",
"DEVHUB_BASE_URL": "https://yourbrand.cloudfrontend.net"
}
}
}
}
After updating the config, restart Claude Desktop.
Configuration for running with uv directly
This MCP requires the following environment variables to be set:
export DEVHUB_API_KEY="your_api_key"
export DEVHUB_API_SECRET="your_api_secret"
export DEVHUB_BASE_URL="https://yourbrand.cloudfrontend.net"
Then run the MCP
uv run main.py
Available Tools
This MCP provides the following tools for interacting with DevHub CMS:
Business and Location Management
- get_businesses(): Gets all businesses within the DevHub account. Returns a list of businesses with their IDs and names.
- get_locations(business_id): Gets all locations for a specific business. Returns detailed location information including address, coordinates, and URLs.
- get_hours_of_operation(location_id, hours_type='primary'): Gets the hours of operation for a specific DevHub location. Returns a structured list of time ranges for each day of the week.
- update_hours(location_id, new_hours, hours_type='primary'): Updates the hours of operation for a DevHub location.
- get_nearest_location(business_id, latitude, longitude): Finds the nearest DevHub location based on geographic coordinates.
- site_from_url(url): Gets the DevHub site ID and details from a URL. Returns site ID, URL, and associated location IDs.
Content Management
- get_blog_post(post_id): Retrieves a single blog post by ID, including its title, date, and HTML content.
- create_blog_post(site_id, title, content): Creates a new blog post. The content should be in HTML format and should not include an H1 tag.
- update_blog_post(post_id, title=None, content=None): Updates an existing blog post's title and/or content.
Media Management
- upload_image(base64_image_content, filename): Uploads an image to the DevHub media gallery. Supports webp, jpeg, and png formats. The image must be provided as a base64-encoded string.
Usage with LLMs
This MCP is designed to be used with Large Language Models that support the Model Context Protocol. It allows LLMs to manage content in DevHub CMS without needing direct API access integrated into the LLM natively.
Testing
This package includes a test suite with mocked requests to the DevHub API, allowing you to test the functionality without making actual API calls.
Running Tests
To run the tests, first install the package with test dependencies:
uv pip install -e ".[test]"
Run the tests with pytest:
uv run pytest
For more detailed output and test coverage information:
uv run pytest -v --cov=devhub_cms_mcp
Test Structure
tests/devhub_cms_mcp/test_mcp_integration.py: Tests for MCP integration endpoints
Máy chủ liên quan
Alpha Vantage MCP Server
nhà tài trợAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
Claude Swarm MCP Server
An MCP server for multi-agent orchestration using Claude AI via Claude Desktop.
Neovim LSP MCP Server
Bridges AI coding assistants with Neovim's Language Server Protocol for AI-powered code intelligence and navigation.
Profile MCP Server
An example MCP server deployable on Cloudflare Workers without authentication.
Context Portal MCP (ConPort)
A server for managing structured project context using SQLite, with support for vector embeddings for semantic search and Retrieval Augmented Generation (RAG).
Azure DevOps
Interact with Azure DevOps for managing projects, pipelines, and repositories.
mcp-hosts-installer
MCP server that installs and registers other MCP servers in Cursor, VS Code, or Claude Desktop from npm, PyPI, or a local folder (via npx).
Remote MCP Server (Authless)
A remote MCP server deployable on Cloudflare Workers without authentication.
OpenExp
Q-learning memory for Claude Code. Persistent memory that learns which context helps you get work done. Memories that lead to productive sessions (commits, PRs, tests) earn higher retrieval rank automatically. 16 MCP tools, hybrid BM25 + vector + Q-value scoring, local-first with Qdrant + FastEmbed.
TeamCity MCP Server
MCP server for JetBrains TeamCity with 87 tools for builds, tests, agents, and CI/CD pipeline management.
MegaChad
Burn-to-create looksmaxxing engine on MegaETH with 14 MCP tools for swap quotes, token stats, NFT minting, gallery, leaderboard, wallet checks, gasless burns, and orchestrated agent flows