Supports deployment on DigitalOcean App Platform using the provided docker-compose.yml
Supports containerized deployment via Docker, with both direct container runs and docker-compose options
Supports deployment workflows that connect from GitHub repositories, particularly for cloud platform integrations
Supports deployment workflows that connect from GitLab repositories, particularly for cloud platform integrations
Supports deployment on Heroku platform using Procfile configuration
Supports using NGINX as a reverse proxy for production deployments
Supports process management via PM2 for production deployments
Supports direct deployment from GitHub with automatic detection on Railway platform
Provides detailed deployment support on Render cloud platform, including both render.yaml blueprint and manual setup options
Taboola API MCP Server
A flexible MCP (Model Context Protocol) server with fetchRecommendations functionality. Supports both local (STDIO) and remote (HTTP) deployment modes.
Setup
Install dependencies:
Activate virtual environment (if using one):
Deployment Options
Local Mode (STDIO Transport)
Perfect for local development and testing with MCP Inspector:
Remote Mode (HTTP Server)
Deploy as a remote HTTP server accessible over the network:
Configuration Options
Command Line Arguments
--mode
: Server mode (local
orremote
) - default:local
--host
: Host to bind to in remote mode - default:0.0.0.0
--port
: Port to bind to in remote mode - default:8000
Environment Variables
MCP_MODE
: Server mode (local
orremote
)MCP_HOST
: Host to bind to in remote modeMCP_PORT
: Port to bind to in remote mode
Environment variables override command line arguments.
Functions
fetchRecommendations
Fetches recommendations for a given publisher using their API key via Taboola API.
Parameters:
publisher_name
(str): The name of the publisherapi_key
(str): The API key for authentication
Returns:
str
: JSON recommendations data from Taboola API
Usage Examples
Local Development with MCP Inspector
Remote Deployment
Production Deployment
For production, consider using environment variables:
Or with a process manager like PM2:
Testing
Use the provided test script to verify functionality:
Cloud Deployment
Render Deployment
Deploy easily on Render cloud platform:
Option 1: Using Render.yaml (Recommended)
Push your code to GitHub/GitLab
Connect to Render:
Go to Render Dashboard
Click "New" > "Blueprint"
Connect your repository
The
render.yaml
file will be automatically detected
Deploy:
Render will automatically build and deploy your MCP server
Your server will be available at:
https://your-app-name.onrender.com
Option 2: Manual Render Setup
Create a new Web Service on Render
Connect your repository
Configure the service:
Build Command:
pip install -r requirements.txt
Start Command:
python server.py --mode remote --host 0.0.0.0 --port $PORT
Environment Variables:
MCP_MODE=remote
MCP_HOST=0.0.0.0
PYTHON_VERSION=3.13.0
Deploy and get your URL
Docker Deployment
For any Docker-compatible platform:
Other Cloud Platforms
The server is compatible with:
Heroku: Use
Procfile
withweb: python server.py --mode remote --port $PORT
Railway: Deploy directly from GitHub with automatic detection
DigitalOcean App Platform: Use the provided
docker-compose.yml
AWS/GCP/Azure: Deploy using Docker or direct Python deployment
Security Notes
In remote mode, the server binds to
0.0.0.0
by default (all interfaces)Consider using a reverse proxy (nginx, Apache) for production deployments
Ensure proper firewall rules are in place for remote access
API keys are passed as parameters - ensure secure transmission (HTTPS recommended)
Cloud platforms like Render automatically provide HTTPS endpoints
This server cannot be installed
hybrid server
The server is able to function both locally and remotely, depending on the configuration or use case.
A flexible MCP server that enables users to fetch recommendations from the Taboola API using publisher credentials, supporting both local (STDIO) and remote (HTTP) deployment modes.
Related MCP Servers
- -securityAlicense-qualityThis MCP server performs multi-topic searches in business, news, finance, and politics using the Tavily API, providing high-quality sources and intelligent summaries.Last updated -1MIT License
- AsecurityAlicenseAqualityAn MCP server implementation that integrates the Tavily Search API, providing optimized search capabilities for LLMs.Last updated -2MIT License
- -securityAlicense-qualityMCP server for using various search tools like Tavily API. Planning to support various search tools (i.e. wiki search, searxng, etc)Last updated -3MIT License
- -securityFlicense-qualityA remote MCP server that enables searching for news articles on specific topics through the Tavily API without requiring authentication.Last updated -