Using the Plugged.in API

Learn how to integrate with the Plugged.in API for programmatic access to your MCP servers

Overview

The Plugged.in API provides programmatic access to manage MCP servers, query RAG knowledge bases, and automate workflows. This guide covers authentication, endpoints, and best practices.

Automation

Automate server management and deployments

Secure Access

API key authentication with rate limiting

Prerequisites

Active Plugged.in account
Basic programming knowledge
Understanding of REST APIs

Step 1: Authentication Setup

Required

Generate and configure API keys for secure access

Generate API Key

Create a new API key from your account settings:

Settings → API Keys → Generate New Key

Using Your API Key

Include your API key in the Authorization header:

Authorization: Bearer YOUR_API_KEY

Store API keys securely and never commit them to version control. Use environment variables for production applications.

Step 2: Core API Endpoints

Endpoints

Explore the main API endpoints for server management

Server Management

Manage your MCP servers programmatically:

# List servers
GET /api/servers

# Get server details
GET /api/servers/:id

# Create server
POST /api/servers

# Update server
PUT /api/servers/:id

RAG Queries

Query your knowledge base:

POST /api/rag/query
{
  "query": "Your question here",
  "limit": 5
}

Step 3: Implementation Examples

Code

Practical examples in different programming languages

JavaScript/Node.js

Example using fetch API:

const response = await fetch('https://pluggedin.ai/api/servers', {
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  }
});

const servers = await response.json();

Python

Example using requests library:

import requests

headers = {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
}

response = requests.get('https://pluggedin.ai/api/servers', headers=headers)
servers = response.json()

Step 4: Rate Limits & Best Practices

Important

Understand rate limiting and optimize your API usage

Rate Limit Tiers

Different endpoints have different rate limits:

• Standard endpoints: 60 requests/minute
• Sensitive operations: 10 requests/hour
• Public endpoints: 100 requests/minute

Rate Limit Headers

Monitor your usage with response headers:

X-RateLimit-Limit: 60
X-RateLimit-Remaining: 59
X-RateLimit-Reset: 1640995200

Next Steps

• Set up webhooks for real-time notifications
• Explore community SDKs for your language
• Review security best practices for API usage