Skip to main content
Cover Image Enhance your VoltAgent applications with real-time social media context from Membit. This integration allows your AI agents to access up-to-the-minute discussions, trends, and insights from platforms like X (Twitter), Farcaster, and more.

​
Prerequisites

Before you begin, ensure you have:
  • Node.js 20 or higher installed
  • A Membit account with API access
  • Basic familiarity with VoltAgent agents and workflows
  • TypeScript knowledge (recommended)
You’ll need valid Membit API credentials and the MCP remote URL. If you don’t have access yet, get your API key to get started.

​
Installation

Install the required packages for VoltAgent and MCP integration: 
# Install VoltAgent core packages
npm install @voltagent/core
VoltAgent works best with TypeScript and structured logging. Make sure your project is configured accordingly.

​
Quick Start

1

Import required modules

Import the necessary components for VoltAgent and MCP integration:
import { VoltAgent, Agent, MCPConfiguration } from "@voltagent/core";
import { createPinoLogger } from "@voltagent/logger";
import { VercelAIProvider } from "@voltagent/vercel-ai";
import { openai } from "@ai-sdk/openai";
2

Configure MCP connection

Set up the MCP configuration to connect to Membit’s tools:
const mcpConfig = new MCPConfiguration({
  servers: {
    membit: {
      type: "stdio",
      command: "npx",
      env: {
        MEMBIT_API_KEY: <your-api-key>,
      },
      args: [
        "mcp-remote",
        "https://mcp.membit.ai/mcp",
        "--header",
        "X-Membit-Api-Key:${MEMBIT_API_KEY}",
      ],
    },
  },
});
VoltAgent supports streamable HTTP transport for efficient MCP connections.
Replace <your-api-key> with your actual Membit API key. Keep this credential secure and don’t share it with unauthorized users.
3

Create your Membit-powered agent

Create a VoltAgent agent with Membit tools:
const membitAgent = new Agent({
  name: "social-media-analyst",
  instructions:
    "You are a social media analyst with access to real-time data. Use cluster_search to find trending discussions, cluster_info for detailed analysis, and post_search for specific posts.",
  llm: new VercelAIProvider(),
  model: openai("gpt-4o-mini"),
  tools: await mcpConfig.getTools(),
});
4

Initialize VoltAgent system

Create the VoltAgent system with your agent:
// Initialize VoltAgent with your agent(s)
new VoltAgent({
  agents: {
    membitAgent,
  },
});
Your VoltAgent is now powered by real-time social media context from Membit!

​
Complete Example

Here’s a full working example that demonstrates the integration: 
import { VoltAgent, Agent, MCPConfiguration } from "@voltagent/core";
import { createPinoLogger } from "@voltagent/logger";
import { VercelAIProvider } from "@voltagent/vercel-ai";
import { openai } from "@ai-sdk/openai";

// Configure MCP connection to Membit
const mcpConfig = new MCPConfiguration({
  servers: {
    membit: {
      type: "stdio",
      command: "npx",
      env: {
        MEMBIT_API_KEY: <your-api-key>,
      },
      args: [
        "mcp-remote",
        "https://mcp.membit.ai/mcp",
        "--header",
        "X-Membit-Api-Key:${MEMBIT_API_KEY}",
      ],
    },
  },
});

// Create Membit-powered agent
const socialAnalyst = new Agent({
  name: "membit-social-analyst",
  instructions: `You are an expert social media analyst with access to real-time trending data.
Use cluster_search to find trending discussions, cluster_info to dive deeper into specific conversations,
and post_search to find individual posts. Always provide context and source URLs.`,
  llm: new VercelAIProvider(),
  model: openai("gpt-4o-mini"),
  tools: await mcpConfig.getTools(),
});

// Initialize VoltAgent
const voltAgent = new VoltAgent({
  agents: {
    socialAnalyst,
  },
});

​
Troubleshooting

Problem: Cannot connect to Membit MCP serverSolutions:
  • Verify your API key
  • Check network connectivity and firewall settings
  • Ensure the streamable HTTP endpoint is accessible
  • Try increasing the timeout value in MCPConfiguration
Problem: mcpConfig.getTools() returns empty or failsSolutions:
  • Ensure MCP configuration is correct with proper server settings
  • Check that the Membit API key is valid
  • Verify the MCP server URL is accessible
  • Try initializing the MCP config in a try-catch block
Problem: Workflows fail or don’t execute properlySolutions:
  • Check agent dependencies and execution order
  • Verify all required agents are properly registered
  • Use structured logging to debug workflow steps
  • Ensure agents have access to required tools