Twitter MCP Bridge Server

Bridges MCP servers with AI SDK to execute MCP tools during AI workflows

typescript

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "vrknetha-aisdk-mcp-bridge": {
      "command": "npx",
      "args": [
        "-y",
        "@enescinar/twitter-mcp"
      ],
      "env": {
        "API_KEY": "YOUR_TWITTER_API_KEY",
        "ACCESS_TOKEN": "YOUR_TWITTER_ACCESS_TOKEN",
        "API_SECRET_KEY": "YOUR_TWITTER_API_SECRET",
        "FIRE_CRAWL_API_KEY": "YOUR_FIRECRAWL_API_KEY",
        "FIRE_CRAWL_API_URL": "https://api.firecrawl.com",
        "ACCESS_TOKEN_SECRET": "YOUR_TWITTER_ACCESS_TOKEN_SECRET"
      }
    }
  }
}

You use the AISDK MCP Bridge to connect MCP servers with AI models, enabling tool execution across multiple MCP servers from your AI workflows. This bridge streamlines running server-side MCP tools inside your AI prompts, while keeping configuration modular and decoupled from your code.

How to use

Initialize the MCP service in your application code to prepare tool access across all configured MCP servers. Retrieve the available tools from the connected MCP servers, or scope to a specific server, and then pass those tools to your AI model so it can invoke them as needed. When you finish, clean up resources to gracefully close all server connections.

Typical usage flow: initialize MCP, fetch tools, use the tools with your AI model, and finally call cleanup to release resources. You can target all servers or just a single server by name to reduce surface area during tool selection.

How to install

Prerequisites: Node.js 20.x or higher and npm 7.x or higher.

Install the bridge package from your project root.

Configuration

Configure one or more MCP servers in an mcp.config.json file at your project root. Each server runs independently and can use stdio for local execution or be interacted with via an HTTP URL if you migrate to a remote MCP server.

Security and best practices

Keep API keys and secrets in environment variables or a secure secret store. Do not hard-code credentials in your source files. Use the bridge’s environment variable support to inject keys at runtime.

Troubleshooting and notes

If you encounter initialization or communication issues, enable debug logging to get verbose insight into server startup, tool registration, and execution details. Review your environment configuration and ensure that each configured MCP server is reachable and that its command arguments match what the server expects.

Available tools

initializeMcp

Initialize the MCP service with optional debug settings to establish the MCP environment and server readiness.

getMcpTools

Retrieve AI SDK compatible tools from configured MCP servers, with optional server scoping.

cleanupMcp

Clean up MCP resources and close all server connections when you are finished.

executeMcpFunction

Execute a specific function on an MCP server directly, given the server name, function name, and arguments.

Built by

VeilStrat

AI signals for GTM teams