ProtoLinkAI

Simplifying MCP server interactions for seamless AI integration.

python

GitHub Stars

python

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": {
    "stevenroyola-protolink": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "-v",
        "/path/to/local/eliza:/app/eliza",
        "--rm",
        "mcpagentai"
      ],
      "env": {
        "ELIZA_PATH": "/path/to/eliza",
        "TWITTER_EMAIL": "you@example.com",
        "TWITTER_API_KEY": "YOUR_API_KEY",
        "TWITTER_PASSWORD": "your_twitter_password",
        "TWITTER_USERNAME": "your_twitter_username",
        "ANTHROPIC_API_KEY": "YOUR_API_KEY",
        "TWITTER_CLIENT_ID": "YOUR_CLIENT_ID",
        "TWITTER_API_SECRET": "YOUR_API_SECRET",
        "TWITTER_ACCESS_TOKEN": "YOUR_ACCESS_TOKEN",
        "TWITTER_BEARER_TOKEN": "YOUR_BEARER_TOKEN",
        "TWITTER_ACCESS_SECRET": "YOUR_ACCESS_SECRET",
        "TWITTER_CLIENT_SECRET": "YOUR_CLIENT_SECRET"
      }
    }
  }
}

You use a standardized MCP server to wrap diverse tools under a common communication protocol, enabling secure, scalable, and interoperable tool interactions across AI models and systems. This guide shows practical ways to run ProtoLinkAI, connect with an MCP client, and integrate tools like Twitter, ElizaOS, time utilities, weather, and more.

How to use

Connect with an MCP client to interact with ProtoLinkAI. You can configure the server to expose a set of tools that perform concrete actions—such as retrieving weather data, calculating expressions, or managing social interactions—through a consistent interface. Use an MCP client to discover available tools, send requests, and receive structured responses. You can tailor which tools you enable by configuring the multi-tool agent to load only the tools you want.

How to install

pip install ProtoLinkai

Run locally with your preferred timezone to ensure correct time-based responses.

ProtoLinkai --local-timezone "America/New_York"

Or build and run using Docker for containerized deployment.

# Build the Docker image
 docker build -t ProtoLinkai .

# Run the container
 docker run -i --rm ProtoLinkai

Additional configuration and examples

You can integrate additional tools and wiring configurations using explicit MCP server configurations. For example, Claude Desktop can connect to a local ElizaOS setup via a defined MCP server entry:

{
  "mcpServers": {
    "claude_desktop": {
      "command": "docker",
      "args": ["run", "-i", "-v", "/path/to/local/eliza:/app/eliza", "--rm", "mcpagentai"]
    }
  }
}

Available tools

TwitterAgent

Automates tweeting, replying, and managing Twitter interactions using the MCP wrapper and Tweepy integration.

ElizaAgent

Provides ElizaOS integration for enhanced automation within ProtoLink via MCP agents.

TimeAgent

Time utilities for current time, timezones, and time-based computations.

WeatherAgent

Weather information from an API to fetch current conditions and forecasts.

DictionaryAgent

Dictionary lookups and word definitions accessed through MCP endpoints.

CalculatorAgent

Mathematical expression evaluation and calculation utilities.

CurrencyAgent

Currency exchange data through an API for real-time rates.

StocksAgent

Real-time and historical stock market data endpoints.

NewsAgent

Latest news headlines (work in progress) provided through MCP endpoints.

ClaudeDesktopConnector

Configures integration with Claude Desktop via a predefined MCP server entry.

Built by

VeilStrat

AI signals for GTM teams