openrouter.mdx

title	OpenRouter MCP Integration
sidebarTitle	OpenRouter
description	Guide for integrating OpenRouter models with PraisonAI agents using MCP
icon	network-wired

Add OpenRouter Tool to AI Agent

flowchart LR
    In[In] --> Agent[AI Agent]
    Agent --> Tool[Airbnb MCP]
    Tool --> Agent
    Agent --> Out[Out]
    
    style In fill:#8B0000,color:#fff
    style Agent fill:#2E8B57,color:#fff
    style Tool fill:#FF5A5F,color:#fff
    style Out fill:#8B0000,color:#fff

Loading

Quick Start

Set your OpenRouter API key as an environment variable in your terminal: ```bash export OPENROUTER_API_KEY=your_openrouter_api_key_here ```

<Step title="Create a file">
    Create a new file `openrouter_airbnb.py` with the following code:
    ```python
    from praisonaiagents import Agent, MCP

    search_agent = Agent(
        instructions="""You help book apartments on Airbnb.""",
        llm="openrouter/google/gemini-2.0-flash-exp:free",
        tools=MCP("npx -y @openbnb/mcp-server-airbnb --ignore-robots-txt")
    )

    search_agent.start("MUST USE airbnb_search Tool to Search. Search for Apartments in Paris for 2 nights. 04/28 - 04/30 for 2 adults. All Your Preference")
    ```
</Step>

<Step title="Install Dependencies">
    Make sure you have Node.js installed, as the MCP server requires it:
    ```bash
    pip install "praisonaiagents[llm]"
    ```
</Step>

<Step title="Run the Agent">
    Execute your script:
    ```bash
    python openrouter_airbnb.py
    ```
</Step>

**Requirements** - Python 3.10 or higher - Node.js installed on your system - OpenRouter API key

Features

Access to various models through OpenRouter's unified API. Seamless integration with Model Context Protocol. Search for accommodations on Airbnb with natural language queries. Use free tier models like Gemini Flash through OpenRouter.