SearchAPI

SearchAPI MCP Agent with A2A Support
  • python

12

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": {
    "rmmargt-searchapi-mcp-agent": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "mcp[cli]",
        "/path/to/searchapi-mcp-agent/mcp_server.py"
      ],
      "env": {
        "GOOGLE_API_KEY": "YOUR_GOOGLE_API_KEY_PLACEHOLDER",
        "SEARCHAPI_API_KEY": "YOUR_API_KEY_PLACEHOLDER"
      }
    }
  }
}

This MCP server provides an Agent-to-Agent (A2A) interface for SearchAPI tools via the Model Context Protocol (MCP). It lets you connect, configure, and route natural language queries to a collection of search services, with real-time status updates and robust error handling. Use it to combine map searches, flight queries, hotel bookings, and more behind a unified MCP client.

How to use

You use this MCP server by connecting an MCP client (such as an AI assistant) to the SearchAPI MCP Agent, which exposes a set of search tools through MCP. Start the agent, configure your MCP client to reach it, and then issue natural language queries or direct tool calls. The system automatically routes requests to the appropriate tool, handles streaming responses, and provides real-time task status updates.

How to install

Prerequisites: ensure you have Python 3.9 or higher and a Python environment available. You also need a working MCP client to connect to the agent and an environment to run the agent and host components.

  1. Install Python and create a virtual environment.

  2. Install required dependencies.

  3. Set up environment variables for API access.

MCP Configuration

Configure the MCP entry that runs the Host-agnostic MCP client for the SearchAPI agent using the following setup. This example uses an stdio-based MCP entry that launches a local process and communicates via standard input/output.

{
  "mcpServers": {
    "searchapi": {
      "type": "stdio",
      "name": "searchapi_mcp",
      "command": "uv",
      "args": [
        "run",
        "--with",
        "mcp[cli]",
        "/path/to/searchapi-mcp-agent/mcp_server.py"
      ],
      "env": {
        "SEARCHAPI_API_KEY": "your_api_key_here",
        "GOOGLE_API_KEY": "your_google_api_key_here"
      }
    }
  }
}

A2A Integration

This project fully implements the A2A protocol and can serve as an endpoint for AI assistants. It supports dynamic tool routing, streaming responses, real-time task status updates, and graceful error handling to ensure reliable operation.

Notes and security

Keep API keys secure and restricted to the necessary scopes. Before confirming actions in MCP clients, verify that the requested operations are appropriate and comply with your usage policies.

Available tools

search_google_web

Web search tool with web results, knowledge graph integration, related questions, suggestions, language support, and region/time range filtering.

search_google_video

Video search tool with lists, duration filtering, source filtering, and HD preview support.

search_google_maps

Place search, details, reviews, and location coordinates retrieval.

search_google_flights

Flight search with one-way/round-trip, multi-city itineraries, price calendar, filters, baggage info, and airline selection.

search_google_hotels

Hotel search with location, price/availability, facilities filtering, ratings, special offers, and room type selection.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational