Web Search

This guide shows how to add web search to workflows using the Tavily Model Context Protocol (MCP) server, an AI-optimized search provider designed for LLM applications. While alternatives exist (Exa, SerpAPI, Brave Search), this guide focuses on Tavily configuration.

Tavily Search

Tavily provides AI-optimized search with structured JSON responses, news search capability, and fast response times through the @tavily/mcp MCP server.

---
on: issues
engine: copilot
mcp-servers:
  tavily:
    command: npx
    args: ["-y", "@tavily/mcp"]
    env:
      TAVILY_API_KEY: "${{ secrets.TAVILY_API_KEY }}"
    allowed: ["search", "search_news"]
---

# Search and Respond

Search the web for information about: ${{ github.event.issue.title }}

Use the tavily search tool to find recent information.

Setup:

1. Sign up at tavily.com and get your API key
2. Add as repository secret: gh aw secrets set TAVILY_API_KEY --value "<your-api-key>"

Tavily Terms of Service

Test your configuration with gh aw mcp inspect <workflow>.

Tool Discovery

To see available tools from the Tavily MCP server:

# Inspect the MCP server in your workflow
gh aw mcp inspect my-workflow --server tavily

# List tools with details
gh aw mcp list-tools tavily my-workflow --verbose

Network Permissions

Agentic workflows require explicit network permissions for MCP servers:

network:
  allowed:
    - defaults
    - "*.tavily.com"

Related Documentation

• MCP Integration - Complete MCP server guide
• Tools - Tool configuration reference
• AI Engines - Engine capabilities and limitations
• CLI Commands - CLI commands including mcp inspect
• Model Context Protocol Specification
• Tavily MCP Server
• Tavily Documentation