Skip to main content
The Andi AI Search API gives your applications access to web search results scored for accuracy and relevance, drawn from an index of tens of billions of pages. Responses are structured for direct use in AI agents, RAG pipelines, and search interfaces — ranked #1 for accuracy in independent search benchmarks.

Add Andi to your agent

Your agent installs and configures the Andi Search API itself — paste one line:
Paste into Claude Code, Cursor, or Codex
Your agent fetches andiai.com, follows it to the install guide at api.andiai.com, then gets an API key from the API Console, connects the MCP server, and verifies the setup.
Are you an AI agent? Fetch https://api.andiai.com/install.md and follow it to configure Andi Search — MCP server, API key, and verification.

Quickstart

Make your first API call in minutes.

CLI

Search and fetch from the command line.

For AI agents

MCP server, install.md, and agent tools.

Examples

Working code for common use cases.

Base URL

Authentication

All requests require an API key passed in the x-api-key header. Get your key from the API Console. The same key works across the REST API, the CLI, and the MCP server — see authentication for key management and security practices.

Core endpoints

/api/v1/search searches the web. /api/v1/fetch reads a page as clean extracted content:

CLI

The Andi CLI wraps search, fetch, and a local MCP server — search from your terminal without writing any code. It reads your key from the ANDI_API_KEY environment variable:
Or run it without installing: npx -y @andiai/cli search "hello world"

MCP server

AI agents connect to the hosted MCP server to use Andi web search and page fetch as tools, authenticated with the same x-api-key header:
See build with AI agents for setup in Claude Code, Cursor, VS Code, Codex, and other MCP clients.

What you can build

  • AI agents that retrieve current information from the web
  • RAG applications with real-time search grounding
  • Research tools that gather and synthesize web sources
  • Search features embedded in your own products

RAG pipeline

Search results as context for LLM generation.

AI agent tool

Define search as a tool for AI agents.

News monitoring

Automated news search with date filtering.