How to integrate Search api MCP with Pi

Connect Pi to Search api MCP. Get the top google search results for "climate change", extract featured snippets for "best project management tools", and more using natural language, with authentication handled for you.

Search api logoSearch api
Api Key

Search api is a real-time SERP API that streamlines proxy management and CAPTCHA handling for web data extraction. Get reliable, structured JSON search results with minimal setup.

5 Tools

Introduction

Pi is a minimal, self-extensible coding agent that lives in your terminal — one agent loop over Claude, GPT-5, Gemini, Grok, DeepSeek, and 20+ other providers, with maximum extension surface and minimum product opinion. Its core ships four tools (read, write, edit, bash) and self-extends at runtime through skills, extensions, and packages.

This guide explains the easiest and most robust way to connect your Search api account to Pi. You can do this through either Composio Connect CLI or Composio Connect MCP. Because Pi already runs shell commands as first-class tools and ships no built-in MCP, the CLI is the recommended path — it's faster to set up, needs no server config, and chains multi-step tasks more reliably. The MCP path is also fully supported through Pi's official pi-mcp-adapter extension.

Also integrate Search api with

What is Composio Connect?

Composio Connect is a consumer offering that lets anyone plug 1,000+ applications directly into their agent harness — including Pi. It can:

  • Search and load tools from relevant toolkits on-demand, reducing context usage.
  • Chain multiple tools to accomplish complex workflows via a remote workbench, without excessive back-and-forth with the LLM.
  • Manage app authentication end-to-end with zero manual overhead.

Connect Search api to Pi with Composio

Prerequisites: Install Pi

Pi needs Node.js 18+ (Node 22 recommended). Install the agent globally with npm:

bash
npm install -g --ignore-scripts @earendil-works/pi-coding-agent

On Linux or macOS you can use the installer script instead:

bash
curl -fsSL https://pi.dev/install.sh | sh

Then run pi in any project directory and authenticate your model provider — use /login inside Pi for subscription providers (Claude Pro/Max, ChatGPT, GitHub Copilot), or set an API key such as ANTHROPIC_API_KEY before starting. Confirm it's working:

bash
pi --version

Full first-run details are in the Pi Quickstart.

Option 1: Composio CLI (recommended)

Pi runs shell commands as first-class tools, so the Composio Universal CLI is the most natural fit — no MCP server to configure and reliable multi-step tool chaining. Install and authenticate:

bash
# Install the Composio CLI
curl -fsSL https://composio.dev/install | bash

# Log in to Composio
composio login

Connect to Search api

Ask Pi to connect to Search api, or simply request any Search api-related task. Under the hood Pi calls Composio commands like any other shell tool:

bash
composio search "what can I do with Search api?"
composio link search_api

On the first Search api call, composio link search_api opens an OAuth prompt so you can authorize access. After that, every Search api command works with your stored credentials automatically — just talk to Pi and it will search, execute, and chain Search api tools as needed.

Option 2: Composio MCP

Pi's core intentionally ships no built-in MCP, but the official pi-mcp-adapter extension adds full MCP support — exposing every server through a single lightweight proxy tool (~200 tokens) instead of loading hundreds of tool definitions into context.

1. Install the MCP adapter extension

bash
pi install npm:pi-mcp-adapter

Restart Pi after installation.

2. Add the Composio MCP server

Create (or edit) a .mcp.json file in your project root, or ~/.config/mcp/mcp.json for a user-global setup:

bash
{
  "mcpServers": {
    "composio": {
      "url": "https://connect.composio.dev/mcp"
    }
  }
}

The adapter connects lazily by default — the server won't start until Pi actually calls one of its tools, and cached metadata keeps search and describe working without a live connection.

3. Authenticate

Run /mcp-auth inside Pi to open the authentication modal and select composio from the list. Complete the sign-in in your browser, then on the consent screen click Allow access to authorize Composio. Once approved, the server shows as connected inside Pi:

Pi /mcp-auth modal listing the composio MCP server
Composio OAuth consent screen with the Allow access button
Composio MCP server connected inside Pi

4. Done!

Confirm the server is live with /mcp to open the interactive panel, then ask Pi to connect to Search api or request any Search api-related task — it will prompt you to authorize Search api on first use.

What is the Search api MCP server, and what's possible with it?

The Search api MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Search api account. It provides structured and secure access so your agent can perform Search api operations on your behalf.

Way Forward

With Search api connected, Pi can now act on your behalf whenever you ask it to.

From here, you can extend Pi further:

  • Connect more apps: Calendar, Slack, Notion, Linear, and hundreds of others are available through the same Composio Connect setup. Each new integration compounds what Pi can do for you.
  • Build workflows across tools: Once multiple apps are connected, Pi can chain actions together — turn an email into a calendar invite, a Slack message into a Linear ticket, or a meeting note into a follow-up draft.
  • Lean into Pi's extension surface: Wrap common Search api flows as Pi skills or prompt templates so recurring tasks become one-line commands, and use directTools in the MCP adapter to promote your most-used Search api tools into Pi's tool list directly.

If you run into trouble or want to share what you've built, join the community or check out the Docs for deeper configuration options.

TOOLS

Supported Tools

Every Search api action and event your agent gets out of the box.

Get Account Info

Tool to retrieve account usage statistics including monthly usage, remaining credits, hourly limits, and subscription period information.

Get Cached Search by ID

Tool to retrieve cached search results by search ID in JSON format.

Get Cached Search HTML by ID

Tool to retrieve cached search results by search ID in HTML format.

Get Locations

Tool to get available locations for geo-localized search queries.

Search

Tool to perform unified search across 40+ search engines including Google, Bing, Yahoo, DuckDuckGo, YouTube, Amazon, and more.

FAQ

Frequently asked questions

With a standalone Search api MCP server, the agents and LLMs can only access a fixed set of Search api tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Search api and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. Pi fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Search api tools.

Yes, absolutely. You can configure which Search api scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Search api data and credentials are handled as safely as possible.

Start with Search api.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Search api tool your agent needs.Free to start.

Start building