BuildKit

The Foundation for your Integrations - Generate AI tools and MCP servers for any integration with a single prompt

收录于 1 年前更新于 1 年前正常收录
BuildKit 网站预览

详细内容

BuildKit 2.0 by Pica

Build AI tools with a single prompt

The easiest way to build AI tools and MCPs for integrations. Create production-ready tools in minutes.

Get startedWatch demo

Supporting:

VercelVercel AI SDK

LangChainLangChain

MCPMCP

Getting Started Tutorial

Build an AI tool to fetch your emails

👋 Follow this tutorial to build a tool to fetch your Gmail emails in under 5 minutes.

What we'll do:

  1. Install the Pica MCP Server

  2. Connect your Gmail account

  3. Set up a starter project (Vercel AI SDK, LangChain, or MCP)

  4. Add some rules for the LLMs to understand BuildKit

  5. Prompt the LLM to build your tool

1

Install the Pica MCP Server

First, let's add the Pica MCP Server to your development environment. Select your preferred tool and follow the instructions.

CursorCursorClaudeClaude CodeWindsurfWindsurf

In the Cursor menu, select "MCP Settings" and update the MCP JSON file to include the following:

MCP Settings JSONCopy

{
  "mcpServers": {
    "pica": {
      "command": "npx",
      "args": ["@picahq/mcp"],
      "env": {
        "PICA_SECRET": "your-pica-secret-key"
      }
    }
  }
}

Note: Replace your-pica-secret-key with your actual Pica secret key from the link below.

!

Grab your API Key

Navigate to your Pica dashboard to access your API keys.

Get API Key

2

Connect your Gmail account

Now we need to connect your Gmail account so we can test our tool after we build it.

Add Gmail Connection

Adding new Gmail connection in Pica

3

Set up a starter project

Choose your preferred framework and follow the setup steps to get your starter project up and running.

VercelVercel AI SDKLangChainLangChainMCPMCP Server

1. Clone and install dependencies

Clone RepositoryCopy

git clone https://github.com/picahq/buildkit-vercel-ai-starter.git && cd buildkit-vercel-ai-starter

Install DependenciesCopy

npm install

2. Set up environment variables

Create a .env.local file in the root directory:

.env.localCopy

OPENAI_API_KEY=your_openai_api_key_here

3. Run the development server

Start ServerCopy

npm run dev

4. Open your browser

Navigate to http://localhost:3000 to see the chat interface.

4

Add some rules for the LLMs to understand BuildKit

CursorCursorClaudeClaude CodeWindsurfWindsurf

BuildKit Rules for Cursor

.cursor/rules/buildkit.mdc

Click the button below to copy the rules for Instant and paste them into .cursor/rules/buildkit.mdc in the root of your project.

Copy

✓

Verify Setup

You can verify setup by asking "What connections do I have in Pica?" - it should show your Gmail connection.

5

Prompt the LLM to build your tool

VercelVercel AI SDK toolLangChainLangChain toolMCPMCP Server tool

Copy this prompt to build the Vercel AI SDK tool:

Vercel AI SDK ToolCopy

Create me a tool called fetchGmailEmails in my Vercel AI SDK agent for fetching my Gmail unread emails and returning the content using BuildKit

🚀

Ready for more?

You've just seen how fast it is to build with BuildKit! Browse our catalog of 25,000+ actions across 150+ integrations and create tools or MCP servers for any platform with a single prompt.

Explore All Integrations

网站信息

域名
buildkit.picaos.com
收录路径
picaos