> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pylar.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Pylar Documentation

> Build AI agents that interact with your data securely. Connect databases, create governed views, and deploy MCP tools to any agent builder.

## Welcome to Pylar

Pylar is a **secure data access layer for AI agents** that enables interaction with structured data sources without requiring direct database access or complex API integrations.

## How It Works

<img src="https://mintcdn.com/pylar/IO576CKliSaQSYid/images/pylar-workflow.svg?fit=max&auto=format&n=IO576CKliSaQSYid&q=85&s=cf01c563b881d10231d753e6016a7bcd" alt="Pylar Workflow Diagram" width="1200" height="480" data-path="images/pylar-workflow.svg" />

1. **Data Sources** connect to Pylar (Snowflake, BigQuery, PostgreSQL, HubSpot, Salesforce, and more)
2. **SQL View** is created to govern exactly what data agents can access
3. **MCP Tools** are built on the view—multiple tools for different use cases
4. **Tools publish** to Agent Builders (Claude Desktop, Cursor, LangGraph, Zapier, Make, n8n, and more)
5. **Evals** monitors all tool interactions for observability and optimization

**Key Benefits**:

* ✅ **Single Control Pane**: Update views and tools without redeploying agents
* ✅ **No Raw Access**: Agents only access data through your governed views
* ✅ **Unified Interface**: One MCP endpoint for all data sources
* ✅ **Real-time Observability**: Monitor all agent interactions with Evals

<CardGroup cols={2}>
  <Card title="What is Pylar?" icon="book" href="/introduction/what-is-pylar">
    Learn how Pylar provides governed SQL views, AI-powered MCP tool creation, and seamless multi-database integration.
  </Card>

  <Card title="Quick Start" icon="rocket" href="/introduction/quick-start">
    Get up and running in minutes. Connect your databases, create views, and deploy your first agent.
  </Card>

  <Card title="Why Pylar?" icon="lightbulb" href="/introduction/why-pylar">
    Discover the benefits: security, developer experience, operational excellence, and cost efficiency.
  </Card>

  <Card title="Examples" icon="code" href="/examples/customer-support-agent">
    See 20 real-world agent examples for customer support, sales, marketing, product, finance, and operations.
  </Card>
</CardGroup>

## Key Features

### 🔒 Governed SQL Views

Create SQL views that define exactly what data agents can access. Views are the only access level—agents never get raw database access.

### 🤖 AI-Powered MCP Tool Creation

Describe what you want in natural language, and Pylar's AI generates MCP tools for your agents. No manual coding required.

### 🔗 Multi-Database Integration

Join data across multiple databases, warehouses, and business applications. Query Snowflake, BigQuery, PostgreSQL, HubSpot, Salesforce, and more—all in one place.

### 📊 Built-in Observability

Monitor agent performance with the Evals dashboard. Track errors, query patterns, and optimize your tools based on real usage data.

### 🚀 One Control Pane

Update views and tools without redeploying agents. Changes reflect immediately across all agent builders—Claude Desktop, Cursor, LangGraph, Zapier, and more.

## Getting Started

### Step 1: Connect Your Data

Connect your databases and data sources to Pylar. Supported sources include:

* **Databases**: BigQuery, Snowflake, PostgreSQL, MySQL, Redshift, MotherDuck, Supabase, and more
* **Business Apps**: HubSpot, Salesforce, Google Sheets, and more

<Card title="Making Connections" icon="plug" href="/learn/making-connections/overview">
  Learn how to connect your data sources
</Card>

### Step 2: Create Views

Use Pylar's SQL IDE to create governed views of your data. Join across multiple databases, filter sensitive data, and define exactly what agents can access.

<Card title="Creating Data Views" icon="code" href="/learn/creating-data-views/overview">
  Learn how to create your first view
</Card>

### Step 3: Build MCP Tools

Create MCP tools using AI or manually. Each tool defines how agents interact with your views.

<Card title="Building MCP Tools" icon="wrench" href="/learn/building-mcp-tools/overview">
  Learn how to create MCP tools
</Card>

### Step 4: Publish and Deploy

Publish your tools and get your MCP credentials. Connect to any agent builder—no API hassles, no redeployment.

<Card title="Publishing Tools" icon="upload" href="/learn/publishing-tools/publishing-your-tools">
  Learn how to publish and deploy your tools
</Card>

## Popular Use Cases

<CardGroup cols={3}>
  <Card title="Customer Support" icon="headphones" href="/examples/customer-support-agent">
    Build agents that access customer history, orders, and support tickets
  </Card>

  <Card title="Sales Analytics" icon="trending-up" href="/examples/sales-assistant">
    Analyze pipeline, forecast revenue, and identify opportunities
  </Card>

  <Card title="Marketing Optimization" icon="megaphone" href="/examples/marketing-campaign-optimizer">
    Optimize campaigns, analyze attribution, and measure ROI
  </Card>

  <Card title="Product Analytics" icon="chart-bar" href="/examples/product-usage-analyst">
    Track feature adoption, analyze usage patterns, and prioritize improvements
  </Card>

  <Card title="Financial Analysis" icon="dollar-sign" href="/examples/financial-analyst">
    Analyze revenue, track expenses, and generate financial reports
  </Card>

  <Card title="Operations Monitoring" icon="server" href="/examples/it-operations-monitor">
    Monitor system health, track performance, and generate incident reports
  </Card>
</CardGroup>

## Documentation Sections

### 📚 Learn

Comprehensive guides covering everything from connecting databases to monitoring with Evals:

* [Making Connections](/learn/making-connections/overview) - Connect your data sources
* [Creating Data Views](/learn/creating-data-views/overview) - Build governed SQL views
* [Building MCP Tools](/learn/building-mcp-tools/overview) - Create tools for your agents
* [Publishing Tools](/learn/publishing-tools/overview) - Deploy to agent builders
* [Connecting Agent Builders](/learn/connecting-agent-builders/overview) - Integrate with Claude, Cursor, LangGraph, and more
* [Evals](/learn/evals/overview) - Monitor and optimize agent performance

### 💡 Examples

20 real-world agent examples across different domains:

* Customer Support & Success (4 examples)
* Sales & Revenue (4 examples)
* Marketing (4 examples)
* Product (3 examples)
* Finance (3 examples)
* Operations (2 examples)

<Card title="Browse All Examples" icon="code" href="/examples/customer-support-agent">
  See how others are using Pylar
</Card>

### ❓ Help

Get answers to common questions and troubleshooting help:

* [FAQ](/help/faq) - Frequently asked questions
* [Troubleshooting](/help/troubleshooting) - Common issues and solutions

## Need Help?

* **Support Email**: [support@pylar.ai](mailto:support@pylar.ai)
* **Get Started**: [Sign up for Pylar](https://app.pylar.ai/signup)
* **Website**: [pylar.ai](https://www.pylar.ai)

## Ready to Get Started?

<Card title="Quick Start Guide" icon="rocket" href="/introduction/quick-start">
  Follow our step-by-step guide to build your first agent
</Card>