# Available MCP Integrations

K3 Labs supports two categories of MCP integrations: pre-built integrations for popular services and custom MCP server connections for any service supporting the MCP standard.

### Available MCP Integrations

<table><thead><tr><th>MCP Name</th><th width="119.7664794921875">Category</th><th>Description</th><th>Use Cases</th></tr></thead><tbody><tr><td><strong>Custom MCP Server</strong></td><td>Universal</td><td>Connect any MCP-compatible service via SSE endpoint</td><td>API integrations, Custom tools, Third-party services</td></tr><tr><td><strong>PostgreSQL MCP</strong></td><td>Database</td><td>Direct PostgreSQL database access and SQL execution</td><td>Database queries, Data analysis, Report generation</td></tr><tr><td><strong>CoinGecko MCP</strong></td><td>Crypto Data</td><td>Real-time cryptocurrency market data and analysis</td><td>Price tracking, Market analysis, Portfolio monitoring</td></tr></tbody></table>

***

### Using MCP Tools in Workflows

After configuring your MCP integrations, they become available in AI Agent functions:

1. **Create or Edit AI Agent**: Add an AI Agent function to your workflow
2. **Select Tool**: In the Tool dropdown, choose your configured MCP integration
3. **Configure AI Agent**: The AI will automatically use the selected MCP tool based on user prompts and conversation context
4. **Deploy**: Deploy your workflow to start using the MCP-powered AI Agent

The AI Agent will intelligently decide when to call your MCP tools based on user requests, making complex integrations accessible through natural language conversations.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.k3-labs.com/introduction/ai-automation-suite/mcp-server/available-mcp-integrations.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.