Data Connectors
Using MCPs with Data Connector
If you’re exploring how to use MCPs (Model Context Protocol) with our new Data Connector feature, you’re in the right place. This guide gives you a quick overview of what MCPs are, why they matter, and how you can use them to power advanced workflows in Julius.
What Are MCPs?
MCPs (short for Model Context Protocol) are a powerful way to connect AI agents like Julius to external data sources and tools. Think of them as secure bridges that allow AI to access live information from databases, file systems, APIs, and other applications, enabling real-time integration with your existing tools and data rather than being limited to the AI’s training knowledge. Each MCP consists of:- Tools: Specific actions Julius can perform (e.g., search your files, query a database, send a Slack message)
- Server: The application or service that makes these tools available to Julius
How MCPs + Data Connector Work Together
Here’s how to set up and use MCP servers:- Connect Your MCP Server
- Go to your Julius workspace settings and add an MCP server via the Data Connector Settings Page
- Authenticate using OAuth or API key, just like other data connectors
- Use the Available Tools
- Once connected, Julius can access all the tools that MCP server provides
- These tools work alongside your other data connectors - you can use them together in the same conversation
- Julius will automatically know when to use MCP tools based on what you’re asking for
- Seamless Integration
- MCP tools appear naturally in your Julius conversations
- No special interface needed - just ask Julius to do something, and it will use the appropriate tools
- Works with your existing data sources and workflows
Connecting your MCP with an Endpoint
When connecting to your MCP, you’ll need to input your endpoint so Julius can access and query the right database. Endpoint = Base MCP server URL
For example: https://api.example.com/v1/mcp
IMPORTANT: we do not support SSE URL’s at this time e.g. https://api.example.com/v1/sse
How to Configure your Application to be MCP compatible with Julius AI
To configure your AI application as an MCP to connect to Julius, you’ll need to set up an MCP server:Visit the Model Context Protocol website for instructions on how to set up an MCP server: https://modelcontextprotocol.io/overview
Applications requiring an MCP Server setup
| Name | Endpoint URL |
|---|---|
| Turkish Tech Labs | https://mcp.turkishtechlab.com |
| Linear | https://mcp.linear.app |
| Canva | https://mcp.canva.com |
| Zapier | https://mcp.zapier.com |
| Square | https://mcp.squareup.com |
| Listenetic | https://mcp.listenetic.com |
| Wix | https://mcp.wix.com |
| Stripe | https://mcp.stripe.com |
| Atlassian | https://mcp.atlassian.com |
| Intercom | https://mcp.intercom.com |
| Waystation | https://waystation.ai |
| Simple Scraper | https://mcp.simplescraper.io |
| Sentry | https://mcp.sentry.dev |
Applications not requiring an MCP setup
| Name | Endpoint URL |
|---|---|
| Notion | https://mcp.notion.com |
| Prisma | https://mcp.prisma.io |