Model Context Protocol (MCP) Integration
Use your favorite MCP client with xpander.ai’s Agentic Interfaces and AI Agents
The xpander.ai platform supports three flavors of MCP use:
- MCP composition: pick-and-choose operations from multiple Agentic Interfaces (connectors) and connect your MCP clients to a fine-grained, controlled list of operations.
- MCP to AI Agents: You can trigger your AI Agents from your MCP clients.
- Specific connectors: You can connect individual Agentic Interfaces (connectors) to MCP clients.
See below for walkthrouhgts on these three usage patterns.
The xpander.ai MCP composition option is an extremely powerful option, allowing you to construct an MCP server that only connects your MCP clients to specific operations across different systems, without any coding. For example, you can select only non-mutating operations across Jira, Asana and Github, and provide a powerful developer assistant to team members with no risk of deleting or modifying data in those target systems.
How is the xpander.ai MCP hosting solution unique?
Using the xpander.ai MCP Servers hosting solution with Claude Desktop
In this option, you can select individual operations from multiple connectors, thus composing a list of operations in various systems that will be available to your MCP client.
Open the MCP Servers menu
In the xpander.ai console (https://app.xpander.ai), go to the MCP Servers section
Create a new MCP Server
Click on “New MCP Server”, and provide a name and description for your MCP Server
Select operations
In this step, you can select Operations from one or more interfaces, which will be composed in your MCP server, and available to your MCP clients.
Add the MCP Server to Claude
After selecting your operations, copy the MCP Server address from the page, and add it to your MCP Client. For example:
In this option, you can select individual operations from multiple connectors, thus composing a list of operations in various systems that will be available to your MCP client.
Open the MCP Servers menu
In the xpander.ai console (https://app.xpander.ai), go to the MCP Servers section
Create a new MCP Server
Click on “New MCP Server”, and provide a name and description for your MCP Server
Select operations
In this step, you can select Operations from one or more interfaces, which will be composed in your MCP server, and available to your MCP clients.
Add the MCP Server to Claude
After selecting your operations, copy the MCP Server address from the page, and add it to your MCP Client. For example:
In this option, you create an MCP server for an entire Agnetic Interfaces (Connector) and connect it to Claude Desktop. For example, Github, Jira, Asana.
Access Agentic Interfaces Settings
Open https://app.xpander.ai In the settings menu, click on “Agentic Interfaces”.
Select a specific interface
In the Agentic Interfaces panel, select the specific application (e.g., Slack, HubSpot)
Click on MCP Configuration
Find and click on the “MCP Configuration” option.
Add the MCP Server to Claude
Add a configuration snippet like the following, replacing the URL with your specific Xpander MCP endpoint: (The file is located at ’~/Library/Application Support/Claude/claude_desktop_config.json’)
In this option, you trigger AI Agents on the xpander.ai platform from your MCP Client.
Access Agent Settings
Open https://app.xpander.ai Navigate to your agent’s settings page and click on “Add source”
Add MCP Server to your agent
Find the “MCP” and click on it to generate unique url for your server with your API keys
MCP Server url
Copy the url and configure it in your MCP-compatible client (Claude Dekstop etc’)
Add the Agent MCP Server to Claude
Add the following configuration to your Claude config file:
When using an agent as MCP, Claude can:
- Send tasks to the agent for execution
- Query the agent’s status for long-running tasks
- Access all agent capabilities through a single MCP server
- Each team member gets their own MCP URL with their specific API key and permissions
Other considerations
The MCP URL contains your API key, so never share it publicly. Treat it as a sensitive credential.
You can add multiple MCP servers to your configuration file by adding them to the mcpServers
object. Each server should have a unique key:
Instead of manually editing the configuration file, you can use the MCP installer by adding this to your configuration file at ’~/Library/Application Support/Claude/claude_desktop_config.json’:
Then simply ask Claude to install your MCP URL, and it will handle the installation automatically.
Working with Authenticated Connectors
If you’ve already configured authentication for connectors in xpander.ai (such as Gmail, LinkedIn, or other services), they will work automatically with the provided MCP URL without requiring additional authentication steps in Claude.
For example, if you’ve already connected your Gmail account in xpander.ai:
- Add the xpander MCP configuration to Claude as shown above
- You can immediately use Gmail capabilities in Claude through natural language
- No additional authentication steps are needed in Claude
Testing Your MCP Integration
Once configured, you can test your integration by asking Claude to perform actions using the connected service:
- For LinkedIn: “Can you search for AI Product Managers on LinkedIn?”
- For Gmail: “Could you check my recent unread emails?”
- For Weather: “What’s the weather like in San Francisco today?”
Claude will seamlessly connect to the xpander MCP server and utilize its agentic interfaces to fulfill your requests.