---
updatedAt: 2026-10-08T11:12:32.000Z
agentTools:
siteIndex: https://documentation.bloomreach.com/llms.txt
projectIndex: https://documentation.bloomreach.com/loomi-connect/llms.txt
---
# Get started with MCP
This guide walks you through connecting an MCP-compatible AI application or platform to the Loomi Connect MCP servers. Once connected, your AI application can read live data from your Bloomreach workspace through more than 160 [tools](https://documentation.bloomreach.com/loomi-connect/docs/marketing-tools) spanning marketing, analytics, search, and Data hub, including write tools that create, update, and delete configuration.
### Note
Loomi Connect is available by default to all orgs on the [unified login](https://documentation.bloomreach.com/engagement/docs/unified-login-overview).
[Join the Loomi Connect Slack channel](https://luma.link/CO9HbirQkr) for updates and support.
## Prerequisites
* A Bloomreach account with access to the workspace you want to query. The MCP server respects your existing Bloomreach [IAM permissions](https://documentation.bloomreach.com/data-hub/docs/unified-administration#role-management-by-product), including [PII masking](https://documentation.bloomreach.com/loomi-connect/docs/what-is-loomi-connect#data-access).
* One of the following AI applications, or another platform that supports MCP connections:
* [Claude Code](https://claude.ai/code)
* [Cursor](https://cursor.com/)
* [VS Code](https://code.visualstudio.com/)
## Setup overview
Loomi Connect runs remote MCP servers, so there's nothing to install locally. Connect to an AI application in three steps:
1. Add a Loomi Connect server URL to your AI application's MCP configuration.
2. Restart or reload the AI application so it picks up the new server.
3. Trigger a tool call to start the browser-based [authentication](https://documentation.bloomreach.com/loomi-connect/docs/authenticate-mcp-connection) flow.
4. [Test MCP capabilities](https://documentation.bloomreach.com/loomi-connect/docs/test-mcp-capabilities) in your AI application.
## Connect the MCP server
### Important
Connect to one or more region-specific MCP servers that match your project or account configuration. Partner organizations can build demos using the demo server at `https://brx.connect.loomi.ai/mcp`.
Contact [loomi-connect@bloomreach.com](mailto:loomi-connect@bloomreach.com) if you face issues with the connection or access.
Follow the steps for your preferred environment to connect the MCP server:
Run one or more of these commands in your terminal:
```shell
claude mcp add loomi-connect-usa --transport http https://us.connect.loomi.ai/mcp
claude mcp add loomi-connect-europe --transport http https://eu.connect.loomi.ai/mcp
claude mcp add loomi-connect-uk --transport http https://uk.connect.loomi.ai/mcp
claude mcp add loomi-connect-canada --transport http https://ca.connect.loomi.ai/mcp
claude mcp add loomi-connect-apac --transport http https://ap.connect.loomi.ai/mcp
```
To verify the server was added, run:
```shell
claude mcp list
```
Refer to the [Claude Code documentation](https://code.claude.com/docs/en/mcp#configure-mcp-servers) for more details on MCP configuration.
Add the server(s) through Cursor's settings under MCP, or by editing `.cursor/mcp.json` for a single project or `~/.cursor/mcp.json` for all projects:
```json mcp.json
{
"mcpServers": {
"Loomi Connect USA": {
"url": "https://us.connect.loomi.ai/mcp"
},
"Loomi Connect Europe": {
"url": "https://eu.connect.loomi.ai/mcp"
},
"Loomi Connect United Kingdom": {
"url": "https://uk.connect.loomi.ai/mcp"
},
"Loomi Connect Canada": {
"url": "https://ca.connect.loomi.ai/mcp"
},
"Loomi Connect Asia Pacific": {
"url": "https://ap.connect.loomi.ai/mcp"
}
}
}
```
Restart Cursor after saving the file.
Refer to the [Cursor documentation](https://cursor.com/docs/mcp#installing-mcp-servers) for additional help.
Add the server(s) to the `.vscode/mcp.json` for a workspace, or to your user settings for all workspaces:
```json mcp.json
{
"mcp": {
"servers": {
"loomi-connect-usa": {
"type": "http",
"url": "https://us.connect.loomi.ai/mcp"
},
"loomi-connect-europe": {
"type": "http",
"url": "https://eu.connect.loomi.ai/mcp"
},
"loomi-connect-uk": {
"type": "http",
"url": "https://uk.connect.loomi.ai/mcp"
},
"loomi-connect-canada": {
"type": "http",
"url": "https://ca.connect.loomi.ai/mcp"
},
"loomi-connect-asia-pacific": {
"type": "http",
"url": "https://ap.connect.loomi.ai/mcp"
}
}
}
}
```
Reload the window after saving.
Learn more about adding MCP servers in the [VS Code documentation](https://code.visualstudio.com/docs/copilot/customization/mcp-servers).
### Custom Python MCP clients
If you build your own client with the official [`mcp` Python SDK](https://py.sdk.modelcontextprotocol.io/) against a Loomi Connect URL (`https://eu.connect.loomi.ai/mcp` and the other regional `/mcp` endpoints), pin the following in your dependencies:
```text
mcp>=1.9,<2
```
### Note
Claude Code, Cursor, VS Code, and Windsurf do not need a Python package pin. They use a built-in MCP HTTP client.
Unpinned installs resolve to `mcp` 2.x, which removes `streamablehttp_client` and fails with:
```shell
ImportError: cannot import name 'streamablehttp_client'
```
If you see this `ImportError`, pin `mcp>=1.9,<2` and retry. Do not treat it as a Loomi Connect outage.
### Important
The MCP SDK 2.x is a code migration, not a drop-in upgrade. It renamed the helper to `streamable_http_client` and changed HTTP client / OAuth types. See the [MCP Python SDK v1 to v2 migration guide](https://py.sdk.modelcontextprotocol.io/migration/). Loomi Connect has not certified SDK 2.x yet.
## Verify the connection
After restarting your AI application, confirm that Loomi Connect is registered and available in the project:
* In Claude Code, type `/mcp` in a new session.
* In Cursor, open the MCP settings panel (**File** > **Preferences** > **Cursor Settings** > **MCP**).
* In VS Code, open the Extensions tab to see installed MCP servers. You can also type `@mcp` in the command palette.
The first time your AI application calls a Loomi Connect tool, a browser window opens to the Bloomreach login page so you can authenticate. Sessions persist for up to 30 days.
## Next steps
* [**Authenticate MCP connection**](https://documentation.bloomreach.com/loomi-connect/docs/authenticate-mcp-connection)**:** sign in with your Bloomreach account and confirm your AI application can read live workspace data.