MCP server for Redis

MCP server for Redis is an application that provides AI assistants with access to Redis databases via the standard Model Context Protocol (MCP). The server is deployed on a virtual machine in Yandex Cloud and connects to an existing Redis cluster.

Key Features and Benefits

• Yandex AI Studio Integration. The MCP server integrates with AI Studio MCP Servers — connect it to your AI agents in just a few clicks.
• AI Assistant Integration. Enables AI models to perform Redis operations: read and write data, manage keys, and analyze database structure.
• Bearer Token Authorization. All requests to the MCP server are protected with a Bearer token stored in Yandex Lockbox.
• Secure Redis Connection. The Redis connection password is stored in Yandex Lockbox and retrieved at startup. TLS support for encrypted connections. Optional CA certificate from Certificate Manager for Redis connections that require one.
• Standard MCP Protocol. Uses the open Model Context Protocol for AI model interaction, ensuring compatibility with a wide range of clients.
• HTTP Transport. The MCP server is accessible on port 8000 (HTTP), simplifying integration with various clients and tools.
• Minimal Resources. The application runs on a virtual machine with minimal configuration (2 vCPU, 2 GB RAM), reducing infrastructure costs.

1. Make sure you have a running Redis cluster: Yandex Managed Service for Valkey^™ or another Redis deployment.
2. Create a secret in Yandex Lockbox to store the Redis password. The secret must contain a redis_password key with the password value.
3. Create a secret in Yandex Lockbox to store the Bearer token for authorization. The secret must contain a bearer_token key with an arbitrary token value.
4. (Optional) If the Redis connection requires an additional CA certificate, upload a certificate to Yandex Certificate Manager.
5. Create a service account for deploying the application and assign it the roles compute.editor, iam.serviceAccounts.admin, vpc.admin, and resource-manager.admin on the deployment folder.
6. Assign the installer service account the lockbox.admin role separately on the Bearer token secret and the Redis password secret. This role is required to read and modify access permissions on the selected secrets; no folder-level Lockbox role is required. This also applies to secrets in another folder. During installation, the application creates a dedicated VM service account and grants it lockbox.payloadViewer only on the selected secrets.
7. The template also grants the VM service account certificate-manager.certificates.downloader on the deployment folder. The installer needs resource-manager.admin to create this IAM binding, even when no custom certificate is selected. If using a certificate, select one from the deployment folder; for a certificate in another folder, grant the VM account access to it separately.
8. In the management console select the Cloud Apps service.
9. In the left panel, select Application Store.
10. Select MCP Redis and click the Use button.
11. Specify:
    • Application name.
    • (Optional) Application description.
    • The service account created earlier.
    • The cloud subnet where the virtual machine will be deployed.
    • Lockbox secret ID containing the Bearer token for authorization.
    • TLS for the Redis connection: disabled by default. If Redis supports TLS, select Enabled and specify its port.
    • (Optional) With TLS enabled, select an additional CA certificate from Certificate Manager if the connection requires one.
    • Redis host (FQDN).
    • Redis port. If you leave this field empty, the application uses port 6379. TLS is configured separately.
    • Redis username. If you leave this field empty, the application uses the username default.
    • Lockbox secret ID containing the Redis password.
    • External access to the MCP server (optional; disabled by default, enable for connections through the public IP address).
    • SSH access settings. If you select Enabled, specify the username and SSH public key.
12. Click the Install button and wait for the application to install.
13. After installation, select the connection address under Application data:
    • To connect from an external network, use MCP server URL: http://<public-ip>:8000/mcp. The VM has a public IP address and TCP port 8000 is accessible from the internet only when external access is enabled, so use a Bearer token and share the URL only with trusted clients.
    • To connect from an internal network, use MCP server URL (internal): http://<private-ip>:8000/mcp. The client needs network access to the VM’s internal IP address. Yandex AI Studio uses this private address.
14. Configure your AI client to connect to the MCP server, specifying the Authorization: Bearer <your-token> header.
15. Check the MCP server: list its available tools, use them to write a temporary Redis key, and read it back. Confirm that the value matches what you wrote, then delete the test key.

Connecting the MCP server to Yandex AI Studio

1. In the management console open AI Studio and go to Agent Core → MCP servers.
2. Click Create MCP server and select the required MCP server under MCP servers from Yandex Cloud Marketplace.
3. Specify the server name and select an existing application instance, or create a new one by following the deployment instructions. When deploying a new server, the Save button becomes available only after the MCP server has been fully deployed and started.
4. After you select the application, the MCP server’s Network and Service account settings are filled in automatically.
5. Click Create. After the connection has been verified successfully, select the required tools and click Save. The MCP server will be registered in AI Studio and available for use by AI agents.

• Managing keys and values in Redis using an AI assistant.
• Analyzing data structure and key types in Redis via natural language.
• Monitoring Redis server and replication status with AI.
• Automating routine Redis operations through an AI assistant.
• Exploring and debugging data stored in Redis.

Yandex Cloud technical support is available 24/7. The types of requests you can submit and the appropriate response time depend on your pricing plan. You can switch to the paid support plan in the management console. You can learn more about the technical support terms here.