MCP server for GitHub

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

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.
• Repository Management. Enables AI assistants to create repositories, forks, branches, search repositories, and view file contents.
• Issues and Pull Requests. Create issues, pull requests, comments, and manage them via natural language.
• Code Search and Repository Commits. Search code, users, and issues across all of GitHub, and list repository commits using an AI assistant.
• Bearer Token Authorization. All requests to the MCP server are protected with a Bearer token stored in Yandex Lockbox.
• Secure Secret Storage. The GitHub personal access token is stored in Yandex Lockbox and retrieved at startup.
• Standard MCP Protocol. Uses the open Model Context Protocol for AI model interaction.
• Streamable HTTP Transport. The MCP server is accessible on port 8000 (Streamable HTTP).
• Virtual Machine Configuration. The application runs on a virtual machine with a fixed configuration: 2 vCPUs and 2 GB of RAM.
• Docker Containerization. The server runs in Docker containers (MCP + supergateway + nginx auth proxy).

The connection to the MCP server uses unencrypted HTTP. The Bearer token authorizes requests but does not encrypt the connection. Use the internal MCP server URL and ensure network access to the VM. Do not send the Bearer token over the public HTTP endpoint.

1. Make sure you have a GitHub account.
2. Create a personal access token in GitHub with the necessary repository access permissions.
3. Create a secret in Yandex Lockbox to store the GitHub personal access token. The secret must contain a personal_access_token key with the token value.
4. 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.
5. Create a service account for deploying the application and assign it the roles compute.editor, iam.serviceAccounts.admin, and vpc.admin on the deployment folder.
6. Assign the installer service account the lockbox.admin role separately on the Bearer token secret and the external service credentials 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. In the management console select the Cloud Apps service.
8. In the left panel, select Application Store.
9. Select MCP GitHub and click the Use button.
10. 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.
    • Lockbox secret ID containing the GitHub personal access token.
    • External access to the MCP server (optional; disabled by default, enable for connections through the public IP address).
    • SSH access: select Disabled if you do not need SSH. If you select Enabled, provide a username and an SSH public key. Enabling SSH allows inbound connections to TCP port 22 from the internet.
11. Click the Install button and wait for the application to install.
12. After installation, copy the full URL from Application data, MCP server URL (internal): http://<private-ip>:8000/mcp. The client needs network access to the VM’s internal IP address.
13. Configure your AI client to connect to the MCP server, specifying the Authorization: Bearer <your-token> header.

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.

• Searching GitHub repositories using an AI assistant.
• Creating issues and pull requests via natural language.
• Viewing and analyzing file contents in repositories.
• Searching code, users, and GitHub issues; listing repository commits.
• Managing branches and repository forks through an AI assistant.

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.