deployhq
DeployHQ MCP Server
claude mcp add --transport stdio deployhq-deployhq-mcp-server npx -y deployhq-mcp-server \ --env LOG_LEVEL="INFO" \ --env DEPLOYHQ_EMAIL="your-email@example.com" \ --env DEPLOYHQ_ACCOUNT="your-account-name" \ --env DEPLOYHQ_API_KEY="your-api-key"
How to use
This DeployHQ MCP Server enables AI assistants such as Claude Desktop and Claude Code to interact with your DeployHQ account using the MCP protocol. It exposes seven tools that let you list projects, get project details, inspect servers and deployments, and create new deployments. The stdio transport is the primary method for Claude Desktop and Claude Code, but the server also supports SSE and HTTP transports if you host it for broader access. To use, configure Claude to point at the MCP server and provide DeployHQ credentials as environment variables so the server can authenticate with DeployHQ on your behalf. You can then issue natural-language requests like asking for a list of your DeployHQ projects, the servers for a given project, or to queue a new deployment, and Claude will translate those into the corresponding MCP tool calls.
How to install
Prerequisites:
- Node.js v18+ and npm or corepack installed
- Access to a terminal with internet access
Step-by-step installation:
- Ensure Node.js is installed:
ode --version
- Run the Deployment MCP server using npx (no global install required):
claude mcp add --transport stdio deployhq --env DEPLOYHQ_EMAIL=your-email@example.com --env DEPLOYHQ_API_KEY=your-api-key --env DEPLOYHQ_ACCOUNT=your-account -- npx -y deployhq-mcp-server
- If you prefer a manual setup with Claude Code, you can copy the provided configuration into your Claude config (see the README example) and start the server similarly:
npx -y deployhq-mcp-server
- Before first run, replace placeholder values in the environment variables with your actual DeployHQ credentials. Ensure your environment variables are accessible to the MCP server process.
Optional: To host the MCP server behind a web service (HTTP or SSE), consult your deployment environment’s guidance for exposing Node.js processes and, if needed, enable the corresponding transport in the server configuration.
Additional notes
Tips and considerations:
- Credentials are stored in environment variables only; never persist them to disk.
- The 3 required DeployHQ credentials are DEPLOYHQ_EMAIL, DEPLOYHQ_API_KEY, and DEPLOYHQ_ACCOUNT. LOG_LEVEL is optional and defaults to INFO.
- If you encounter authentication errors, double-check that your DeployHQ API key is valid and that the account name matches the DeployHQ URL (ACCOUNT).
- For debugging, set LOG_LEVEL=DEBUG to see more verbose API interactions.
- The MCP server supports multiple transports; switch to SSE or HTTP hosting if you need to expose the tools over a network rather than solely via stdio.
- Keep Node.js up to date to avoid compatibility issues with TypeScript and dependencies used by the MCP server.
Related MCP Servers
mcp-graphql
Model Context Protocol server for GraphQL
mcp-google-map
A powerful Model Context Protocol (MCP) server providing comprehensive Google Maps API integration with LLM processing capabilities.
systemprompt-code-orchestrator
MCP server for orchestrating AI coding agents (Claude Code CLI & Gemini CLI). Features task management, process execution, Git integration, and dynamic resource discovery. Full TypeScript implementation with Docker support and Cloudflare Tunnel integration.
pluggedin-app
The Crossroads for AI Data Exchanges. A unified, self-hostable web interface for discovering, configuring, and managing Model Context Protocol (MCP) servers—bringing together AI tools, workspaces, prompts, and logs from multiple MCP sources (Claude, Cursor, etc.) under one roof.
rohlik
MCP server that lets you shop groceries across the Rohlik Group platforms (Rohlik.cz, Knuspr.de, Gurkerl.at, Kifli.hu, Sezamo.ro)
mcp -js
MCP server that exposes YepCode processes as callable tools for AI platforms. Securely connect AI assistants to your YepCode workflows, APIs, and automations.