by deployhq
DeployHQ MCP Server: reliable deployment server for continuous deployment — automate builds, tests and releases with a p
Connects AI assistants to DeployHQ to manage deployments, view project details, and monitor deployment logs through the DeployHQ API.
deployhq-mcp-server is an official MCP server published by deployhq that provides AI assistants with tools and capabilities via the Model Context Protocol. DeployHQ MCP Server: reliable deployment server for continuous deployment — automate builds, tests and releases with a p It is categorized under developer tools.
You can install deployhq-mcp-server in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
MIT
deployhq-mcp-server is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
Add new capabilities to Claude beyond text generation
Example
Access external data sources, execute code, interact with tools and services
Transform Claude from chatbot to action-taking agent
Provide Claude with access to relevant context and data
Example
Load project documentation, access knowledge bases, query databases
Get more accurate, context-aware responses
Automate multi-step workflows combining AI and external tools
Example
Research → Summarize → Create document → Send notification
Complete complex tasks end-to-end without manual steps
Share your MCP server with the developer community
deployhq-mcp-server is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.
Strong directory entry: deployhq-mcp-server surfaces stars and publisher context so we could sanity-check maintenance before adopting.
deployhq-mcp-server reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
We wired deployhq-mcp-server into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
Useful MCP listing: deployhq-mcp-server is the kind of server we cite when onboarding engineers to host + tool permissions.
deployhq-mcp-server is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
deployhq-mcp-server reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
deployhq-mcp-server has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
According to our notes, deployhq-mcp-server benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
Useful MCP listing: deployhq-mcp-server is the kind of server we cite when onboarding engineers to host + tool permissions.
showing 1-10 of 48
A Model Context Protocol (MCP) server for DeployHQ that enables AI assistants like Claude Desktop and Claude Code to interact with your DeployHQ deployments.
npx - no installation requiredThe MCP server provides 7 tools for AI assistants:
| Tool | Description | Parameters |
|---|---|---|
list_projects | List all projects | None |
get_project | Get project details | permalink |
list_servers | List project servers | project |
list_deployments | List deployments with pagination | project, page?, server_uuid? |
get_deployment | Get deployment details | project, uuid |
get_deployment_log | Get deployment log output | project, uuid |
create_deployment | Create new deployment | project, parent_identifier, start_revision, end_revision, + optional params |
list_projectsList all projects in your DeployHQ account.
Returns: Array of projects with repository information and deployment status.
get_projectGet detailed information about a specific project.
Parameters:
permalink (string): Project permalink or identifierlist_serversList all servers configured for a project.
Parameters:
project (string): Project permalinklist_deploymentsList deployments for a project with pagination support.
Parameters:
project (string): Project permalinkpage (number, optional): Page number for paginationserver_uuid (string, optional): Filter by server UUIDget_deploymentGet detailed information about a specific deployment.
Parameters:
project (string): Project permalinkuuid (string): Deployment UUIDget_deployment_logGet the deployment log for a specific deployment. Useful for debugging failed deployments.
Parameters:
project (string): Project permalinkuuid (string): Deployment UUIDReturns: Complete deployment log as text
create_deploymentCreate a new deployment for a project.
Parameters:
project (string): Project permalinkparent_identifier (string): Server or server group UUIDstart_revision (string): Starting commit hashend_revision (string): Ending commit hashbranch (string, optional): Branch to deploy frommode (string, optional): "queue" or "preview"copy_config_files (boolean, optional): Copy config filesrun_build_commands (boolean, optional): Run build commandsuse_build_cache (boolean, optional): Use build cacheuse_latest (string, optional): Use latest deployed commit as startThe fastest way to install for Claude Code:
claude mcp add --transport stdio deployhq --env [email protected] --env DEPLOYHQ_API_KEY=your-api-key --env DEPLOYHQ_ACCOUNT=your-account -- npx -y deployhq-mcp-server
Replace [email protected], your-api-key, and your-account with your actual DeployHQ credentials.
The same configuration works for both clients. Copy from docs/claude-config.json and add your credentials.
For Claude Desktop:
Edit your config file:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.jsonThen restart Claude Desktop.
For Claude Code:
Add to your .claude.json file in your project directory.
Configuration:
{
"mcpServers": {
"deployhq": {
"command": "npx",
"args": ["-y", "deployhq-mcp-server"],
"env": {
"DEPLOYHQ_EMAIL": "[email protected]",
"DEPLOYHQ_API_KEY": "your-password",
"DEPLOYHQ_ACCOUNT": "your-account-name"
// Optional: "LOG_LEVEL": "INFO" (ERROR, INFO, or DEBUG)
}
}
}
}
Note: Only the 3 DeployHQ credentials are required. LOG_LEVEL is optional and defaults to INFO.
Once configured, you can ask Claude to interact with DeployHQ:
User: What's the status of my latest deployment for my-app?
Claude: [Uses list_deployments → get_deployment → shows status]
User: Why did the last deployment fail for my-app?
Claude: [Uses list_deployments → get_deployment_log → analyzes log]
User: Deploy the latest changes to production for my-app
Claude: [Uses list_servers → list_deployments → create_deployment with use_latest]
User: I want to deploy my-app to production with the latest changes
Claude will:
1. Use list_projects to find "my-app"
2. Use list_servers to find production server UUID
3. Use list_deployments with use_latest to get last revision
4. Use create_deployment to queue deployment
5. Use get_deployment to show status
6. Use get_deployment_log if anything fails
DEPLOYHQ_EMAIL: Your DeployHQ login emailDEPLOYHQ_API_KEY: Your DeployHQ password/API keyDEPLOYHQ_ACCOUNT: Your DeployHQ account name (from URL: https://ACCOUNT.deployhq.com)LOG_LEVEL: Controls log verbosity - ERROR, INFO, or DEBUG (default: INFO)NODE_ENV: Environment mode - production or developmentControl verbosity with the LOG_LEVEL environment variable:
Example:
{
"mcpServers": {
"deployhq": {
"command": "npx",
"args": ["-y", "deployhq-mcp-server"],
"env": {
"DEPLOYHQ_EMAIL": "[email protected]",
"DEPLOYHQ_API_KEY": "your-password",
"DEPLOYHQ_ACCOUNT": "your-account-name",
"LOG_LEVEL": "DEBUG"
}
}
}
}
Problem: Server exits immediately after starting
Solutions:
node --versionLOG_LEVEL=DEBUG for more detailsProblem: "Authentication failed" or 401/403 errors
Solutions:
Problem: "Project not found" or 404 errors
Solutions:
list_projects to see exact permalink formatProblem: "Server is running in read-only mode" error when trying to create deployments
Solution:
DEPLOYHQ_READ_ONLY=false in your environment variables--read-only=false CLI flagProblem: Deployment created but fails immediately
Solutions:
get_deployment_log to see detailed error logslist_serversProblem: "Request timeout" errors
Solutions:
curl https://YOUR_ACCOUNT.deployhq.comProblem: Not seeing any log output
Solutions:
~/Library/Logs/Claude/%APPDATA%\Claude\logs\LOG_LEVEL=DEBUG for verbose outputhttps://ACCOUNT.deployhq.com)┌─────────────────┐ ┌─────────────┐
│ Claude Desktop │ stdio/JSON-RPC │ DeployHQ │
│ or Claude Code │◄──────────────────►│ API │
│ │ (via npx) │ │
│ Environment │ │ │
│ Variables ─────┼───────────────────►│ Basic Auth │
└─────────────────┘ └─────────────┘
npxNote: The server uses node-fetch for HTTP requests. Node 18+ is required for development tools (ESLint, Vitest).
Prerequisites
Time Estimate
15-60 minutes depending on server complexity
Steps
Troubleshooting
✓ Do
✗ Don't
💡 Pro Tips
Architecture
Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.
Protocols
Compatibility
✓ Use when
Use when you need Claude to access external data, execute actions, or integrate with tools. Best for extending AI capabilities beyond conversation.
✗ Avoid when
Avoid when native integrations exist (use official APIs directly), for real-time critical systems, or when security/compliance requires zero external dependencies.