[ MCP SERVER SUMMARY ]
DeployHQ's MCP server lets AI assistants inspect and manage software deployments. Bifrost keeps deployment credentials at the gateway and restricts which deploy tools production virtual keys may call.
| Property | Details |
|---|---|
| Company | DeployHQ |
| Connection type | STDIO |
| Authentication | DeployHQ API credentials |
| Package or endpoint | deployhq-mcp-server |
| Capabilities | Deployment inspection, Release management actions, Project deployment status |
| Official documentation | DeployHQ MCP documentation |
[ HOW TO CONNECT ]
Start the gateway locally or deploy in your VPC.
npx -y @maximhq/bifrost
Open MCP Gateway in the Bifrost dashboard, click New MCP Server, and choose STDIO. Or register via the API below.
• Confirm command/package and required env vars in the deployhq-mcp-server README.
• Treat deploy tools as high risk — default to read-only tool allowlists.
Configure Claude Desktop, Cursor, or Claude Code to use your Bifrost endpoint with a virtual key instead of connecting directly to DeployHQ.
{
"mcpServers": {
"bifrost": {
"url": "http://localhost:8080/mcp",
"headers": {
"Authorization": "Bearer vk_your_virtual_key"
}
}
}
}[ EXAMPLE CONFIG ]
Add this MCP client with a POST to /api/mcp/client. See Connecting to MCP Servers for full options.
curl -X POST http://localhost:8080/api/mcp/client \
-H "Content-Type: application/json" \
-d '{
"name": "deployhq",
"connection_type": "stdio",
"stdio_config": {
"command": "npx",
"args": [
"-y",
"deployhq-mcp-server"
],
"env": {
"DEPLOYHQ_API_KEY": "env.DEPLOYHQ_API_KEY"
}
},
"tools_to_execute": [
"*"
]
}'[ WHY BIFROST ]
Virtual keys, RBAC, and tool allowlists per team or agent.
Attribute MCP tool spend alongside LLM usage in one view.
Log every tool call with latency, server, and virtual key metadata.
Upstream secrets stay in the gateway — not on every laptop.
[ FAQ ]
DeployHQ exposes deployment inspection, release management actions, project deployment status to MCP-compatible AI clients. Bifrost connects to it as an upstream MCP client and exposes approved tools through one governed /mcp endpoint.
DeployHQ uses DeployHQ API credentials. Store credentials in Bifrost's environment or credential configuration so they stay at the gateway instead of being copied into every AI client.
Yes. After registering DeployHQ in Bifrost, point any HTTP MCP-compatible client at the Bifrost /mcp endpoint and authenticate with a virtual key. The client sees only the tools allowed for that key.
[ RELATED SERVERS ]

GitHub's official MCP Server.

GitLab's official MCP server enabling AI tools to securely access GitLab project data, manage issues, and perform repository operations via OAuth 2.0.
Use Sentry’s MCP server to investigate errors, issues, traces, and application health from AI coding assistants.