devops-infra MCP Server
Build, run, and monitor AI/ML workflows from any agent. MCP server extension for Claude Code, Gemini CLI, Cursor, VS Code Copilot, and more.
Discovered via github-topic:mcp and last synced 3mo ago.
1. Install the package
npx -y jetty-mcp-server
2. Add to claude_desktop_config.json
{
"mcpServers": {
"jettyio-skills": {
"command": "npx",
"args": [
"jettyio-skills"
]
}
}
}Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) / %APPDATA%\Claude\claude_desktop_config.json (Windows)
List all collections (workspaces)
Run a workflow synchronously (blocks until done)
Basic LLM chat with system prompt
Create a new task with a workflow
Label a trajectory (e.g., quality=high)
Update a task's workflow or description
List tasks (workflows) in a collection
Get full run details with step outputs
Use Case
Text-to-image with Replicate/FLUX
Description
Run a workflow asynchronously
Description
Get collection details and environment variable keys
List recent workflow runs
Set or delete environment variables on a collection (merge semantics, pass `null` to delete a key)
Get task details and workflow definition
Fan-out parallel processing
Partial
List available step templates
URL
Full
Verify which env vars a collection has vs. what a runbook needs — returns configured, missing, and ready status
Configurable document summarization
Solution
Full
Compare two LLM responses with an AI judge
Full
Get template details and schema
Get execution statistics