data-ai MCP Server
MCP server for reusable prompt templates, multi-step workflow chains, and quality gates. Compose agentic workflows with an operator syntax; export as native skills to Claude Code, Cursor, OpenCode, and Gemini CLI.
Discovered via github-topic:model-context-protocol and last synced 1w ago.
1. Install the package
npx -y claude-prompts@latest --client claude-code
2. Add to claude_desktop_config.json
{
"mcpServers": {
"claude-prompts-root": {
"command": "npx",
"args": [
"-y",
"claude-prompts@latest",
"--client",
"claude-code"
]
}
}
}Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) / %APPDATA%\Claude\claude_desktop_config.json (Windows)
5 min
`@`
Tries
Route step to agent
Create, update, version, and roll back resources
`~/.codeium/windsurf/mcp_config.json`
Execute template
Purpose
`~/.codex/config.toml`
Name
`#`
`~/.config/zed/settings.json` → `mcp` key
Pipe to next step
Execute prompts with frameworks and validation
Config Location
What happens
Toggle behavior
30s
Run prompt N times
Status, analytics, framework switching
10 min
`::`
Symbol
Unlocks