A standardized framework for enhancing how LLMs process and respond to prompts through composable decorators, featuring an official open standard specification and Python reference implementation. Claude Code plugin and MCP server integration.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add prompt-decorators -- python -m prompt_decorators verify~/.codex/config.toml
[mcp_servers.prompt-decorators]
command = "python"
args = ["-m", "prompt_decorators", "verify"]
# codex mcp add prompt-decorators -- python -m prompt_decorators verify~/.cursor/mcp.json
{
"mcpServers": {
"prompt-decorators": {
"command": "python",
"args": [
"-m",
"prompt_decorators",
"verify"
]
}
}
}.vscode/mcp.json
{
"servers": {
"prompt-decorators": {
"type": "stdio",
"command": "python",
"args": [
"-m",
"prompt_decorators",
"verify"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"prompt-decorators": {
"command": "python",
"args": [
"-m",
"prompt_decorators",
"verify"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"prompt-decorators": {
"command": "python",
"args": [
"-m",
"prompt_decorators",
"verify"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"prompt-decorators": {
"command": "python",
"args": [
"-m",
"prompt_decorators",
"verify"
]
}
}
}