jamjet-labs/jamjet-policy
📇 🏠 🍎 🪟 🐧 - MCP stdio interceptor (@jamjet/mcp-shim) that applies one YAML policy file (block / requireapproval / audit / budget cap) to tools/call requests before they reach the real MCP server. The same policy also runs in Claude Code PreToolUse hooks (@jamjet/claude-code-hook), OpenAI Agents SDK guardrails (@jamjet/openai-guardrail), and JamJet's Python/TS SDKs — jamjet audit show tails every decision across every adapter from /.jamjet/audit/.
Quick Install
{
"mcpServers": {
"jamjet-labs-jamjet-policy": {
"command": "npx",
"args": [
"-y",
"jamjet-labs-jamjet-policy"
]
}
}
}Using an AI coding agent (Claude Code, Cursor, etc.)? Copy a ready-made prompt that tells it to fetch the setup instructions and install this server for you.
Documentation Overview
JamJet Policy
The portable policy layer for AI agent actions.
One policy file. One audit trail. Across hooks, guardrails, MCP gateways, SDKs, and custom runtimes.
Packages
@jamjet/claude-code-hook— JamJet policy as a Claude Code PreToolUse hook@jamjet/openai-guardrail— JamJet policy as an OpenAI Agents SDK guardrail@jamjet/mcp-shim— JamJet policy as an MCP stdio interceptor@jamjet/cli— Unifiedaudit show+approveacross all adapters
All four adapters share a single policy.yaml format and a single audit JSONL schema.
See conformance/ for the spec these adapters all satisfy.