MCP Server

envpkt ships an MCP server that exposes credential metadata to AI agents. No secret values are ever exposed.

Configuration

Add envpkt to your MCP client config:

{
  "mcpServers": {
    "envpkt": {
      "command": "envpkt",
      "args": ["mcp"]
    }
  }
}

Starting the Server

envpkt mcp

Uses stdio transport. The server reads envpkt.toml from the current directory (or specify with -c).

Tools

Tool	Description
getPacketHealth	Get overall health status with per-secret audit results
listCapabilities	List agent and per-secret capabilities
getSecretMeta	Get metadata for a specific secret by key
checkExpiration	Check expiration status and days remaining

getPacketHealth

Returns the full audit result including overall status and per-secret health.

listCapabilities

Returns agent-level capabilities (from [agent].capabilities) and per-secret capabilities (from each [meta.KEY].capabilities).

getSecretMeta

Takes a secret key and returns its metadata (service, purpose, capabilities, expiration, rotation URL, etc.).

checkExpiration

Returns expiration status for all secrets, including days remaining and expired flags.

Resources

URI	Description
envpkt://health	Current credential health summary
envpkt://capabilities	Agent and secret capabilities

Security Model

The MCP server:

• Never exposes secret values
• Only shares metadata (service names, expiration dates, capabilities, rotation URLs)
• Reads from envpkt.toml which itself contains no secret values

This follows envpkt’s core principle: awareness, not access.

Library API

import { createServer, startServer, toolDefinitions, callTool, resourceDefinitions, readResource } from "envpkt"

// Tool definitions for MCP registration
const tools = toolDefinitions

// Call a tool
const result = callTool("getPacketHealth", {}, config, audit)

// Resource definitions
const resources = resourceDefinitions

// Read a resource
const data = readResource("envpkt://health", config, audit)