mcpwall 0.1.0 → 0.1.2

package/README.md

@@ -1,8 +1,13 @@
 # mcpwall
 
-Deterministic security proxy for [MCP](https://modelcontextprotocol.io) tool calls. Sits between your AI coding tool (Claude Code, Cursor, Windsurf) and MCP servers, intercepting every JSON-RPC message and enforcing YAML-defined policies — no LLM, no cloud, pure rule-based.
+[![npm version](https://img.shields.io/npm/v/mcpwall)](https://www.npmjs.com/package/mcpwall)
+[![CI](https://github.com/behrensd/mcp-firewall/actions/workflows/ci.yml/badge.svg)](https://github.com/behrensd/mcp-firewall/actions/workflows/ci.yml)
+[![Node.js](https://img.shields.io/node/v/mcpwall)](https://nodejs.org)
+[![License: FSL-1.1-ALv2](https://img.shields.io/badge/license-FSL--1.1--ALv2-blue)](./LICENSE)
 
-Think **iptables**, but for MCP tool calls.
+**iptables for MCP.** Blocks dangerous tool calls, scans for secret leakage, logs everything. No AI, no cloud, pure rules.
+
+Sits between your AI coding tool (Claude Code, Cursor, Windsurf) and MCP servers, intercepting every JSON-RPC message and enforcing YAML-defined policies.
 
 ## Why
 
@@ -30,7 +35,37 @@ npx mcpwall -- npx -y @modelcontextprotocol/server-filesystem /path/to/dir
 
 ## Quick Start
 
-### Option 1: Interactive setup
+### Option 1: Docker MCP Toolkit
+
+If you use [Docker MCP Toolkit](https://docs.docker.com/ai/mcp-catalog-and-toolkit/toolkit/) (the most common setup), change your MCP config from:
+
+```json
+{
+  "mcpServers": {
+    "MCP_DOCKER": {
+      "command": "docker",
+      "args": ["mcp", "gateway", "run"]
+    }
+  }
+}
+```
+
+To:
+
+```json
+{
+  "mcpServers": {
+    "MCP_DOCKER": {
+      "command": "npx",
+      "args": ["-y", "mcpwall", "--", "docker", "mcp", "gateway", "run"]
+    }
+  }
+}
+```
+
+That's it. mcpwall now sits in front of all your Docker MCP servers, logging every tool call and blocking dangerous ones. No config file needed — sensible defaults apply automatically.
+
+### Option 2: Interactive setup
 
 ```bash
 npx mcpwall init
@@ -38,7 +73,7 @@ npx mcpwall init
 
 This finds your existing MCP servers in `~/.claude.json` or `.mcp.json` and wraps them.
 
-### Option 2: Manual wrapping
+### Option 3: Manual wrapping (any MCP server)
 
 Change your MCP config from:
 
@@ -69,7 +104,7 @@ To:
 }
 ```
 
-### Option 3: Wrap a specific server
+### Option 4: Wrap a specific server
 
 ```bash
 npx mcpwall wrap filesystem
@@ -79,7 +114,7 @@ npx mcpwall wrap filesystem
 
 ```
 ┌──────────────┐    stdio     ┌──────────────┐    stdio     ┌──────────────┐
-│  Claude Code │ ──────────▶  │ MCP Firewall │ ──────────▶  │  Real MCP    │
+│  Claude Code │ ──────────▶  │   mcpwall    │ ──────────▶  │  Real MCP    │
 │  (MCP Host)  │ ◀──────────  │   (proxy)    │ ◀──────────  │   Server     │
 └──────────────┘              └──────────────┘              └──────────────┘
 ```
@@ -203,7 +238,7 @@ Options:
 
 ## Audit Logs
 
-Logs are written as JSON Lines to `~/.mcpwall/logs/YYYY-MM-DD.jsonl`:
+All tool calls are logged by default — both allowed and denied. Logs are written as JSON Lines to `~/.mcpwall/logs/YYYY-MM-DD.jsonl`:
 
 ```json
 {"ts":"2026-02-16T14:30:00Z","method":"tools/call","tool":"read_file","action":"allow","rule":null}
@@ -212,6 +247,8 @@ Logs are written as JSON Lines to `~/.mcpwall/logs/YYYY-MM-DD.jsonl`:
 
 Denied entries have args redacted to prevent secrets from leaking into logs.
 
+mcpwall also prints color-coded output to stderr so you can see decisions in real time.
+
 ## Security Design
 
 - **Fail closed on invalid config**: Bad regex in a rule crashes at startup, never silently passes traffic

package/dist/index.js

@@ -577,9 +577,8 @@ var Logger = class {
       case "deny":
         return "warn";
       case "ask":
-        return "info";
       case "allow":
-        return "debug";
+        return "info";
       default:
         return "info";
     }

package/package.json

@@ -1,10 +1,10 @@
 {
   "name": "mcpwall",
-  "version": "0.1.0",
+  "version": "0.1.2",
   "description": "Deterministic security proxy for MCP tool calls — iptables for MCP. Blocks dangerous tool calls, scans for secret leakage, logs everything. No AI, no cloud, pure rules.",
   "type": "module",
   "bin": {
-    "mcpwall": "./dist/index.js"
+    "mcpwall": "dist/index.js"
   },
   "files": [
     "dist",
@@ -32,9 +32,10 @@
   "license": "FSL-1.1-Apache-2.0",
   "repository": {
     "type": "git",
-    "url": "https://github.com/behrensd/mcp-firewall.git"
+    "url": "git+https://github.com/behrensd/mcp-firewall.git"
   },
-  "homepage": "https://github.com/behrensd/mcp-firewall",
+  "mcpName": "io.github.behrensd/mcpwall",
+  "homepage": "https://mcpwall.dev",
   "bugs": {
     "url": "https://github.com/behrensd/mcp-firewall/issues"
   },