mcp-guardian 2.3.0 → 2.3.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +38 -0
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -88,6 +88,44 @@ if (pinResult.status === "changed") {
88
88
  }
89
89
  ```
90
90
 
91
+ ## Demo
92
+
93
+ Try mcp-guardian with the included poisoned server example:
94
+
95
+ ```bash
96
+ # Clone and run demo
97
+ git clone https://github.com/alexandriashai/mcp-guardian
98
+ cd mcp-guardian
99
+ npm install
100
+ cd examples/poisoned-server && npm install && cd ../..
101
+ npm run build
102
+ npm run demo
103
+ ```
104
+
105
+ Or scan the example config directly:
106
+
107
+ ```bash
108
+ npx mcp-guardian examples/demo-config.json
109
+ ```
110
+
111
+ **Expected output:**
112
+ ```
113
+ ✅ filesystem (14 tools)
114
+ ✅ memory (9 tools)
115
+ 🔴 suspicious-tool (4 tools)
116
+ └─ add: sensitive_path (~/.ssh)
117
+ └─ format_text: privilege_escalation ("You are now")
118
+ └─ search_docs: exfiltration (evil URL), sensitive_path (~/.aws/credentials)
119
+
120
+ Summary:
121
+ 📊 Total tools: 27
122
+ ✅ Clean: 2
123
+ ⚠️ Warning: 0
124
+ 🚨 Critical: 1
125
+ ```
126
+
127
+ The poisoned server demonstrates real attack patterns from published security research. See `examples/poisoned-server/README.md` for details.
128
+
91
129
  ## Detection Patterns
92
130
 
93
131
  ### Critical Severity (38 patterns)
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "mcp-guardian",
3
- "version": "2.3.0",
3
+ "version": "2.3.1",
4
4
  "description": "MCP security scanner - detect prompt injection in tool descriptions",
5
5
  "type": "module",
6
6
  "main": "dist/src/index.js",