shroud-privacy 2.5.0 → 2.5.2

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.
package/README.md CHANGED
@@ -119,6 +119,27 @@ Verify after a conversation:
119
119
  cat ~/.hermes/shroud-stats.json | python3 -m json.tool
120
120
  ```
121
121
 
122
+ ### Claude Code
123
+
124
+ ```bash
125
+ npm install shroud-privacy
126
+ ```
127
+
128
+ Add to your project's `.mcp.json` or `~/.claude/.mcp.json`:
129
+
130
+ ```json
131
+ {
132
+ "mcpServers": {
133
+ "shroud": {
134
+ "command": "node",
135
+ "args": ["node_modules/shroud-privacy/clients/claude-code/shroud-mcp.mjs"]
136
+ }
137
+ }
138
+ }
139
+ ```
140
+
141
+ That's it — the MCP server auto-starts the privacy engine. Claude gains six tools: `shroud_obfuscate`, `shroud_deobfuscate`, `shroud_status`, `shroud_scan_tool`, `shroud_configure`, and `shroud_reset`.
142
+
122
143
  ### Any agent (via APP)
123
144
 
124
145
  The **Agent Privacy Protocol** (APP) lets any AI agent add privacy and infrastructure protection — no OpenClaw required. Shroud ships with an APP server and a Python client.
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "id": "shroud-privacy",
3
3
  "name": "Shroud",
4
- "version": "2.5.0",
4
+ "version": "2.5.2",
5
5
  "description": "Privacy obfuscation with deterministic fake values and deobfuscation — PII never reaches the LLM, tool calls still work",
6
6
  "configSchema": {
7
7
  "type": "object",
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "shroud-privacy",
3
- "version": "2.5.0",
3
+ "version": "2.5.2",
4
4
  "description": "Privacy and infrastructure protection for AI agents — detects sensitive data (PII, network topology, credentials, OT/SCADA) and replaces with deterministic fakes before anything reaches the LLM.",
5
5
  "type": "module",
6
6
  "main": "dist/index.js",