mcp-nervous-system 1.9.0 → 1.9.2

package/README.md

@@ -4,7 +4,7 @@
 
 7 mechanically enforced rules that prevent the most common failure modes when LLMs have access to real infrastructure: context loss, silent failures, file damage, goal drift, and overreach.
 
-Built by [Arthur Palyan](https://www.levelsofself.com) at Palyan Family AI System. 19 tools including configuration drift detection and emergency kill switch. Battle-tested on a 13-agent AI family running 29 processes 24/7 on a single VPS. 58+ violations logged, 0 bypassed.
+Built by [Arthur Palyan](https://www.levelsofself.com) at Palyan Family AI System. 21 tools including configuration drift detection and emergency kill switch. Battle-tested on a 13-agent AI family running 27 processes 24/7 on a single VPS. 58+ violations logged, 0 bypassed.
 
 ## The Problem
 
@@ -93,7 +93,7 @@ Configuration drift detection across 5 scopes: roles, versions, files, processes
 | 6 | **Ask Before Touching** | Unauthorized changes. Logic changes need human approval. |
 | 7 | **Hand Off** | Context loss. Written handoffs every 3-4 exchanges. |
 
-## MCP Tools (12)
+## MCP Tools (21)
 
 | Tool | Description |
 |------|------------|
@@ -143,7 +143,7 @@ https://api.100levelup.com/family/eu-ai-act.html
 
 ## Production Reference: Tamara
 
-Tamara is an autonomous AI operations manager built on the Nervous System framework. She manages 13 AI agents across 5 platforms, serving 175 countries from a $24/month VPS - without dedicated DevOps staff.
+Tamara is an autonomous AI operations manager built on the Nervous System framework. She manages 13 AI agents across 5 platforms, serving 175+ countries accessible from a $12/month VPS - without dedicated DevOps staff.
 
 Tamara is the proof that the Nervous System works in production. She runs 60-minute autonomous check cycles, detects configuration drift, dispatches remediation agents, and reports to the human operator only when judgment is needed.
 
@@ -168,10 +168,10 @@ From the live Palyan Family AI System deployment (Feb 28 - Mar 5, 2026):
 
 - **58+** violations caught
 - **29** edits blocked by preflight
-- **13** unique files protected
+- **100** files protected
 - **0** rules bypassed
-- **28** processes monitored
-- **7** days continuous operation
+- **27** processes monitored
+- **5** days continuous operation
 
 ## Live Demo
 
@@ -199,6 +199,12 @@ Works with the major multi-agent platforms and any MCP client:
 
 Each integration includes working code, example configs, and a step-by-step README.
 
+## Agent Skills
+
+The Nervous System is also available as an Agent Skill following the open [Agent Skills standard](https://agentskills.io). Install the governance skill to teach any AI agent (Claude, Codex, Cursor, Copilot, VS Code) how to enforce behavioral guardrails in multi-agent systems.
+
+See `skills/multi-agent-governance/SKILL.md` for the full skill definition.
+
 ## Philosophy
 
 > "LLMs can't reliably self-enforce promises. Guardrails work via preflight.sh, violation logs, and catching drift. Build enforcement systems, don't make promises."

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "mcp-nervous-system",
-  "version": "1.9.0",
+  "version": "1.9.2",
   "description": "Governance layer for multi-agent AI systems. 7 mechanically enforced rules, 19 tools including kill switch, audit chain, dispatch, drift audit, security audit, page health, pre-publish audit, and session close. Works with Ruflo, Hivemind, Agent Teams, and any MCP client.",
   "main": "server.js",
   "bin": {
@@ -43,5 +43,6 @@
   },
   "dependencies": {
     "@modelcontextprotocol/sdk": "^1.0.0"
-  }
+  },
+  "mcpName": "io.github.levelsofself/nervous-system"
 }

package/server.js

@@ -1147,7 +1147,7 @@ const NERVOUS_SYSTEM_INFO = {
     ]
   },
   stats: {
-    protected_files: '89+ untouchable files',
+    protected_files: '100 untouchable files',
     core_rules: 7,
     reflection_trigger: 'Every 4 messages',
     processes_managed: '22+ autonomous PM2 processes',

package/skills/multi-agent-governance/SKILL.md

@@ -0,0 +1,97 @@
+---
+name: multi-agent-governance
+description: "Use this skill when building, managing, or auditing multi-agent AI systems. Provides governance patterns for behavioral enforcement, drift detection, audit trails, role management, and accountability across autonomous AI agents. Compatible with any orchestration framework."
+license: Apache-2.0
+metadata:
+  author: palyan-family-ai
+  version: "1.0.0"
+  homepage: https://www.npmjs.com/package/@anthropic-ai/mcp-nervous-system
+  repository: https://github.com/anthropics/mcp-nervous-system
+---
+
+# Multi-Agent Governance
+
+Governance patterns for multi-agent AI systems. When you have multiple autonomous AI agents operating together, you need accountability, behavioral enforcement, and drift detection - just like human organizations.
+
+## Core Principles
+
+1. **Single source of truth** - One config file defines all agent roles. Every agent reads from it. No parallel systems.
+2. **Behavioral enforcement** - Rules are not suggestions. Guardrails are enforced through preflight checks, violation logging, and automated audits.
+3. **Drift detection** - Systems drift from their intended state over time. Automated drift audits catch configuration mismatches, version inconsistencies, and role conflicts before they cause failures.
+4. **Tamper-proof audit trails** - Every action, every change, every decision is logged in append-only logs that can be verified for integrity.
+5. **File-based memory** - Agent memory lives in files on disk, not in cloud databases. This enables air-gapped deployment, full auditability, and zero vendor dependency.
+
+## Governance Patterns
+
+### Role Management
+Define roles in a single JSON file that all agents reference:
+```json
+{
+  "agent-name": {
+    "role": "Operations Manager",
+    "scope": ["dispatch", "monitoring", "reporting"],
+    "access": "admin",
+    "model": "claude-opus-4-6"
+  }
+}
+```
+Every agent reads from this file at startup. Changes propagate automatically.
+
+### Preflight Checks
+Before any agent modifies a file:
+1. Check if the file is on the protected list
+2. If protected: log the attempt, report to admin, and STOP
+3. If allowed: create backup, make change, syntax check, restart affected process
+
+### Drift Audit Scopes
+Run periodic audits across these dimensions:
+- **roles** - Do running agents match their role definitions?
+- **versions** - Are all agents on the correct model version?
+- **files** - Have any protected files been modified?
+- **processes** - Are all expected processes running?
+- **config** - Do config files match expected state?
+
+### Session Management
+Every agent session should:
+1. Read the current system state before acting
+2. Write progress as it goes (no silent failures)
+3. Update handoff documentation before ending
+4. Run a drift audit on affected areas
+
+### Permission Protocol
+Two categories of changes:
+- **DATA** (values, content, configuration): Agent can act with general authorization
+- **LOGIC** (how something decides, classifies, responds): Agent PROPOSES and WAITS for human approval
+
+When in doubt, it is LOGIC. Ask the human.
+
+## Implementation
+
+### Using the Nervous System MCP
+The Nervous System is a Model Context Protocol server that implements these governance patterns with 19+ tools:
+
+```bash
+npm install -g @anthropic-ai/mcp-nervous-system
+```
+
+Tools include: drift_audit, security_audit, auto_propagate, session_close, preflight_check, violation_logging, and more.
+
+### DIY Implementation
+If building your own governance layer:
+1. Create a roles config file (JSON) as single source of truth
+2. Create a protected files list that agents check before editing
+3. Implement append-only logging for all agent actions
+4. Schedule periodic drift audits (compare expected vs actual state)
+5. Build a violation log that captures unauthorized changes
+
+## Anti-Patterns
+- Letting agents self-modify their own rules
+- Multiple sources of truth for the same data
+- Silent failures (agent encounters error but does not report it)
+- Manual fixes without adding automated detection
+- Hardcoding values that should come from config
+
+## Resources
+- [Nervous System MCP on npm](https://www.npmjs.com/package/@anthropic-ai/mcp-nervous-system)
+- [Agent Skills Specification](https://agentskills.io/specification)
+- [Model Context Protocol](https://modelcontextprotocol.io)

package/stdio.js

@@ -37,7 +37,7 @@ const TOOLS = [
   { name: "dispatch_to_llm", description: "Dispatch a task to a background Claude Code agent", schema: { type: "object", properties: { task: { type: "string", description: "Task description" }, max_turns: { type: "number", description: "Max turns (default 15)" } }, required: ["task"] } }
 ];
 
-const server = new Server({ name: "nervous-system", version: "1.1.1" }, { capabilities: { tools: {}, resources: {} } });
+const server = new Server({ name: "nervous-system", version: "1.9.0" }, { capabilities: { tools: {}, resources: {} } });
 
 server.setRequestHandler(ListToolsRequestSchema, async () => ({
   tools: TOOLS.map(t => ({ name: t.name, description: t.description, inputSchema: t.schema }))
@@ -48,10 +48,10 @@ server.setRequestHandler(CallToolRequestSchema, async (request) => {
   
   switch (name) {
     case "get_framework":
-      return { content: [{ type: "text", text: JSON.stringify({ name: "The Nervous System", version: "1.1.1", description: "LLM Behavioral Enforcement Framework", rules: RULES, total_tools: 11, production_stats: { violations_caught: 56, rules_bypassed: 0, edits_blocked: 32, processes_monitored: 22 } }, null, 2) }] };
+      return { content: [{ type: "text", text: JSON.stringify({ name: "The Nervous System", version: "1.9.0", description: "LLM Behavioral Enforcement Framework", rules: RULES, total_tools: 11, production_stats: { violations_caught: 58, rules_bypassed: 0, edits_blocked: 32, processes_monitored: 22 } }, null, 2) }] };
     
     case "get_nervous_system_info":
-      return { content: [{ type: "text", text: JSON.stringify({ name: "The Nervous System", version: "1.1.1", author: "Arthur Palyan", company: "Palyan Family AI System / Levels of Self LLC", website: "https://www.levelsofself.com", demo: "https://api.100levelup.com/family/arthur.html?guest=1", github: "https://github.com/levelsofself/mcp-nervous-system", npm: "https://www.npmjs.com/package/mcp-nervous-system", tools: 11, rules: 7, production_stats: { violations: 56, bypasses: 0, blocked_edits: 32, uptime_days: 25, monthly_cost: "$12" } }, null, 2) }] };
+      return { content: [{ type: "text", text: JSON.stringify({ name: "The Nervous System", version: "1.9.0", author: "Arthur Palyan", company: "Palyan Family AI System / Levels of Self LLC", website: "https://www.levelsofself.com", demo: "https://api.100levelup.com/family/arthur.html?guest=1", github: "https://github.com/levelsofself/mcp-nervous-system", npm: "https://www.npmjs.com/package/mcp-nervous-system", tools: 11, rules: 7, production_stats: { violations: 58, bypasses: 0, blocked_edits: 32, uptime_days: 25, monthly_cost: "$12" } }, null, 2) }] };
     
     case "check_preflight":
       const fp = args?.file_path || "unknown";
@@ -100,7 +100,7 @@ server.setRequestHandler(ReadResourceRequestSchema, async (request) => {
     return { contents: [{ uri, mimeType: "application/json", text: JSON.stringify(RULES, null, 2) }] };
   }
   if (uri === "ns://stats") {
-    return { contents: [{ uri, mimeType: "application/json", text: JSON.stringify({ violations: 56, bypasses: 0, blocked: 32, processes: 22, uptime_days: 25, version: "1.1.1" }, null, 2) }] };
+    return { contents: [{ uri, mimeType: "application/json", text: JSON.stringify({ violations: 58, bypasses: 0, blocked: 32, processes: 22, uptime_days: 25, version: "1.9.0" }, null, 2) }] };
   }
   return { contents: [{ uri, mimeType: "text/plain", text: "Unknown resource" }] };
 });