⚡ High-frequency (~60Hz) in-browser behavior tree execution engine for autonomous AI agents. Reactive priority interrupts, safety guardrails & deterministic action replay over MCP.
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
claude mcp add behavior-mcp -- npx -y @putervision/behavior-mcp{
"mcpServers": {
"behavior-mcp": {
"command": "npx",
"args": ["-y", "@putervision/behavior-mcp"]
}
}
}MCP Servers overview
# @putervision/behavior-mcp
[](https://www.npmjs.com/package/@putervision/behavior-mcp)
[](https://github.com/putervision/behavior-mcp/actions/workflows/ci.yml)
[](https://nodejs.org)
[](https://opensource.org/licenses/MIT)
> **High-Frequency (~60Hz) In-Browser Behavior Tree Tactical Runtime Engine for AI Agents**
`@putervision/behavior-mcp` is a Model Context Protocol (MCP) server that executes deterministic behavior trees directly in browser runtimes at ~60Hz with reactive trigger preemption, frame recordings, SHA-256 Merkle audit chains, and a 5-layer safety guardrail stack.
🌐 **Official Documentation**: [putervision.com](https://putervision.com) • [Interactive Web Docs](docs/index.html)
---
## ⚡ 15-Second Quick Start
```bash
# 1. Initialize runtime & seed default behavior trees in your workspace
npx @putervision/behavior-mcp init
# 2. Run system diagnostic and health checks
npx @putervision/behavior-mcp doctor
# 3. Inspect active executions, blackboard state, and reactive triggers
npx @putervision/behavior-mcp inspect
```
---
## 🛠️ 10 Core MCP Tools
| Tool | Actions | Purpose |
|------|---------|---------|
| `load_behavior` | `load`, `unload`, `swap` | Inject, initialize, or hot-swap a behavior tree in browser runtime |
| `set_parameters` | `set`, `get`, `reset` | Dynamically update or query runtime execution parameters |
| `get_status` | `current`, `history`, `tree_state` | Query active status, node traversal path, tick count, duration |
| `abort_behavior` | `abort`, `pause`, `resume` | Halt, pause, or resume behavior execution safely |
| `register_trigger` | `register`, `list` | Configure reactive interrupt triggers with priority preemption |
| `replay_recording` | `capture`, `list` | Capture or inspect deterministic browser action sequences |
| `get_metrics` | `current`, `history` | Retrieve runtime telemetry, tick durations, and stuck events |
| `manage_behaviors` | `register`, `get`, `list` | CRUD for immutable behavior tree JSON with SHA-256 tree hashes |
| `manage_blackboard` | `get`, `set` | Read, write, or query shared behavior tree blackboard variables |
| `manage_runtime_db` | `stats`, `audit`, `snapshot`, `restore` | SQLite diagnostics, SHA-256 Merkle audit, and checkpoint rollback |
---
## 🛡️ 5-Layer Safety Guardrail Stack
1. **Fail-Closed Evaluator**: Unrecognized node definitions throw fatal exceptions immediately.
2. **Watchdog Heartbeat Timer**: Halts execution if tick evaluation stalls beyond 5,000ms.
3. **Action Rate Limiter**: Strict 60 actions/sec maximum throughput ceiling.
4. **Leaf Policy Gate**: Blocks irreversible, high-risk mutations (`delete_item`, `spend_currency`).
5. **Emergency Kill Switch**: Atomic safety latch (`EmergencySafety.engageKillSwitch()`) halts all runtimes.
---
## 📚 Deep Documentation Guides
- 📖 **[Formal API Reference](docs/api-reference.md)**: Full parameter tables, type definitions, and tool schemas.
- 💡 **[Core Architecture & Concepts](docs/concepts.md)**: Behavior tree execution model, ~60Hz loop, and trigger lifecycle.
- 🖥️ **[CLI Usage Guide](docs/cli-usage.md)**: Complete CLI command reference (`init`, `doctor`, `inspect`, `run`).
- 💾 **[Database Schema](docs/database-schema.md)**: SQLite table structures, indexes, and Merkle audit ledger.
- ⚙️ **[Configuration Reference](docs/configuration.md)**: `.behavior-mcp.json` parameters and environment variables.
---
## 🔗 Client Configuration
Add to `.cursor/mcp.json` or `.vscode/mcp.json`:
```json
{
"mcpServers": {
"behavior-mcp": {
"command": "behavior-mcp",
"args": ["run"]
}
}
}
```
---
## 🧪 Testing
```bash
# Run full unit and integration test suite across 15 test files (87 tests)
npm test
```
---
## 📄 License
MIT © PuterVision
What people ask about behavior-mcp
What is putervision/behavior-mcp?
+
putervision/behavior-mcp is mcp servers for the Claude AI ecosystem. ⚡ High-frequency (~60Hz) in-browser behavior tree execution engine for autonomous AI agents. Reactive priority interrupts, safety guardrails & deterministic action replay over MCP. It has 2 GitHub stars and its last recorded update is dated 2026-09-10.
How do I install behavior-mcp?
+
You can install behavior-mcp by cloning the repository (https://github.com/putervision/behavior-mcp) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is putervision/behavior-mcp safe to use?
+
Our security agent has analyzed putervision/behavior-mcp and assigned a Trust Score of 95/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains putervision/behavior-mcp?
+
putervision/behavior-mcp is maintained by putervision. The last recorded GitHub activity is dated 2026-09-10, with 0 open issues.
Are there alternatives to behavior-mcp?
+
Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.
Deploy behavior-mcp to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/putervision-behavior-mcp)<a href="https://claudewave.com/repo/putervision-behavior-mcp"><img src="https://claudewave.com/api/badge/putervision-behavior-mcp" alt="Featured on ClaudeWave: putervision/behavior-mcp" width="320" height="64" /></a>More MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
The fastest path to AI-powered full stack observability, even for lean teams.
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!