MCP Server

Active

MIT

Behavior Runtime MCP MCP Server

io.github.putervision/behavior-mcp

High-frequency (~60Hz) in-browser behavior tree execution engine with reactive triggers and safety guardrails for AI agents.

Repository Registry

What is the Behavior Runtime MCP MCP server?

The Behavior Runtime MCP is a Model Context Protocol server that executes deterministic behavior trees directly in browser runtimes at ~60Hz with reactive trigger preemption, frame recordings, and a 5-layer safety guardrail stack. It provides tools for loading, managing, and monitoring behavior tree execution with cryptographic audit trails and emergency kill switches.

This server enables AI agents to run tactical behavior trees in-browser at high frequency with built-in safety mechanisms. It's useful for applications requiring deterministic, auditable execution of complex decision trees with reactive interrupt handling, real-time telemetry, and strict rate limiting to prevent unintended actions.

How to install Behavior Runtime MCP

Copy-paste configuration for popular MCP clients.

transport: stdio

Config generated by PluginBench — verify against the source before use.

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "behavior-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@putervision/behavior-mcp"
      ]
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

load_behavior — Inject, initialize, or hot-swap a behavior tree in browser runtime
set_parameters — Dynamically update or query runtime execution parameters
get_status — Query active status, node traversal path, tick count, and execution duration
abort_behavior — Halt, pause, or resume behavior execution safely
register_trigger — Configure reactive interrupt triggers with priority preemption
replay_recording — Capture or inspect deterministic browser action sequences
get_metrics — Retrieve runtime telemetry, tick durations, and stuck events
manage_behaviors — CRUD for immutable behavior tree JSON with SHA-256 tree hashes
manage_blackboard — Read, write, or query shared behavior tree blackboard variables
manage_runtime_db — SQLite diagnostics, SHA-256 Merkle audit, and checkpoint rollback

Use cases

Execute deterministic behavior trees in-browser at 60Hz with full audit trails for safety-critical AI agent tasks
Implement reactive interrupt handling and priority-based trigger preemption for dynamic behavior switching
Monitor real-time execution metrics, tick durations, and stuck events to debug behavior tree performance
Capture and replay deterministic action sequences for testing and validation of agent behavior
Enforce strict action rate limits and cryptographic intention verification to prevent unintended mutations

Behavior Runtime MCP MCP server FAQ

What is the Behavior Runtime MCP server?

It's an MCP server that executes behavior trees in-browser at ~60Hz with reactive triggers, safety guardrails, cryptographic audit trails, and deterministic frame recording for AI agents.

Is it free?

Yes, it is licensed under MIT and available on npm as @putervision/behavior-mcp.

How do I install it in Cursor or Claude?

Add it to .cursor/mcp.json or .vscode/mcp.json with command 'behavior-mcp' and args ['run'], setting PENTAD_HMAC_SECRET as an environment variable.

What safety features does it include?

It has a 5-layer safety stack: fail-closed evaluator, 60Hz tick invariant, HMAC intention gate verification, action rate limiter (60 actions/sec max), and emergency kill switch with watchdog heartbeat.

Does it require authentication?

It requires a PENTAD_HMAC_SECRET environment variable for cryptographic intention gate verification, but no external service authentication.

What are the system requirements?

Node.js >= 20.0.0 is required to run the server.

README (reference)

Source of truth, from the repository.

@putervision/behavior-mcp

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 • Interactive Web Docs

⚡ 15-Second Quick Start

# 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 & System 1 Invariants

Fail-Closed Evaluator: Unrecognized node definitions throw fatal exceptions immediately.
60Hz Tick Invariant & Synchronous semantic_check: The loop never blocks on external network calls; semantic condition checks resolve synchronously against blackboard caches.
HMAC Intention Gate Verification: Intentions dispatched to execution nodes require unexpired, cryptographically signed dispatch tokens (PENTAD_HMAC_SECRET).
Action Rate Limiter & Leaf Policy Gate: Strict 60 actions/sec maximum throughput ceiling and policy guardrails blocking irreversible mutations.
Emergency Kill Switch & Watchdog Heartbeat: Atomic safety latch and watchdog timers halting execution if tick stalls beyond 5,000ms.

📚 Deep Documentation Guides

📖 Formal API Reference: Full parameter tables, type definitions, and tool schemas.
💡 Core Architecture & Concepts: Behavior tree execution model, ~60Hz loop, and trigger lifecycle.
🖥️ CLI Usage Guide: Complete CLI command reference (init, doctor, inspect, run).
💾 Database Schema: SQLite table structures, indexes, and Merkle audit ledger.
⚙️ Configuration Reference: .behavior-mcp.json parameters and environment variables.

🔗 Client Configuration & Environment

Add to .cursor/mcp.json or .vscode/mcp.json:

{
  "mcpServers": {
    "behavior-mcp": {
      "command": "behavior-mcp",
      "args": ["run"],
      "env": {
        "PENTAD_HMAC_SECRET": "your-secure-shared-secret-here"
      }
    }
  }
}

🧪 Testing

# Run full unit and integration test suite across 38 test files (266 tests)
npm test

📄 License

MIT © PuterVision

Related MCP servers

State Memory MCP

Active

Deterministic, persistent SQLite graph for AI agents to track workflow state, decisions, and blockers with zero infrastructure.

TypeScript

MIT

View repository →

Visual Memory MCP

Active

Local visual UI cache for AI agents using perceptual hashing and CLIP to reduce vision token costs.

TypeScript

View repository →

WebCrypt MCP Server

Maintained

Zero-dependency Web Crypto MCP server with AES-256-GCM, RSA-4096, and post-quantum cryptography for AI agents.

JavaScript

MIT

View repository →

World Model MCP

Active

Persistent 3D/2D spatial world model for AI agents with entity tracking, collision simulation, and durable memory.

TypeScript

MIT

View repository →

io.github.putput-io-dev/putput-mcp

Maintained

File uploads for AI agents. Upload, list, and manage files. No signup required.

JavaScript

View repository →

Image Generation MCP Server

Active

MCP server for AI image generation via OpenAI, Stable Diffusion (SD WebUI), or placeholders.

Python

MIT

View repository →