mcpField
B
Behavior Runtime MCP

Behavior Runtime MCP

Local
behaviormcp.comAI & Agents7Updated 4w ago

About Behavior Runtime MCP

Behavior Runtime MCP is an in-browser behavior-tree execution engine for AI agents, with deterministic operation at about 60 Hz, reactive triggers, and audit records. It provides tools for runtime state, blackboards, and behavior management, alongside layered safety controls.

Key features

  1. 01In-browser behavior-tree execution at about 60 Hz
  2. 02Reactive triggers with priority preemption
  3. 03Capture and inspect deterministic replays
  4. 04Query runtime status, metrics, and blackboard
  5. 05Manage behavior trees and Merkle audits
  6. 06Safety limits and emergency halt

Use cases

  1. 01Run AI-agent behavior trees in a browser runtime
  2. 02Interrupt or pause behavior on triggers
  3. 03Inspect runtime state and blackboard variables
  4. 04Audit execution records and restore checkpoints

MCP support

The MCP server exposes tools to load and control behavior trees, register triggers, inspect runtime status and metrics, and manage blackboards and the runtime database.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"putervision-behavior": {
"command": "npx",
"args": [
"-y",
"@putervision/behavior-mcp"
]
}
}
}
Run commandnpx -y @putervision/behavior-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@putervision/behavior-mcp0.4.1

Tools

10

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
actionenumYesBehavior loading operation: load, unload, swapload | unload | swap
projectstringNoTarget project slug
trace_idstringNoDistributed trace ID for cross-server correlation
intentionobjectNoOptional linked intention payload matching the dispatch token
parametersobjectNoInitial execution parameters
session_idstringNoLinked state-memory session ID
intention_idstringNoLinked agent-reasoning intention ID
behavior_namestringYesName of the behavior tree to load
dispatch_tokenobjectNoCryptographically signed dispatch token issued by agent-reasoning-mcp (gate_intention)
dispatch_token.audstringNo
dispatch_token.token_idstringNo
dispatch_token.issued_atstringNo
dispatch_token.expires_atstringNo
dispatch_token.params_hashstringNo
dispatch_token.intention_idstringNo
dispatch_token.behavior_namestringNo
dispatch_token.hmac_signaturestringNo
behavior_versionnumberNoVersion of behavior tree (defaults to latest)
client_request_idstringNoIdempotency key

Details

From the project README

@putervision/behavior-mcp

npm version version CI Node License: 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 • 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

ToolActionsPurpose
load_behaviorload, unload, swapInject, initialize, or hot-swap a behavior tree in browser runtime
set_parametersset, get, resetDynamically update or query runtime execution parameters
get_statuscurrent, history, tree_stateQuery active status, node traversal path, tick count, duration
abort_behaviorabort, pause, resumeHalt, pause, or resume behavior execution safely
register_triggerregister, listConfigure reactive interrupt triggers with priority preemption
replay_recordingcapture, listCapture or inspect deterministic browser action sequences
get_metricscurrent, historyRetrieve runtime telemetry, tick durations, and stuck events
manage_behaviorsregister, get, listCRUD for immutable behavior tree JSON with SHA-256 tree hashes
manage_blackboardget, setRead, write, or query shared behavior tree blackboard variables
manage_runtime_dbstats, audit, snapshot, restoreSQLite diagnostics, SHA-256 Merkle audit, and checkpoint rollback

🛡️ 5-Layer Safety Guardrail Stack & System 1 Invariants

  1. Fail-Closed Evaluator: Unrecognized node definitions throw fatal exceptions immediately.
  2. 60Hz Tick Invariant & Synchronous semantic_check: The loop never blocks on external network calls; semantic condition checks resolve synchronously against blackboard caches.
  3. HMAC Intention Gate Verification: Intentions dispatched to execution nodes require unexpired, cryptographically signed dispatch tokens (PENTAD_HMAC_SECRET).
  4. Action Rate Limiter & Leaf Policy Gate: Strict 60 actions/sec maximum throughput ceiling and policy guardrails blocking irreversible mutations.
  5. Emergency Kill Switch & Watchdog Heartbeat: Atomic safety latch and watchdog timers halting execution if tick stalls beyond 5,000ms.

📚 Deep Documentation Guides


🔗 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

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.