Behavior Runtime Engine (behavior-mcp)
SkillWeb & browsingTeaches the agent to use the Behavior MCP server for ~60Hz in-browser behavior trees, triggers, and recordings.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Behavior Runtime Engine (behavior-mcp) skill
What this skill tells your AI
The instructions your AI receives, as published by putervision/world-model-mcp in .agents/skills/behavior-mcp/SKILL.md and read by ahel’s review.
This skill provides step-by-step guidance and operational patterns for interacting with @putervision/behavior-mcp with project slug "world-model-mcp".
1. Role in the PuterVision Pentad
- Workflow State (
state-memory-mcp): Persistent task DAGs, decisions, milestones, and blockers. - Perception (
vision-memory-mcp): Visual layout caching, screenshots, and visual specifications. - Spatial World (
world-model-mcp): Persistent 3D/2D coordinates, bounding boxes, and topological relations. - Strategic Reasoning (
agent-reasoning-mcp): Strategic BDI goals, utility scoring, and intention dispatch. - Tactical Execution (
behavior-mcp): High-frequency (~60Hz) deterministic behavior tree execution directly in browser runtimes with reactive interrupts.
2. Core Operational Sequence
- Define or Load Behavior: Call
load_behaviorwithaction: "load"to inject and start tree execution. - Register Reactive Triggers: Configure emergency preemption using
register_triggerwith priority and cooldown guards. - Monitor Telemetry: Poll execution health, tick rates, and active traversal nodes with
get_status. - Runtime Blackboard: Read and mutate execution variables via
manage_blackboard. - Safety Guardrails: Immediately halt or pause rogue states using
abort_behavior.
3. Complete 10 Consolidated MCP Tools Reference
| Tool Name | Key Actions | Key Parameters | Description |
|---|---|---|---|
load_behavior | load, unload, swap | behavior_name, behavior_version, parameters, intention_id | Hot-swap, inject, or initialize behavior tree instances in browser runtime. |
set_parameters | set, get, reset | execution_id, parameters | Dynamically update or query execution parameters for the active tree. |
get_status | current, history, tree_state | execution_id, limit | Query active behavior status, current node path, tick count, duration, and errors. |
abort_behavior | abort, pause, resume | execution_id, reason | Immediately halt, pause, or resume execution and disengage active inputs. |
register_trigger | register, list | name, condition_type, priority, cooldown_ms, behavior_name | Configure reactive interrupt triggers with priority preemption and cooldowns. |
replay_recording | capture, list | recording_id, execution_id, frames, name | Capture or replay deterministic browser action sequences with adaptive timing. |
get_metrics | current, history, aggregate, compare | execution_id, behavior_name, limit | Retrieve execution telemetry, tick durations, stuck events, and statistics. |
manage_behaviors | register, list, get | name, version, tree, tree_json, description | CRUD operations for immutable JSON behavior trees with SHA-256 tree hash verification. |
manage_blackboard | get, set | execution_id, key, value | Read or write shared behavior tree blackboard state variables. |
manage_runtime_db | stats, audit, snapshot, diff, restore | action, name, description | Database maintenance, diagnostics, and SHA-256 Merkle audit verification. |
Signals
- GitHub stars
- 16
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
behavior-mcp- Source
- github.com/putervision/world-model-mcp