navagent_configure
Add a NavigationAgent3D under a parent (undoable) and set any of its steering/avoidance properties. Returns the new node's path and the resulting config (radius, height, max_speed, path/target desired distances, avoidance_enabled).
This record as markdown: /tools/breakpoint-mcp/navagent-configure.md
What navagent_configure does on Breakpoint
AI agents use navagent_configure to create or update resources in Breakpoint, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Breakpoint environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
name | string | — | Node name (default NavigationAgent3D) |
height | number | — | Agent height |
radius | number | — | Agent radius |
max_speed | number | — | Maximum movement speed |
parent_path | string | Yes | Parent node path relative to the scene root; "." for the root |
avoidance_enabled | boolean | — | Enable RVO avoidance |
path_desired_distance | number | — | Distance to a path point before advancing |
target_desired_distance | number | — | Distance to the target that counts as arrived |
Parameters from the server's own tool schema.
Why navagent_configure is rated Medium
This tool creates a new scene node and modifies its properties (steering/avoidance settings, radius, height, max_speed, etc.). These are reversible operations—the node can be deleted and properties can be changed back. The parenthetical '(undoable)' further confirms reversibility.
From the tool's definition Tool description states 'Add a NavigationAgent3D under a parent (undoable) and set any of its steering/avoidance properties.' The 'Add' operation creates a new node and modifies configuration properties.
Attacks that exploit this kind of access
The rule that runs navagent_configure safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Breakpoint, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For navagent_configure, this is the rule to start with:
navagent_configure stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Breakpoint, apply this rule, and every navagent_configure call is checked against it from then on.
Questions about navagent_configure
Add a NavigationAgent3D under a parent (undoable) and set any of its steering/avoidance properties. Returns the new node's path and the resulting config (radius, height, max_speed, path/target desired distances, avoidance_enabled). It is categorised as a Write tool in the Breakpoint MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
navagent_configure accepts 8 parameters: name, height, radius, max_speed, parent_path, avoidance_enabled, path_desired_distance, target_desired_distance. Required: parent_path. The full parameter table on this page comes from the server's own tool schema.
Register the Breakpoint MCP server in PolicyLayer and add a rule for navagent_configure: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Breakpoint. Nothing to install.
navagent_configure is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the navagent_configure rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for navagent_configure. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
navagent_configure is provided by the Breakpoint MCP server (breakpoint-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Breakpoint, and thousands of servers like it.
This server
Across the catalogue