inputmap_add_action
Define a project input action (ProjectSettings input/<name>) with an empty event list and a deadzone. Set save=true to persist to project.godot. DESTRUCTIVE (project-wide input map) — gated by confirmation.
This record as markdown: /tools/breakpoint-mcp/inputmap-add-action.md
What inputmap_add_action does on Breakpoint
AI agents use inputmap_add_action 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 | Yes | Action name (without the input/ prefix) |
save | boolean | — | Persist to project.godot (default false) |
confirm | boolean | — | Auto-approve this destructive action (skip the confirmation prompt) |
deadzone | number | — | Analog deadzone 0..1 (default 0.5) |
Parameters from the server's own tool schema.
Why inputmap_add_action is rated Medium
This tool creates or modifies project input actions, which is a Write operation. Although the description uses the word 'DESTRUCTIVE' for emphasis (warning of project-wide impact), the operation itself is reversible—new actions can be removed or redefined. It does not delete or purge existing data.
From the tool's definition Tool description states 'Define a project input action' and 'Set save=true to persist to project.godot' — it creates or modifies input action definitions in the project configuration.
Attacks that exploit this kind of access
The rule that runs inputmap_add_action 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 inputmap_add_action, this is the rule to start with:
inputmap_add_action 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 inputmap_add_action call is checked against it from then on.
Questions about inputmap_add_action
Define a project input action (ProjectSettings input/<name>) with an empty event list and a deadzone. Set save=true to persist to project.godot. DESTRUCTIVE (project-wide input map) — gated by confirmation. 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.
inputmap_add_action accepts 4 parameters: name, save, confirm, deadzone. Required: name. 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 inputmap_add_action: 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.
inputmap_add_action 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 inputmap_add_action 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 inputmap_add_action. 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.
inputmap_add_action 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