gd_completion
Type-aware code completion at a position via the Godot language server. Returns at most max_results items (default 200) and sets truncated when the language server offered more.
This record as markdown: /tools/breakpoint-mcp/gd-completion.md
What gd_completion does on Breakpoint
AI agents use gd_completion 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 |
|---|---|---|---|
line | integer | Yes | 0-based line |
path | string | Yes | Script path (res://..., absolute, or project-relative) |
character | integer | Yes | 0-based character |
max_results | integer | — | Maximum completion items to return (default 200). Completion is the one verb whose result size is a function of project scope rather than of the cursor — one ca |
Parameters from the server's own tool schema.
Why gd_completion is rated Medium
An AI agent can call gd_completion faster than any human can review: one bad instruction and it creates or modifies resources in Breakpoint by the hundred, each call as confident as the last.
Risk signalsAccepts file system path (path)
Attacks that exploit this kind of access
The rule that runs gd_completion 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 gd_completion, this is the rule to start with:
gd_completion 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 gd_completion call is checked against it from then on.
Questions about gd_completion
Type-aware code completion at a position via the Godot language server. Returns at most max_results items (default 200) and sets truncated when the language server offered more. 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.
gd_completion accepts 4 parameters: line, path, character, max_results. Required: line, path, character. 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 gd_completion: 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.
gd_completion 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 gd_completion 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 gd_completion. 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.
gd_completion 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