gd_code_action
List the code actions (quick fixes / refactors) the language server offers for a range — the lightbulb menu. Read-only: returns the available actions (title, kind, whether each carries a WorkspaceEdit or a Command) without applying any. end_line/end_character default to the start position (a care...
This record as markdown: /tools/breakpoint-mcp/gd-code-action.md
What gd_code_action does on Breakpoint
AI agents call gd_code_action to retrieve information from Breakpoint without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
only | array | — | Restrict to these CodeActionKind prefixes, e.g. 'quickfix', 'refactor', 'source' |
path | string | Yes | Script path (res://..., absolute, or project-relative) |
end_line | integer | — | 0-based end line (default = start_line) |
start_line | integer | Yes | 0-based start line |
end_character | integer | — | 0-based end character (default = start_character) |
start_character | integer | Yes | 0-based start character |
Parameters from the server's own tool schema.
Why gd_code_action is rated Low
The tool only lists available code actions from the language server without executing or applying any of them. It is a pure query operation with no side effects.
From the tool's definition Read-only: returns the available actions (title, kind, whether each carries a WorkspaceEdit or a Command) without applying any.
Risk signalsAccepts file system path (path)
Attacks that exploit this kind of access
The rule that runs gd_code_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 gd_code_action, this is the rule to start with:
gd_code_action is read-only, so it stays allowed. 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_code_action call is checked against it from then on.
Questions about gd_code_action
List the code actions (quick fixes / refactors) the language server offers for a range — the lightbulb menu. Read-only: returns the available actions (title, kind, whether each carries a WorkspaceEdit or a Command) without applying any. end_line/end_character default to the start position (a caret, not a selection). It is categorised as a Read tool in the Breakpoint MCP Server, which means it retrieves data without modifying state.
gd_code_action accepts 6 parameters: only, path, end_line, start_line, end_character, start_character. Required: path, start_line, start_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_code_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.
gd_code_action is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the gd_code_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 gd_code_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.
gd_code_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