gd_semantic_tokens
Return the semantic-highlighting tokens for a whole script — each token's position, length, type (e.g. function, variable, keyword) and modifiers — decoded from the LSP packed-integer form through the server's advertised legend. Read-only. Godot's GDScript language server does not advertise seman...
This record as markdown: /tools/breakpoint-mcp/gd-semantic-tokens.md
What gd_semantic_tokens does on Breakpoint
AI agents call gd_semantic_tokens 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 |
|---|---|---|---|
path | string | Yes | Script path (res://..., absolute, or project-relative) |
Parameters from the server's own tool schema.
Why gd_semantic_tokens is rated Low
This tool purely retrieves and decodes LSP semantic token information for display/analysis purposes. It has no side effects, performs no modifications, and cannot affect the state of any data or system. The explicit "Read-only" designation confirms its non-destructive nature.
From the tool's definition Tool description states "Return the semantic-highlighting tokens" and explicitly marks it as "Read-only". It retrieves syntax highlighting metadata without modifying any data.
Risk signalsAccepts file system path (path)
Attacks that exploit this kind of access
The rule that runs gd_semantic_tokens 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_semantic_tokens, this is the rule to start with:
gd_semantic_tokens 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_semantic_tokens call is checked against it from then on.
Questions about gd_semantic_tokens
Return the semantic-highlighting tokens for a whole script — each token's position, length, type (e.g. function, variable, keyword) and modifiers — decoded from the LSP packed-integer form through the server's advertised legend. Read-only. Godot's GDScript language server does not advertise semanticTokensProvider through 4.7; feature-detected. It is categorised as a Read tool in the Breakpoint MCP Server, which means it retrieves data without modifying state.
gd_semantic_tokens accepts 1 parameter: path. Required: 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 gd_semantic_tokens: 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_semantic_tokens 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_semantic_tokens 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_semantic_tokens. 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_semantic_tokens 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