read_game_log
Read the Godot engine log written by a game run (user://logs/godot.log). Filter by severity (error/warning/script/shader) or regex; tail or head N lines. NOTE: editor sessions never write log files, only actual game runs do.
This record as markdown: /tools/yanhuifair-godot-mcp/read-game-log.md
What read_game_log does on Godot
AI agents call read_game_log to retrieve information from Godot 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 |
|---|---|---|---|
file | object | — | Read a specific log file name from the log directory instead of the newest one (see list_game_logs). |
level | object | — | Filter by severity. "error" also matches SCRIPT/SHADER ERROR. Continuation lines (" at: ...") are kept. |
lines | object | — | How many lines to return (default 200). Use 0 for the whole file. |
pattern | object | — | Only return lines matching this regular expression (applied after the level filter). |
from_start | object | — | Return the FIRST N lines instead of the last N (default: tail). |
Parameters from the server's own tool schema.
Why read_game_log is rated Low
Tool retrieves game logs without modifying data or executing commands. Non-invasive information access.
From the tool's definition Read the Godot engine log; Filter by severity or regex; tail or head N lines.
Risk signalsAccepts file system path (file)
Attacks that exploit this kind of access
The rule that runs read_game_log safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Godot, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For read_game_log, this is the rule to start with:
read_game_log 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 Godot, apply this rule, and every read_game_log call is checked against it from then on.
Questions about read_game_log
Read the Godot engine log written by a game run (user://logs/godot.log). Filter by severity (error/warning/script/shader) or regex; tail or head N lines. NOTE: editor sessions never write log files, only actual game runs do. It is categorised as a Read tool in the Godot MCP Server, which means it retrieves data without modifying state.
read_game_log accepts 5 parameters: file, level, lines, pattern, from_start. The full parameter table on this page comes from the server's own tool schema.
Register the Godot MCP server in PolicyLayer and add a rule for read_game_log: 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 Godot. Nothing to install.
read_game_log 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 read_game_log 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 read_game_log. 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.
read_game_log is provided by the Godot MCP server (@yanhuifair/godot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Godot, and thousands of servers like it.
This server
Across the catalogue