assert_visual_match
Assert that a screenshot matches a baseline within a threshold - pass/fail result
This record as markdown: /tools/keeveeg-godot-mcp/assert-visual-match.md
What assert_visual_match does on Godot
AI agents use assert_visual_match to create or update resources in Godot, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Godot environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
name | string | Yes | Screenshot name to check — must match a name previously used with take_screenshot_with_context |
baseline | string | Yes | Path or name of the baseline screenshot (resolves against baselines directory if not a full path) |
threshold | number | — | Acceptable difference threshold (default: 0.01) |
Parameters from the server's own tool schema.
Why assert_visual_match is rated Medium
An AI agent can call assert_visual_match faster than any human can review: one bad instruction and it creates or modifies resources in Godot by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
The rule that runs assert_visual_match 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 assert_visual_match, this is the rule to start with:
assert_visual_match 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 Godot, apply this rule, and every assert_visual_match call is checked against it from then on.
Questions about assert_visual_match
Assert that a screenshot matches a baseline within a threshold - pass/fail result. It is categorised as a Write tool in the Godot MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
assert_visual_match accepts 3 parameters: name, baseline, threshold. Required: name, baseline. 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 assert_visual_match: 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.
assert_visual_match 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 assert_visual_match 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 assert_visual_match. 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.
assert_visual_match is provided by the Godot MCP server (@keeveeg/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