AI agents call compare_color to retrieve information from Glyphs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name 'compare_color' most likely performs a read-only comparison of color properties in font glyphs, consistent with sibling tools like 'analyze_kerning' and 'analyze_spacing' which are analytical/read operations. However, confidence is reduced because the description is empty and we cannot definitively confirm the tool does not have side effects.
From the tool's definition Tool name 'compare_color' suggests a comparison operation; server description indicates 'read and write font data' capabilities. Name suggests data retrieval/comparison rather than modification.
Documented attack patterns abuse exactly the kind of access compare_color gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Glyphs, and nothing reaches the server without passing your rules. This is the rule we recommend for compare_color:
{
"version": "1",
"default": "deny",
"tools": {
"compare_color": {}
}
}compare_color is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
compare_color. It is categorised as a Read tool in the Glyphs MCP Server, which means it retrieves data without modifying state.
Register the Glyphs MCP server in PolicyLayer and add a rule for compare_color: 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 Glyphs. Nothing to install.
compare_color 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 compare_color 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 compare_color. 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.
compare_color is provided by the Glyphs MCP server (nmassi/glyphs-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Glyphs, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
41 Glyphs tools catalogued and risk-classified — across an index of 43,000+ MCP servers.