Low Risk

compare_stems

compare_stems

How to control compare_stems ↓

What compare_stems does on Glyphs

AI agents call compare_stems 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.

Low Risk

Why compare_stems needs a policy

Based on naming convention and peer tools on the server, 'compare_stems' most likely performs a comparative analysis of font stem measurements — a read-only operation. However, confidence is moderate because the empty description prevents confirmation. The tool does not suggest code execution, data modification, deletion, or financial operations.

From the tool's definition Tool name 'compare_stems' suggests data retrieval/comparison operation. Description is empty, limiting evidentiary support.

Documented attack patterns abuse exactly the kind of access compare_stems gives an agent:

How to control compare_stems

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_stems:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "compare_stems": {}
  }
}

compare_stems is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Glyphs — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about compare_stems

What does the compare_stems tool do? +

compare_stems. It is categorised as a Read tool in the Glyphs MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on compare_stems? +

Register the Glyphs MCP server in PolicyLayer and add a rule for compare_stems: 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.

What risk level is compare_stems? +

compare_stems is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit compare_stems? +

Yes. Add a rate_limit block to the compare_stems 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.

How do I block compare_stems completely? +

Set action: deny in the PolicyLayer policy for compare_stems. 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.

What MCP server provides compare_stems? +

compare_stems 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.

Enforce policy on every Glyphs tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.