AI agents use set_glyph_paths to create or update resources in Glyphs — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Glyphs environment.
This tool modifies glyph path data in a font file, which is a reversible write operation. While not destructive (paths can be undone/reverted), setting glyph paths alters the core visual design of a typeface. The severity is high because incorrect path modifications could render glyphs unusable or corrupt font integrity, and an AI agent with unconstrained access could systematically degrade an entire font's quality.
From the tool's definition Tool name 'set_glyph_paths' combined with server description stating it 'lets Claude, Cursor, or any MCP client read and write font data directly in GlyphsApp' indicates modification of glyph outline data.
Documented attack patterns abuse exactly the kind of access set_glyph_paths 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 set_glyph_paths:
{
"version": "1",
"default": "deny",
"tools": {
"set_glyph_paths": {
"limits": [
{
"counter": "set_glyph_paths_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}set_glyph_paths 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.
Free to start. No card required.
set_glyph_paths. It is categorised as a Write tool in the Glyphs MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Glyphs MCP server in PolicyLayer and add a rule for set_glyph_paths: 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.
set_glyph_paths 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 set_glyph_paths 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 set_glyph_paths. 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.
set_glyph_paths 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.