Set the CSS framework to use for all subsequent operations. Choose based on your project
AI agents use set_framework to create or update resources in Classmcp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Classmcp environment.
This tool creates or modifies configuration state reversibly. It changes which CSS framework is active for the session, affecting all subsequent tool outputs (generate_css, get_class, etc.). This is a reversible write operation — an AI could set it to an incorrect framework, causing wrong CSS suggestions, but the operation can be undone by calling set_framework again.
From the tool's definition Tool description states 'Set the CSS framework to use for all subsequent operations' — this modifies configuration state that affects downstream behavior.
Documented attack patterns abuse exactly the kind of access set_framework gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Classmcp, and nothing reaches the server without passing your rules. This is the rule we recommend for set_framework:
{
"version": "1",
"default": "deny",
"tools": {
"set_framework": {
"limits": [
{
"counter": "set_framework_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}set_framework 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 the CSS framework to use for all subsequent operations. Choose based on your project. It is categorised as a Write tool in the Classmcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Class MCP server in PolicyLayer and add a rule for set_framework: 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 Classmcp. Nothing to install.
set_framework 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_framework 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_framework. 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_framework is provided by the Class MCP server (thedecipherist/classmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Classmcp, 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.
10 Classmcp tools catalogued and risk-classified — across an index of 43,000+ MCP servers.