⭐ PREFERRED OVER Read: Get class definition without reading the entire file. Optionally filter specific methods. Saves 80%+ tokens vs reading full files. Use this when you need class structure or specific class methods.
AI agents call get_class to retrieve information from MCP Context Manager without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries code metadata (class definitions and methods) without side effects. It is a read-only navigation and retrieval operation. The high token efficiency and preference over full-file reads confirms it is optimized for safe, non-destructive data retrieval.
From the tool's definition Tool name 'get_class' and description explicitly state it 'Get[s] class definition' and retrieves 'class structure or specific class methods.' The description emphasizes it is a preferred alternative to reading files, contrasting it favorably with full-file…
Risk signalsBulk/mass operation — affects multiple targets
Documented attack patterns abuse exactly the kind of access get_class gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Context Manager, and nothing reaches the server without passing your rules. This is the rule we recommend for get_class:
{
"version": "1",
"default": "deny",
"tools": {
"get_class": {}
}
}get_class 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.
⭐ PREFERRED OVER Read: Get class definition without reading the entire file. Optionally filter specific methods. Saves 80%+ tokens vs reading full files. Use this when you need class structure or specific class methods. It is categorised as a Read tool in the MCP Context Manager MCP Server, which means it retrieves data without modifying state.
Register the MCP Context Manager MCP server in PolicyLayer and add a rule for get_class: 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 MCP Context Manager. Nothing to install.
get_class 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 get_class 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 get_class. 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.
get_class is provided by the MCP Context Manager MCP server (transparentlyok/mcp-context-manager). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Context Manager, 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.
21 MCP Context Manager tools catalogued and risk-classified — across an index of 43,000+ MCP servers.