⭐ PREFERRED OVER Read: Get complete function code without reading the entire file. Saves 85% tokens compared to Read. Use when you need a specific function implementation instead of reading full files. Returns only the function definition with signature.
AI agents call get_function 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 queries and retrieves specific function implementations from a codebase. It has no capability to modify, delete, execute, or create data—it only fetches and returns function definitions. The low severity reflects that unauthorized access would primarily expose source code without enabling further malicious actions through this tool alone.
From the tool's definition Tool retrieves function code without side effects. Description states 'Get complete function code' and 'Returns only the function definition with signature.' The emphasis on being 'PREFERRED OVER Read' and saving tokens confirms it is a read-only retrieval…
Documented attack patterns abuse exactly the kind of access get_function 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_function:
{
"version": "1",
"default": "deny",
"tools": {
"get_function": {}
}
}get_function 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 complete function code without reading the entire file. Saves 85% tokens compared to Read. Use when you need a specific function implementation instead of reading full files. Returns only the function definition with signature. 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_function: 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_function 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_function 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_function. 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_function 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.