AI agents call function_documentation to retrieve information from Ragmacs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns documentation strings from a running Emacs instance. It performs a read-only introspection of function metadata without modifying, executing, or deleting any data. The operation is non-destructive and informational in nature, fitting the Read category profile of tools that retrieve or query data without side effects.
From the tool's definition Tool is named 'function_documentation' and explicitly described as 'Return the docstring for a function or macro' — a retrieval operation with no side effects.
Attacks that exploit this kind of access
Return the docstring for a function or macro. It is categorised as a Read tool in the Ragmacs MCP Server, which means it retrieves data without modifying state.
Register the Ragmacs MCP server in PolicyLayer and add a rule for function_documentation: 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 Ragmacs. Nothing to install.
function_documentation 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 function_documentation 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 function_documentation. 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.
function_documentation is provided by the Ragmacs MCP server (landermkerbey/ragmacs-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →