AI agents call function_source 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 source code information from a running Emacs instance. It performs a read-only introspection operation that retrieves data without modifying any state or executing code. The action is analogous to reading documentation or viewing source files, which are foundational Read operations. No data is created, modified, deleted, or executed as a result of calling this tool.
From the tool's definition Tool name 'function_source' and description 'Return the source code of a function or macro' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Return the source code of 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_source: 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_source 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_source 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_source. 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_source 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 →