AI agents call variable_completions 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 retrieves matching variable names from Emacs' internal state based on a prefix pattern. It has no side effects—it only reads and returns completion candidates for display or filtering purposes. This is a classic Read operation similar to autocomplete/search functionality.
From the tool's definition Tool name 'variable_completions' and description 'Return all variables matching a prefix' indicate a query/retrieval operation. The verb 'return' and context of completion suggestion confirms data retrieval with no modification, deletion, or code execution.
Attacks that exploit this kind of access
Return all variables matching a prefix using orderless. 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 variable_completions: 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.
variable_completions 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 variable_completions 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 variable_completions. 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.
variable_completions 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 →