AI agents call symbol_exists 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 the Emacs symbol table (obarray) to determine existence of a symbol. It retrieves information without creating, modifying, deleting, or executing any code. The return value (symbol name or nil) is purely informational. Even in the context of an Emacs introspection server, checking symbol existence is a safe read operation with minimal blast radius if misused by an agent.
From the tool's definition Tool checks if a symbol exists in obarray and returns symbol name or nil. The verb "check" and the query nature (returns data, no modification) indicate a read-only operation. Description explicitly states it returns a value without side effects.
Attacks that exploit this kind of access
Check if a symbol exists in obarray. Returns symbol name or nil. 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 symbol_exists: 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.
symbol_exists 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 symbol_exists 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 symbol_exists. 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.
symbol_exists 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 →