AI agents call symbol_manual_section 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 documentation references for Emacs symbols—purely informational lookup with no side effects. It does not modify state, execute code, delete data, or commit financial actions. The sibling tool 'elisp_eval' would be Execute/Destructive depending on arguments, but this tool itself only returns references to existing manual sections.
From the tool's definition Tool name 'symbol_manual_section' and description 'Return the manual section that documents a given symbol' indicate data retrieval with no modification or execution. It queries documentation metadata.
Attacks that exploit this kind of access
Return the manual section that documents a given symbol. 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_manual_section: 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_manual_section 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_manual_section 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_manual_section. 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_manual_section 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 →