elisp_eval · Ragmacs MCP: Risk & Policy

WHAT IT DOES

What elisp_eval does on Ragmacs

AI agents invoke elisp_eval to trigger actions in Ragmacs. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why elisp_eval needs a policy

This tool executes arbitrary Elisp code inside a running Emacs instance. Elisp has full access to the filesystem, network, shell commands, and all Emacs internals. An AI agent could use this to run shell commands, delete files, exfiltrate data, or perform any other action the Emacs process is permitted to do. This is the definition of arbitrary code execution with a critical blast radius.

From the tool's definition "Evaluate an arbitrary Elisp expression and return the result"

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

elisp_eval Rate-limited

elisp_eval stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "elisp_eval": {
      "limits": [
        {
          "counter": "elisp_eval_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Ragmacs, so you can run agents against it safely.

FAQ

Questions about elisp_eval

What does the elisp_eval tool do? +

Evaluate an arbitrary Elisp expression and return the result. It is categorised as a Execute tool in the Ragmacs MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on elisp_eval? +

Register the Ragmacs MCP server in PolicyLayer and add a rule for elisp_eval: 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.

What risk level is elisp_eval? +

elisp_eval is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit elisp_eval? +

Yes. Add a rate_limit block to the elisp_eval 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.

How do I block elisp_eval completely? +

Set action: deny in the PolicyLayer policy for elisp_eval. 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.

What MCP server provides elisp_eval? +

elisp_eval 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.