elfa_query · CG Alpha MCP: Risk & Policy

WHAT IT DOES

What elfa_query does on CG Alpha MCP

AI agents invoke elfa_query to trigger actions in CG Alpha MCP. 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 elfa_query needs a policy

A generic proxy that forwards arbitrary HTTP methods (GET, POST, PUT, DELETE, etc.) to any ELFA endpoint cannot be safely scoped to Read. Because it permits any method and any path, it can execute operations well beyond simple reads — including mutations and deletions. The most severe plausible category is Execute (potentially Destructive depending on what endpoints exist), so Execute at high severity is appropriate.

From the tool's definition "Generic ELFA proxy. Call any ELFA path with method/query/body." — arbitrary method, path, query, and body parameters mean this tool can trigger any ELFA API operation, including writes and destructive actions.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

elfa_query Rate-limited

elfa_query 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": {
    "elfa_query": {
      "limits": [
        {
          "counter": "elfa_query_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 CG Alpha MCP, so you can run agents against it safely.

FAQ

Questions about elfa_query

What does the elfa_query tool do? +

Generic ELFA proxy. Call any ELFA path with method/query/body. Returns JSON. It is categorised as a Execute tool in the CG Alpha MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on elfa_query? +

Register the CG Alpha MCP server in PolicyLayer and add a rule for elfa_query: 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 CG Alpha MCP. Nothing to install.

What risk level is elfa_query? +

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

Can I rate-limit elfa_query? +

Yes. Add a rate_limit block to the elfa_query 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 elfa_query completely? +

Set action: deny in the PolicyLayer policy for elfa_query. 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 elfa_query? +

elfa_query is provided by the CG Alpha MCP server (jcf0/cg-alpha-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.