context_gc · ContextGC MCP: Risk & Policy

WHAT IT DOES

What context_gc does on ContextGC

AI agents invoke context_gc to trigger actions in ContextGC. 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 context_gc needs a policy

context_gc triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

context_gc Rate-limited

context_gc 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": {
    "context_gc": {
      "limits": [
        {
          "counter": "context_gc_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 ContextGC, so you can run agents against it safely.

FAQ

Questions about context_gc

What does the context_gc tool do? +

Trigger context garbage collection. This clears cached file skeletons that are no longer needed, freeing context window space. Use this when you notice context is getting full or after completing a task branch. It is categorised as a Execute tool in the ContextGC MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on context_gc? +

Register the ContextGC MCP server in PolicyLayer and add a rule for context_gc: 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 ContextGC. Nothing to install.

What risk level is context_gc? +

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

Can I rate-limit context_gc? +

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

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

context_gc is provided by the ContextGC MCP server (superzavier/contextgc-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.