// MCP TOOL REFERENCE

ctx_purge

DESTRUCTIVE: permanently delete indexed content. Cannot be undone. Requires confirm:true and exactly one scope. WHEN: - User explicitly asks to clear a specific session (

ServerContext Mode
CategoryDestructive

How to control ctx_purge ↓

WHAT IT DOES

What ctx_purge does on Context Mode

AI agents call ctx_purge to permanently remove resources in Context Mode — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

THE RISK

Critical Risk

Why ctx_purge needs a policy

This tool irreversibly deletes indexed content without recovery options. Although it requires confirmation and scope specification (safety guards), the core operation is permanent data destruction. The high severity reflects that an AI agent misusing this could permanently lose critical indexed context or documentation.

From the tool's definition Tool description explicitly states 'DESTRUCTIVE: permanently delete indexed content. Cannot be undone.' The name 'ctx_purge' and the word 'purge' both indicate irreversible deletion.

Documented attack patterns abuse exactly the kind of access ctx_purge gives an agent:

POLICY

How to control ctx_purge

PolicyLayer is an MCP gateway — it sits between your AI agents and Context Mode, and nothing reaches the server without passing your rules. This is the rule we recommend for ctx_purge:

policy.json

{
  "version": "1",
  "default": "deny",
  "hide": [
    "ctx_purge"
  ]
}

ctx_purge disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

Create a free account and register Context Mode — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RESTRICT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Context Mode tools

Execute ctx_batch_execute Run multiple commands in ONE call. Every command Execute ctx_execute Run code in a sandboxed subprocess.${RB} Languages: ${PB}. Think-in-Code \u2014 the core Execute ctx_execute_file Read a file into a sandboxed FILE_CONTENT variable and run code over it. Only what you con Execute ctx_insight Opens the context-mode Insight dashboard in the browser \u2014 a dashboard launcher for se Execute ctx_upgrade Upgrade context-mode to the latest version. Returns a shell command to execute. You MUST r Write ctx_index Store content in a searchable knowledge base (BM25 over FTS5). Splits markdown by headings Write ctx_fetch_and_index Fetches URL content, converts HTML to markdown (JSON is chunked by key paths, plain text i Read ctx_doctor Diagnose context-mode installation. Runs all checks server-side and returns a plain-text s

All 11 Context Mode tools →

Destructive tools on other servers

Android Forensics ADB MCP Server create_full_backup 0xarchive web3_revoke_key Frida Game Hacking MCP clear_scan cPanel MCP Server clear_spam_box

Go deeper

Critical-risk tools in Context Mode → Every critical-risk tool this server exposes, in one view.
All critical-risk MCP tools → Every critical-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Blast radius → How much damage one compromised or confused agent can do — and how to bound it.
Tool call approval → Approval gates on individual tool calls: auto-allow, prompt, or deny.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about ctx_purge

What does the ctx_purge tool do? +

DESTRUCTIVE: permanently delete indexed content. Cannot be undone. Requires confirm:true and exactly one scope. WHEN: - User explicitly asks to clear a specific session (. It is categorised as a Destructive tool in the Context Mode MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on ctx_purge? +

Register the Context Mode MCP server in PolicyLayer and add a rule for ctx_purge: 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 Context Mode. Nothing to install.

What risk level is ctx_purge? +

ctx_purge is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit ctx_purge? +

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

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

ctx_purge is provided by the Context Mode MCP server (mksglu/context-mode). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Context Mode tool call.

Start from Context Mode, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →

Free to start. No card required.

11 Context Mode tools catalogued and risk-classified — across an index of 43,000+ MCP servers.