clear_cache

THE RISK

Critical Risk

Why clear_cache needs a policy

Clearing a cache is a non-reversible deletion of stored index data. While the cache can be rebuilt by re-indexing, the act itself cannot be undone and destroys the current cached state. This fits Destructive. Severity is medium because the blast radius is limited to performance/availability (re-indexing may be costly or slow) rather than loss of source data.

From the tool's definition 'Clear the cached index for a repository' and 'force a fresh index' — the cache data is irreversibly wiped

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

POLICY

How to control clear_cache

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

policy.json

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

clear_cache 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 MCP Context Manager — 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 MCP Context Manager tools

Destructive delete_symbol 🗑️ NEW: Delete a symbol (Serena-inspired). Remove function/class/etc cleanly. Symbol-leve Execute build_dependency_graph 🚀 NEW: Build dependency graph for the entire codebase. Call this once after indexing to e Execute index_repository 🔧 REQUIRED FIRST STEP: Index or re-index the repository to enable all context-manager too Write insert_after_symbol ✏️ NEW: Insert code after a symbol (Serena-inspired). Symbol-level editing without reading Write replace_symbol ✏️ NEW: Replace a symbol with new code (Serena-inspired). Surgical precision editing. Repl Read find_similar Find code similar to a given symbol. Useful for discovering related implementations, simil Read find_symbol ⭐ PREFERRED FOR SYMBOLS: Use this INSTEAD OF Grep when looking for specific functions, cla Read find_symbol_references 🔍 NEW: Find all places where a symbol is used (Serena-inspired). Shows usages across all

All 21 MCP Context Manager 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 MCP Context Manager → 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 clear_cache

What does the clear_cache tool do? +

Clear the cached index for a repository. Useful if cache becomes corrupted or you want to force a fresh index. It is categorised as a Destructive tool in the MCP Context Manager 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 clear_cache? +

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

What risk level is clear_cache? +

clear_cache 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 clear_cache? +

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

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

clear_cache is provided by the MCP Context Manager MCP server (transparentlyok/mcp-context-manager). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP Context Manager tool call.

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

CHECK YOUR STACK →