Clear the parse tree cache. Args: project: Optional project to clear cache for file_path: Optional specific file to clear cache for Returns: Status message
AI agents call clear_cache to permanently remove resources in Tree Sitter — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Clearing a cache is irreversible in that the cached parse trees are discarded and cannot be recovered (they must be recomputed). However, the blast radius is low because cache data is derived/ephemeral — no source code or user data is lost, only cached analysis results that can be regenerated by re-parsing files.
From the tool's definition 'Clear the parse tree cache' - clears cached data irreversibly
Documented attack patterns abuse exactly the kind of access clear_cache gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Tree Sitter, and nothing reaches the server without passing your rules. This is the rule we recommend for clear_cache:
{
"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.
Free to start. No card required.
Clear the parse tree cache. Args: project: Optional project to clear cache for file_path: Optional specific file to clear cache for Returns: Status message. It is categorised as a Destructive tool in the Tree Sitter MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Tree Sitter 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 Tree Sitter. Nothing to install.
clear_cache is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
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.
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.
clear_cache is provided by the Tree Sitter MCP server (wrale/mcp-server-tree-sitter). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 26 Tree Sitter tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
26 Tree Sitter tools catalogued and risk-classified — across an index of 42,500+ MCP servers.