<tool> <purpose>Permanently removes all indexed data for a codebase</purpose> <when_to_use> <scenario>Clear stale data before reindexing after major code changes</scenario> <scenario>Remove old indexed codebases no longer needed</scenario> <scenario>Fix corrupted index causing search issues</scen...
AI agents call clear_index to permanently remove resources in Mcp Deepcontext — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes indexed codebase data. While the data can be regenerated by reindexing, the current index state cannot be recovered. This fits the Destructive category as it performs an action that cannot be undone. Severity is high because loss of the index could disrupt development workflows and search functionality, though the underlying source code is not affected.
From the tool's definition "Permanently removes all indexed data for a codebase" - the word 'permanently' and 'removes' indicate irreversible deletion of data.
Documented attack patterns abuse exactly the kind of access clear_index gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Deepcontext, and nothing reaches the server without passing your rules. This is the rule we recommend for clear_index:
{
"version": "1",
"default": "deny",
"hide": [
"clear_index"
]
}clear_index 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.
<tool> <purpose>Permanently removes all indexed data for a codebase</purpose> <when_to_use> <scenario>Clear stale data before reindexing after major code changes</scenario> <scenario>Remove old indexed codebases no longer needed</scenario> <scenario>Fix corrupted index causing search issues</scenario> </when_to_use> <parameters> <parameter name=. It is categorised as a Destructive tool in the Mcp Deepcontext MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mcp Deepcontext MCP server in PolicyLayer and add a rule for clear_index: 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 Deepcontext. Nothing to install.
clear_index 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_index 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_index. 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_index is provided by the Mcp Deepcontext MCP server (jmerelnyc/mcp-deepcontext). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Deepcontext, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 Mcp Deepcontext tools catalogued and risk-classified — across an index of 43,000+ MCP servers.