Delete all indexed data for a project: vector embeddings, symbol graph (definitions/references/imports/centrality), and stored memories.
AI agents call th0th_reset_project to permanently remove resources in Th0th — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes all indexed data associated with a project. The operation cannot be undone and results in complete loss of project-specific embeddings, semantic graphs, and stored memories. While the blast radius is scoped to a single project, the total data loss within that project scope is comprehensive and permanent.
From the tool's definition Tool description states 'Delete all indexed data for a project: vector embeddings, symbol graph (definitions/references/imports/centrality), and stored memories.' The use of 'Delete all' combined with enumeration of what is permanently removed (embeddings,…
Documented attack patterns abuse exactly the kind of access th0th_reset_project gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Th0th, and nothing reaches the server without passing your rules. This is the rule we recommend for th0th_reset_project:
{
"version": "1",
"default": "deny",
"hide": [
"th0th_reset_project"
]
} th0th_reset_project 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.
Delete all indexed data for a project: vector embeddings, symbol graph (definitions/references/imports/centrality), and stored memories. It is categorised as a Destructive tool in the Th0th MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Th0th MCP server in PolicyLayer and add a rule for th0th_reset_project: 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 Th0th. Nothing to install.
th0th_reset_project 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 th0th_reset_project 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 th0th_reset_project. 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.
th0th_reset_project is provided by the Th0th MCP server (s1lv4/th0th). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 21 Th0th tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
21 Th0th tools catalogued and risk-classified — across an index of 42,500+ MCP servers.