Search stored memories across sessions using semantic search (recovers context from previous conversations)
AI agents call th0th_recall to retrieve information from Th0th without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
th0th_recall retrieves previously stored conversation context using semantic search. This is a query/retrieval operation analogous to a database SELECT or vector similarity search. No data is modified, deleted, or executed; the tool only surfaces existing information.
From the tool's definition Tool performs "semantic search" to "search stored memories" and "recover context" — these are retrieval operations with no modification, deletion, or execution side effects.
Documented attack patterns abuse exactly the kind of access th0th_recall 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_recall:
{
"version": "1",
"default": "deny",
"tools": {
"th0th_recall": {}
}
}th0th_recall is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search stored memories across sessions using semantic search (recovers context from previous conversations). It is categorised as a Read tool in the Th0th MCP Server, which means it retrieves data without modifying state.
Register the Th0th MCP server in PolicyLayer and add a rule for th0th_recall: 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_recall is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the th0th_recall 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_recall. 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_recall 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.