AI agents call deep_recall to retrieve information from Project Tessera without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and searches existing data in the vector store with scoring/ranking capabilities, which is purely a read operation. It retrieves information from cross-session memory without side effects. No data creation, modification, deletion, or external execution occurs. The low severity reflects that misuse would only expose existing information the user already has access to in their local workspace.
From the tool's definition Tool performs 'multi-angle memory search with verdict scoring' - a retrieval and analysis operation on stored memories without modifying, deleting, or executing external actions.
Documented attack patterns abuse exactly the kind of access deep_recall gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Project Tessera, and nothing reaches the server without passing your rules. This is the rule we recommend for deep_recall:
{
"version": "1",
"default": "deny",
"tools": {
"deep_recall": {}
}
}deep_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.
Multi-angle memory search with verdict scoring. It is categorised as a Read tool in the Project Tessera MCP Server, which means it retrieves data without modifying state.
Register the Project Tessera MCP server in PolicyLayer and add a rule for deep_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 Project Tessera. Nothing to install.
deep_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 deep_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 deep_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.
deep_recall is provided by the Project Tessera MCP server (besslframework-stack/project-tessera). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Project Tessera, 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.
43 Project Tessera tools catalogued and risk-classified — across an index of 43,000+ MCP servers.