AI agents call memory_categories 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 performs a non-destructive read operation—it lists and counts memory categories stored in the vector store but does not create, modify, delete, or execute code. The blast radius is minimal: exposing category counts poses no financial, operational, or data integrity risk. Low severity reflects the read-only nature and limited information disclosure.
From the tool's definition Tool name 'memory_categories' and description 'List all memory categories with counts' indicate a retrieval operation that queries existing data without modification or side effects.
Documented attack patterns abuse exactly the kind of access memory_categories 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 memory_categories:
{
"version": "1",
"default": "deny",
"tools": {
"memory_categories": {}
}
}memory_categories 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.
List all memory categories with counts. 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 memory_categories: 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.
memory_categories 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 memory_categories 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 memory_categories. 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.
memory_categories 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.