AI agents use toggle_auto_learn to create or update resources in Project Tessera — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Project Tessera environment.
This tool modifies a system configuration setting (auto-learn mode), which is a reversible write operation. Misuse could cause the system to stop learning from interactions or start learning undesired content, affecting cross-session memory behavior. It does not delete data or execute code, so Write is the most appropriate category.
From the tool's definition Toggle auto-learning on/off
Documented attack patterns abuse exactly the kind of access toggle_auto_learn 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 toggle_auto_learn:
{
"version": "1",
"default": "deny",
"tools": {
"toggle_auto_learn": {
"limits": [
{
"counter": "toggle_auto_learn_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}toggle_auto_learn stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Toggle or check auto-learning on/off. It is categorised as a Write tool in the Project Tessera MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Project Tessera MCP server in PolicyLayer and add a rule for toggle_auto_learn: 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.
toggle_auto_learn is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the toggle_auto_learn 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 toggle_auto_learn. 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.
toggle_auto_learn 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.