AI agents call memento_get_warnings to retrieve information from Memento without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries warnings for a given code context or library. There is no modification, deletion, execution of code, or financial impact. The action is read-only introspection of existing warning state. The deprecation status suggests it is no longer actively used, but its function remains a simple data retrieval operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name uses 'get_' prefix and description states 'Get proactive warnings', indicating retrieval of warning data with no side effects. The [DEPRECATED] status further confirms it is informational only.
Attacks that exploit this kind of access
[DEPRECATED] Get proactive warnings (spider-sense) for a specific code context or library. It is categorised as a Read tool in the Memento MCP Server, which means it retrieves data without modifying state.
Register the Memento MCP server in PolicyLayer and add a rule for memento_get_warnings: 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 Memento. Nothing to install.
memento_get_warnings 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 memento_get_warnings 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 memento_get_warnings. 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.
memento_get_warnings is provided by the Memento MCP server (joyciakira/memento). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →