AI agents call get_last to retrieve information from Arca MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a straightforward read operation that retrieves memories from storage in chronological order. There is no capability to modify, delete, or execute operations. The tool has minimal blast radius—misuse would only result in unauthorized data access, not data loss or state changes. Classified as Read with low severity.
From the tool's definition Tool name 'get_last' and description 'Retrieve the last N memories ordered by creation time' explicitly indicates a retrieval operation with no side effects. It queries stored data without modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Retrieve the last N memories ordered by creation time (most recent first). It is categorised as a Read tool in the Arca MCP MCP Server, which means it retrieves data without modifying state.
Register the Arca MCP server in PolicyLayer and add a rule for get_last: 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 Arca MCP. Nothing to install.
get_last 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 get_last 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 get_last. 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.
get_last is provided by the Arca MCP server (m0nochr0me/arca-mcp). 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 →