AI agents call vscode_recent to retrieve information from Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries VSCode's recent files/folders history and returns that data without modifying, deleting, or executing anything. It has no destructive, financial, or execution capabilities. The blast radius of misuse is minimal—an agent could learn about the user's recent development activity, which is sensitive but not operationally dangerous. Classified as Read with low severity.
From the tool's definition Tool name 'vscode_recent' and description 'Get recently opened files and folders from VSCode' indicate a retrieval operation with no side effects. The verb 'Get' is a classic Read operation.
Attacks that exploit this kind of access
Get recently opened files and folders from VSCode. It is categorised as a Read tool in the Memory MCP Server, which means it retrieves data without modifying state.
Register the Memory MCP server in PolicyLayer and add a rule for vscode_recent: 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 Memory. Nothing to install.
vscode_recent 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 vscode_recent 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 vscode_recent. 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.
vscode_recent is provided by the Memory MCP server (shaktisinhchavda/memory-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 →