List recent chat summaries from the notes directory.
AI agents call list_summaries to retrieve information from IDE Chat Summarizer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves existing summary files from a directory. It performs no side effects—no data is created, modified, deleted, or overwritten. It is a pure read operation similar to listing or fetching stored records. The blast radius of misuse is minimal, as an AI agent can only view what summaries exist. Severity is low because viewing file listings poses no direct harm.
From the tool's definition Tool name 'list_summaries' and description 'List recent chat summaries from the notes directory' indicate a retrieval operation with no modification, deletion, or execution of code.
Attacks that exploit this kind of access
List recent chat summaries from the notes directory. It is categorised as a Read tool in the IDE Chat Summarizer MCP Server, which means it retrieves data without modifying state.
Register the IDE Chat Summarizer MCP server in PolicyLayer and add a rule for list_summaries: 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 IDE Chat Summarizer. Nothing to install.
list_summaries 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 list_summaries 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 list_summaries. 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.
list_summaries is provided by the IDE Chat Summarizer MCP server (ralphli213/ide-chat-summarizer-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 →