Summarize the number and titles of local notes.
AI agents call workspace_summary to retrieve information from Local Knowledge Desk without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads data to generate a summary report. It has no side effects—it does not create, modify, delete, or execute any external operations. It is purely informational and retrieves existing note metadata, placing it squarely in the Read category with low severity.
From the tool's definition Tool performs a 'summarize' operation that retrieves and aggregates metadata (number and titles) from existing notes without modification, addition, or deletion. The description explicitly states it summarizes note counts and titles.
Attacks that exploit this kind of access
Summarize the number and titles of local notes. It is categorised as a Read tool in the Local Knowledge Desk MCP Server, which means it retrieves data without modifying state.
Register the Local Knowledge Desk MCP server in PolicyLayer and add a rule for workspace_summary: 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 Local Knowledge Desk. Nothing to install.
workspace_summary 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 workspace_summary 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 workspace_summary. 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.
workspace_summary is provided by the Local Knowledge Desk MCP server (matiaslaukka/openai-mcp-project). 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 →