Search and retrieve notes. Searches in title, content, and tags.
AI agents call retrieve_notes to retrieve information from MCP Demo Application without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs read-only queries against stored notes without any side effects. It retrieves data based on search criteria but does not create, modify, delete, or execute any operations. This is a classic Read category tool with minimal security risk, appropriate for low severity classification.
From the tool's definition Tool is named 'retrieve_notes' and described as 'Search and retrieve notes' with search-only operations across title, content, and tags. No modification, deletion, or execution capability is indicated.
Attacks that exploit this kind of access
Search and retrieve notes. Searches in title, content, and tags. It is categorised as a Read tool in the MCP Demo Application MCP Server, which means it retrieves data without modifying state.
Register the MCP Demo Application MCP server in PolicyLayer and add a rule for retrieve_notes: 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 MCP Demo Application. Nothing to install.
retrieve_notes 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 retrieve_notes 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 retrieve_notes. 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.
retrieve_notes is provided by the MCP Demo Application MCP server (mic-havock/model-context-protocol). 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 →