Map user inputs to verbatim matching excerpts from reference content.
AI agents call extract_original_text to retrieve information from Notemd MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs text matching and extraction from reference materials. This is a read-only operation that retrieves data without creating, modifying, deleting, or executing anything. The low severity reflects minimal risk even if misused — it can only return what already exists in the reference content.
From the tool's definition Tool description states it 'Map[s] user inputs to verbatim matching excerpts from reference content' — this is a retrieval/query operation that extracts existing text without modification or side effects.
Attacks that exploit this kind of access
Map user inputs to verbatim matching excerpts from reference content. It is categorised as a Read tool in the Notemd MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Notemd MCP Server MCP server in PolicyLayer and add a rule for extract_original_text: 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 Notemd MCP Server. Nothing to install.
extract_original_text 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 extract_original_text 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 extract_original_text. 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.
extract_original_text is provided by the Notemd MCP Server MCP server (jacobinwwey/notemd-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 →