Read the fillable knowledge note template.
AI agents call note_template_read to retrieve information from Knowledge Wiki without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves a template document without modifying, executing, or deleting anything. It has no side effects beyond data retrieval. This is a straightforward Read operation with minimal risk—worst case, the AI agent learns the template structure, which is intended behavior. The blast radius is negligible.
From the tool's definition Tool name is 'note_template_read' and description states it will 'Read the fillable knowledge note template.' The word 'Read' explicitly appears in the tool name and description.
Attacks that exploit this kind of access
Read the fillable knowledge note template. It is categorised as a Read tool in the Knowledge Wiki MCP Server, which means it retrieves data without modifying state.
Register the Knowledge Wiki MCP server in PolicyLayer and add a rule for note_template_read: 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 Knowledge Wiki. Nothing to install.
note_template_read 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 note_template_read 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 note_template_read. 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.
note_template_read is provided by the Knowledge Wiki MCP server (pongs1/knowledge-wiki-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 →