AI agents call list_knowledge to retrieve information from Querywise without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and enumerates metadata about knowledge documents associated with a database connection. It performs a simple read operation without creating, modifying, deleting, or executing any operations. The blast radius of misuse is minimal—an attacker gains only informational access to what knowledge documents exist for a connection, which does not compromise data security or trigger external operations.
From the tool's definition Tool name 'list_knowledge' and description 'List the knowledge documents imported for a connection' indicate a query/retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
List the knowledge documents imported for a connection. It is categorised as a Read tool in the Querywise MCP Server, which means it retrieves data without modifying state.
Register the Querywise MCP server in PolicyLayer and add a rule for list_knowledge: 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 Querywise. Nothing to install.
list_knowledge 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_knowledge 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_knowledge. 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_knowledge is provided by the Querywise MCP server (kosminus/querywise-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 →