get-knowledge-by-id
AI agents call get-knowledge-by-id to retrieve information from Better Qdrant without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name strongly suggests a simple lookup/retrieval operation (get by ID), consistent with Read category semantics. The absence of description lowers confidence slightly, but the naming convention and parallel tools on a semantic search server confirm this is a retrieval action with no side effects. Severity is low as it only queries stored data.
From the tool's definition Tool name 'get-knowledge-by-id' indicates retrieval by identifier. Server context shows this is a knowledge/memory storage system with sibling tools including 'search-knowledge' and 'store-knowledge', positioning this as a data retrieval function.
Attacks that exploit this kind of access
get-knowledge-by-id. It is categorised as a Read tool in the Better Qdrant MCP Server, which means it retrieves data without modifying state.
Register the Better Qdrant MCP server in PolicyLayer and add a rule for get-knowledge-by-id: 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 Better Qdrant. Nothing to install.
get-knowledge-by-id 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 get-knowledge-by-id 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 get-knowledge-by-id. 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.
get-knowledge-by-id is provided by the Better Qdrant MCP server (jtsang4/better-qdrant-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 →