query_vectorstore
AI agents call query_vectorstore to retrieve information from Combined MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to retrieve or search vector-based data from a knowledgebase. Although the description is empty (lowering confidence), the tool name and server context indicate read-only semantic search operations. Query operations on vector stores are non-destructive information retrieval, placing this in the Read category with low severity.
From the tool's definition Tool name 'query_vectorstore' indicates a query operation on vector storage. Server description states it 'perform[s] hybrid semantic searches on markdown files stored in S3.' The name pattern 'query_' combined with sibling tools (build_vectorstore,…
Attacks that exploit this kind of access
query_vectorstore. It is categorised as a Read tool in the Combined MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Combined MCP Server MCP server in PolicyLayer and add a rule for query_vectorstore: 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 Combined MCP Server. Nothing to install.
query_vectorstore 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 query_vectorstore 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 query_vectorstore. 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.
query_vectorstore is provided by the Combined MCP Server MCP server (manish6007/mcp_servers). 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 →