listDBs
AI agents call listDBs to retrieve information from RAG 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 list available databases or collections in the RAG system, which is a non-destructive query operation with no side effects. Even with an empty description, the naming convention and context of sibling read-only tools (listDocuments, collectionStats) support classification as Read. Confidence is slightly reduced due to missing description, but the functional intent is clear from the name.
From the tool's definition Tool name 'listDBs' indicates listing/enumerating database collections; consistent with sibling tools like 'listDocuments' and 'collectionStats' which are read operations.
Attacks that exploit this kind of access
listDBs. It is categorised as a Read tool in the RAG MCP Server MCP Server, which means it retrieves data without modifying state.
Register the RAG MCP Server MCP server in PolicyLayer and add a rule for listDBs: 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 RAG MCP Server. Nothing to install.
listDBs 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 listDBs 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 listDBs. 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.
listDBs is provided by the RAG MCP Server MCP server (nsantra/rag-mcp-server). 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 →