collectionStats
AI agents call collectionStats 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.
No description available, but the naming pattern and server context strongly suggest this retrieves metadata/statistics about collections. Statistics queries are inherently read-only with no side effects. The low confidence penalty reflects the missing description, but the category assignment remains high confidence based on sibling tool patterns and semantic meaning of 'stats'.
From the tool's definition Tool name 'collectionStats' with empty description; context shows this server provides retrieval and analysis functions. Sibling tools like 'listDBs', 'listDocuments', 'retrieveDocs', and 'searchAcrossCollections' are all Read operations.
Attacks that exploit this kind of access
collectionStats. 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 collectionStats: 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.
collectionStats 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 collectionStats 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 collectionStats. 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.
collectionStats 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 →