searchAcrossCollections
AI agents call searchAcrossCollections 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 search across document collections in ChromaDB—a read-only operation with no side effects. The function name pattern and the broader server purpose (enabling retrieval-augmented generation with citations) strongly suggest it retrieves or queries embedded documents.
From the tool's definition Tool name 'searchAcrossCollections' and context of a RAG (Retrieval-Augmented Generation) system with ChromaDB and embedding models indicate query/retrieval functionality.
Attacks that exploit this kind of access
searchAcrossCollections. 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 searchAcrossCollections: 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.
searchAcrossCollections 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 searchAcrossCollections 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 searchAcrossCollections. 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.
searchAcrossCollections 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 →