AI agents call query_workspace to retrieve information from RAG Anything 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 query a workspace (likely retrieving processed documents or metadata) without modifying data. The destructive sibling 'clear_all_data' is separate, indicating this tool does not delete. The absence of parameters or write indicators suggests passive data retrieval. Low severity due to read-only nature and limited blast radius from misuse.
From the tool's definition Tool name 'query_workspace' combined with sibling tools like 'query_with_multimodal' and 'check_doc_ingested' suggests read-only querying. The server's purpose is RAG (Retrieval-Augmented Generation), which is fundamentally about retrieving information.
Documented attack patterns abuse exactly the kind of access query_workspace gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and RAG Anything MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for query_workspace:
{
"version": "1",
"default": "deny",
"tools": {
"query_workspace": {}
}
}query_workspace is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
query_workspace. It is categorised as a Read tool in the RAG Anything MCP Server MCP Server, which means it retrieves data without modifying state.
Register the RAG Anything MCP Server MCP server in PolicyLayer and add a rule for query_workspace: 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 Anything MCP Server. Nothing to install.
query_workspace 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_workspace 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_workspace. 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_workspace is provided by the RAG Anything MCP Server MCP server (jesse-merhi/rag-anything-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from RAG Anything MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
7 RAG Anything MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.