AI agents call search_workspace to retrieve information from AnythingLLM MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries data from a workspace without creating, modifying, or deleting anything. It is a read-only operation that has no lasting impact on the system state. The low severity reflects minimal blast radius if an AI agent misuses it—it can only access information it is already scoped to query.
From the tool's definition Tool name 'search_workspace' and description 'Search within a workspace' indicate a query/retrieval operation with no modification or side effects.
Documented attack patterns abuse exactly the kind of access search_workspace gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and AnythingLLM MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search_workspace:
{
"version": "1",
"default": "deny",
"tools": {
"search_workspace": {}
}
}search_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.
Search within a workspace. It is categorised as a Read tool in the AnythingLLM MCP Server MCP Server, which means it retrieves data without modifying state.
Register the AnythingLLM MCP Server MCP server in PolicyLayer and add a rule for search_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 AnythingLLM MCP Server. Nothing to install.
search_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 search_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 search_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.
search_workspace is provided by the AnythingLLM MCP Server MCP server (raqueljezweb/anythingllm-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from AnythingLLM 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.
38 AnythingLLM MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.