AI agents call list_bricks_documents to retrieve information from MCP-RAGAnything without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'list_' prefix strongly implies data retrieval without side effects. In the context of a RAG (Retrieval-Augmented Generation) system managing documents, listing documents is a fundamental Read operation that queries available resources without modification. The empty description reduces confidence slightly, but the naming convention and sibling tool patterns provide sufficient basis for classification.
From the tool's definition Tool name 'list_bricks_documents' indicates a listing operation typical of Read category (list, get, fetch). Description is empty, limiting direct evidence.
Documented attack patterns abuse exactly the kind of access list_bricks_documents gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP-RAGAnything, and nothing reaches the server without passing your rules. This is the rule we recommend for list_bricks_documents:
{
"version": "1",
"default": "deny",
"tools": {
"list_bricks_documents": {}
}
}list_bricks_documents 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.
list_bricks_documents. It is categorised as a Read tool in the MCP-RAGAnything MCP Server, which means it retrieves data without modifying state.
Register the MCP-RAGAnything MCP server in PolicyLayer and add a rule for list_bricks_documents: 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 MCP-RAGAnything. Nothing to install.
list_bricks_documents 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 list_bricks_documents 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 list_bricks_documents. 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.
list_bricks_documents is provided by the MCP-RAGAnything MCP server (soludevtech/mcp-raganything). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP-RAGAnything, 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.
9 MCP-RAGAnything tools catalogued and risk-classified — across an index of 43,000+ MCP servers.