Low Risk

read_bricks_document

read_bricks_document

How to control read_bricks_document ↓

What read_bricks_document does on MCP-RAGAnything

AI agents call read_bricks_document 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.

Low Risk

Why read_bricks_document needs a policy

This tool retrieves or queries document data without side effects. The name implies a read operation on brick documents within the knowledge base system. Even without explicit description, the naming pattern aligns with other Read-category tools on the same server (read_file, list_*).

From the tool's definition Tool name 'read_bricks_document' indicates a read operation on documents. Sibling tools include 'read_file' and 'list_bricks_documents', establishing a pattern of read-only document access on this RAG service.

Documented attack patterns abuse exactly the kind of access read_bricks_document gives an agent:

How to control read_bricks_document

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 read_bricks_document:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "read_bricks_document": {}
  }
}

read_bricks_document is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register MCP-RAGAnything — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about read_bricks_document

What does the read_bricks_document tool do? +

read_bricks_document. It is categorised as a Read tool in the MCP-RAGAnything MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on read_bricks_document? +

Register the MCP-RAGAnything MCP server in PolicyLayer and add a rule for read_bricks_document: 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.

What risk level is read_bricks_document? +

read_bricks_document is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit read_bricks_document? +

Yes. Add a rate_limit block to the read_bricks_document 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.

How do I block read_bricks_document completely? +

Set action: deny in the PolicyLayer policy for read_bricks_document. 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.

What MCP server provides read_bricks_document? +

read_bricks_document 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.

Enforce policy on every MCP-RAGAnything tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.