// SCAN REPORT

RAG-Anything MCP Server

8 tools. 4 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 12 Jun 2026

4 can modify or destroy data

4 read-only

8 tools total

Community server · catalogue entry verified 12/06/2026

How to control RAG-Anything MCP Server ↓

TOOL MAP

What RAG-Anything MCP Server exposes to your agents

Read (4) Write / Execute (3) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous RAG-Anything MCP Server tools

Destructive · High delete_data This tool permanently removes documents from the knowledge graph storage. Write · Medium insert_content_list This tool modifies the knowledge graph by inserting new content. Write · Medium ingest_document Based on the tool name and server context (RAG system supporting document ingestion), this tool likely reads a document and writes/indexes it into the knowledge graph or vector store. Write · Medium process_document_file This tool ingests and processes a PDF document, extracting multimodal content and presumably writing it into the knowledge graph/RAG system.

4 of RAG-Anything MCP Server's 8 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control RAG-Anything MCP Server

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. These are the rules we recommend:

Deny destructive operations

{
  "delete_data": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "ingest_document": {
    "limits": [
      {
        "counter": "ingest_document_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_config_info": {
    "limits": [
      {
        "counter": "get_config_info_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register RAG-Anything MCP Server — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON RAG-ANYTHING →

Free to start. No card required.

FULL CATALOGUE

All 8 RAG-Anything MCP Server tools

DESTRUCTIVE 1 tools

Destructive delete_data Delete document by ID from knowledge graph.

WRITE 3 tools

Write ingest_document ingest_document Write process_document_file Process a PDF document file with multimodal content extraction. Write insert_content_list Insert pre-parsed multimodal content directly into knowledge graph.

READ 4 tools

Read get_config_info Get knowledge graph configuration information. Read get_graph_statistics Get knowledge graph statistics. Read query_knowledge_graph query_knowledge_graph Read query_multimodal query_multimodal

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about RAG-Anything MCP Server

Can an AI agent delete data through the RAG-Anything MCP Server MCP server? +

Yes. The RAG-Anything MCP Server server exposes 1 destructive tools including delete_data. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through RAG-Anything MCP Server? +

The RAG-Anything MCP Server server has 3 write tools including ingest_document, process_document_file, insert_content_list. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach RAG-Anything MCP Server.

How many tools does the RAG-Anything MCP Server MCP server expose? +

8 tools across 3 categories: Destructive, Read, Write. 4 are read-only. 4 can modify, create, or delete data.

How do I enforce a policy on RAG-Anything MCP Server? +

Register the RAG-Anything MCP Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every RAG-Anything MCP Server tool call.

Deterministic rules across all 8 RAG-Anything MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON RAG-ANYTHING →

Free to start. No card required.

8 RAG-Anything MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.