// SCAN REPORT

PDF RAG MCP Server

5 tools. 2 can modify or destroy data without limits.

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

Last updated: 28 Jun 2026

2 can modify or destroy data

3 read-only

5 tools total

Community server · catalogue entry verified 28/06/2026

How to control PDF RAG MCP Server ↓

TOOL MAP

What PDF RAG MCP Server exposes to your agents

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

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous PDF RAG MCP Server tools

Destructive · High pdf_remove pdf_remove Write · Medium pdf_add pdf_add

2 of PDF RAG MCP Server's 5 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control PDF RAG MCP Server

PolicyLayer is an MCP gateway — it sits between your AI agents and PDF RAG MCP Server, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "pdf_remove": {
    "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

{
  "pdf_add": {
    "limits": [
      {
        "counter": "pdf_add_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "pdf_list": {
    "limits": [
      {
        "counter": "pdf_list_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 PDF RAG 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 PDF RAG →

Instant setup, no code required.

FULL CATALOGUE

All 5 PDF RAG MCP Server tools

DESTRUCTIVE 1 tools

Destructive pdf_remove pdf_remove

WRITE 1 tools

Write pdf_add pdf_add

READ 3 tools

Read pdf_list pdf_list Read pdf_search_keywords pdf_search_keywords Read pdf_search_similarity pdf_search_similarity

EXPLORE

Related servers

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

FAQ

Questions about PDF RAG MCP Server

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

Yes. The PDF RAG MCP Server server exposes 1 destructive tools including pdf_remove. 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 PDF RAG MCP Server? +

The PDF RAG MCP Server server has 1 write tools including pdf_add. 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 PDF RAG MCP Server.

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

5 tools across 3 categories: Destructive, Read, Write. 3 are read-only. 2 can modify, create, or delete data.

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

Register the PDF RAG 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 PDF RAG MCP Server tool call.

Deterministic rules across all 5 PDF RAG MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON PDF RAG →

Instant setup, no code required.

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