// SCAN REPORT

DeepL MCP Server

24 tools. 7 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated: 29 Jun 2026

7 can modify or destroy data

17 read-only

24 tools total

Community server · catalogue entry verified 29/06/2026

How to control DeepL MCP Server ↓

TOOL MAP

What DeepL MCP Server exposes to your agents

Read (17) Write / Execute (5) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous DeepL MCP Server tools

Destructive · High delete_glossary Deletes a DeepL v3 glossary. Destructive · High delete_style_rule Deletes a DeepL v3 style rule list. Execute · Medium rephrase_text Rephrases/improves text using DeepL Write API with optional writing style and tone. Write · Medium create_glossary Creates a DeepL v3 glossary with one or more dictionaries.

7 of DeepL MCP Server's 24 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control DeepL MCP Server

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

Deny destructive operations

{
  "delete_glossary": {
    "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

{
  "create_glossary": {
    "limits": [
      {
        "counter": "create_glossary_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "download_document": {
    "limits": [
      {
        "counter": "download_document_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 DeepL 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 DEEPL →

Instant setup, no code required.

FULL CATALOGUE

All 24 DeepL MCP Server tools

DESTRUCTIVE 2 tools

Destructive delete_glossary Deletes a DeepL v3 glossary. Destructive delete_style_rule Deletes a DeepL v3 style rule list.

EXECUTE 1 tools

Execute rephrase_text Rephrases/improves text using DeepL Write API with optional writing style and tone.

WRITE 4 tools

Write create_glossary Creates a DeepL v3 glossary with one or more dictionaries. Write create_style_rule Creates a DeepL v3 style rule list. Write update_style_rule Updates a DeepL v3 style rule list name. Write upload_document Uploads a local document file for DeepL document translation and returns document_id/document_key.

READ 17 tools

Read download_document Downloads a completed translated document to a local output path. Read get_document_status Checks DeepL document translation status. Read get_glossary Gets DeepL v3 glossary metadata. Read get_glossary_entries Gets entries for a DeepL v3 glossary. For multilingual glossaries, source_lang and target_lang select a dictio Read get_glossary_language_pairs Lists language pairs supported by DeepL glossaries. Read get_language_products_v3 Retrieves DeepL v3 beta language products and product feature metadata. Read get_languages_v3 Retrieves DeepL v3 beta supported languages by product, with feature metadata. Read get_source_languages Retrieves all available source languages for translation. Read get_style_rule Gets a DeepL v3 style rule list by style_id. Read get_target_languages Retrieves all available target languages for translation, including formality support info. Read get_usage Retrieves current API usage statistics (character count and limits). Read list_glossaries Lists DeepL v3 glossaries. Read list_style_rules Lists DeepL v3 style rule lists, optionally detailed. Read list_translation_memories Lists DeepL v3 translation memories available to the account. Read reconnect_voice_session Gets a new DeepL Voice real-time WebSocket URL/token, optionally using the latest stream token. Read request_voice_session Requests a DeepL Voice real-time WebSocket session and ephemeral token. Streaming itself is handled by the ret Read translate_text Translates text using DeepL API with formality, context, glossary, next-gen model, style, translation memory,

EXPLORE

Related servers

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

FAQ

Questions about DeepL MCP Server

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

Yes. The DeepL MCP Server server exposes 2 destructive tools including delete_glossary, delete_style_rule. 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 DeepL MCP Server? +

The DeepL MCP Server server has 4 write tools including create_glossary, create_style_rule, update_style_rule. 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 DeepL MCP Server.

How many tools does the DeepL MCP Server MCP server expose? +

24 tools across 4 categories: Destructive, Execute, Read, Write. 17 are read-only. 7 can modify, create, or delete data.

How do I enforce a policy on DeepL MCP Server? +

Register the DeepL 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 DeepL MCP Server tool call.

Deterministic rules across all 24 DeepL MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON DEEPL →

Instant setup, no code required.

24 DeepL MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.