// SCAN REPORT

DeepL

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

2 write tools that can modify data. Rate limits recommended.

Last updated: 21 Jul 2026

2 can modify or destroy data

7 read-only

9 tools total

Verified publisher · catalogue entry checked 03/04/2026

How to control DeepL ↓

TOOL MAP

What DeepL exposes to your agents

Read (7) Write / Execute (2) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous DeepL tools

Execute · Medium translate-document This tool executes a document translation operation, which is an external service call with effects dependent on the input document and target language parameters. Write · Low rephrase-text This tool modifies/transforms text by rephrasing it.

2 of DeepL's 9 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

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

Rate limit write operations

{
  "rephrase-text": {
    "limits": [
      {
        "counter": "rephrase-text_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get-glossary-dictionary-entries": {
    "limits": [
      {
        "counter": "get-glossary-dictionary-entries_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 — 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 9 DeepL tools

EXECUTE 1 tools

Execute translate-document Translate a document file via DeepL

WRITE 1 tools

Write rephrase-text Rephrase text in the same or different language

READ 7 tools

Read get-glossary-dictionary-entries Retrieve dictionary entries from a glossary Read get-glossary-info Get metadata about a specific glossary Read get-source-languages Get list of available source languages Read get-target-languages Get list of available target languages Read get-writing-styles Get available writing styles for rephrasing Read list-glossaries List all glossaries and their metadata Read translate-text Translate text to a target language via DeepL

EXPLORE

Related servers

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

FAQ

Questions about DeepL

How do I prevent bulk modifications through DeepL? +

The DeepL server has 1 write tools including rephrase-text. 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.

How many tools does the DeepL MCP server expose? +

9 tools across 2 categories: Execute, Read. 7 are read-only. 2 can modify, create, or delete data.

How do I enforce a policy on DeepL? +

Register the DeepL 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 tool call.

Deterministic rules across all 9 DeepL tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON DEEPL →

Instant setup, no code required.

9 DeepL tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from DeepL's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →