# rephrase-text

Rephrase text in the same or different language

Agent View of the PolicyLayer registry record for `rephrase-text`. HTML page: https://policylayer.com/tools/deepl/rephrase-text

## Facts

- Tool: `rephrase-text`
- Server: DeepL (`@deepl-mcp-server`) — https://policylayer.com/tools/deepl.md
- Install: `npx -y @deepl-mcp-server`
- Homepage: https://www.npmjs.com/package/@deepl-mcp-server
- Risk category: Write (Medium risk)
- Registry record: grade C, identity verified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "rephrase-text",
    "arguments": {}
  }
}
```

## Why rephrase-text is rated Medium

This tool modifies/transforms text by rephrasing it. It creates a new version of the input text, which is a reversible write/transform operation. No data is deleted, no code is executed, and no financial transaction occurs. The blast radius is low since it only affects the text passed to it.

From the tool's own definition: "Rephrase text in the same or different language"

Risk signals: Consumes DeepL API credits

## Use case

AI agents use rephrase-text to create or update resources in DeepL, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your DeepL environment.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches DeepL:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "rephrase-text": {
      "limits": [
        {
          "counter": "rephrase-text_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on DeepL (8)

- `translate-document` — Execute — https://policylayer.com/tools/deepl/translate-document.md
- `get-glossary-dictionary-entries` — Read — https://policylayer.com/tools/deepl/get-glossary-dictionary-entries.md
- `get-glossary-info` — Read — https://policylayer.com/tools/deepl/get-glossary-info.md
- `get-source-languages` — Read — https://policylayer.com/tools/deepl/get-source-languages.md
- `get-target-languages` — Read — https://policylayer.com/tools/deepl/get-target-languages.md
- `get-writing-styles` — Read — https://policylayer.com/tools/deepl/get-writing-styles.md
- `list-glossaries` — Read — https://policylayer.com/tools/deepl/list-glossaries.md
- `translate-text` — Read — https://policylayer.com/tools/deepl/translate-text.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=deepl · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/deepl