9 tools. 2 can modify or destroy data without limits.
2 write tools that can modify data. Rate limits recommended.
Last updated:
Execute tools (rephrase-text, translate-document) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.
Intercept sits between your agent and DeepL. Every tool call checked against your policy before it executes — so your agent can do its job without breaking things.
npx -y @policylayer/intercept scan -- npx -y @deepl-mcp-server get-glossary-dictionary-entries:
rules:
- rate_limit: 60/minute Controls API costs and prevents retry loops from exhausting upstream rate limits.
The DeepL server is primarily read-only with 7 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.
9 tools across 2 categories: Execute, Read. 7 are read-only. 2 can modify, create, or delete data.
One line change. Instead of running the DeepL server directly, prefix it with Intercept: intercept -c deepl.yaml -- npx -y @@deepl-mcp-server. Download a pre-built policy from policylayer.com/policies/deepl and adjust the limits to match your use case.
Starter policies available for each. Same risk classification, same one-command setup.
Set budgets, approvals, and hard limits across MCP servers.
npx -y @policylayer/intercept init