> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.merge.dev/merge-workforce/security/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.merge.dev/_mcp/server.

# Secure

> Build once. Connect to every API, tool, and LLM. Ship products and agents to production without owning the integration stack.

## Docs

- [Security Gateway](https://docs.merge.dev/merge-workforce/security/overview.md): How the Workforce Security Gateway works: where it sits in the tool call path, the three rule types, what log, redact, and block do, and per-Tool-Pack overrides.
- [Standard Entity Rules](https://docs.merge.dev/merge-workforce/security/standard-entity-rules.md): Reference for Workforce Standard Entity Rules: every entity type, what it detects, the detection methods behind it, the action choices, and per-Tool-Pack overrides.
- [Custom Regex Rules](https://docs.merge.dev/merge-workforce/security/custom-regex-rules.md): How to write Custom Regex Rules for the Workforce Security Gateway: the pattern, context keywords, and the action, with three worked examples.
- [AI Guardrails](https://docs.merge.dev/merge-workforce/security/ai-guardrails.md): How Workforce AI Guardrails work: writing the instruction, the block and log actions, pre-run and post-run screening, Tool Pack and Group scoping, and picking an evaluation model.
- [Violations and alerts](https://docs.merge.dev/merge-workforce/security/violations-and-alerts.md): Tour of the Workforce Alerts page: violations over time, the breakdown by entity type, the per-violation table, and how to go from a spike to the tool call behind it.
- [Guardrail tester](https://docs.merge.dev/merge-workforce/security/rule-tester.md): How to use the Workforce guardrail tester to check Standard Entity Rules, Custom Regex Rules, and AI Guardrails against sample input, and how to read the pipeline and the feed it streams back.