> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.merge.dev/merge-agent-handler/secure/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 - [Scoping access per user](https://docs.merge.dev/merge-agent-handler/secure/scoping-access-per-user.md): How to scope Agent Handler access per end user: mint a short-lived user-scoped Access Key from your production key, what the runtime and management boundaries enforce, and why a Registered User ID in the MCP URL cannot be used to reach another user's data. - [Security Gateway](https://docs.merge.dev/merge-agent-handler/secure/security-gateway.md): How the Agent Handler Security Gateway works: where it sits in the request path, the rule types, the actions, and how it differs from raw MCP. - [Standard Entity Rules](https://docs.merge.dev/merge-agent-handler/secure/standard-entity-rules.md): Full reference for Agent Handler's Standard Entity Rules: every entity type, what it detects, the action choices, and per-tool-pack overrides. - [Custom Regex Rules](https://docs.merge.dev/merge-agent-handler/secure/custom-regex-rules.md): How to write Custom Regex Rules for Agent Handler's Security Gateway: pattern, score, context keywords, with three worked examples. - [AI Guardrails](https://docs.merge.dev/merge-agent-handler/secure/ai-guardrails.md): How Agent Handler's 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-agent-handler/secure/violations-and-alerts.md): Tour of the Agent Handler Alerts dashboard: timeseries, breakdowns, per-violation drilldowns, and CSV export for compliance. - [Rule Tester](https://docs.merge.dev/merge-agent-handler/secure/rule-tester.md): How to use the Agent Handler Rule Tester to validate custom regex rules, Standard Entity Rules, and AI Guardrails before going live.