# Lakera Guard — MCP server on mcp.ai > Connect your Lakera Guard account and use 10 tools for AI safety and compliance straight from your AI agent. Connect with your own API key. Lakera Guard screens AI application interactions for security and safety risks and provides Enterprise APIs for managing guardrail policies and projects. By: mcp.ai · official Page: https://mcp.ai/lakera_guard ## Connect (MCP protocol) Remote MCP endpoint (HTTP, streamable): https://api.mcp.ai/p_lakera_guard?ms=1787291400000 Add it as a custom/remote MCP connector, then authenticate when prompted. ## REST API (no MCP client required) Every tool is also a REST endpoint, authed with a workspace API key. Discover: GET https://api.mcp.ai/api/lakera_guard/_endpoints # public; lists every endpoint Call: POST https://api.mcp.ai/api/lakera_guard/ Authorization: Bearer sk_live_… # create one at https://mcp.ai/settings/api-keys Content-Type: application/json Body: { …args } → { "ok": true, "tool": "", "result": { … } } ## Developer docs How to use (MCP or REST), markdown: https://mcp.ai/lakera_guard/skill.md Postman collection (v2.1): https://mcp.ai/lakera_guard/postman.json ## Tools - lakera_guard_create_policy(name: string, detectors?: object[], default_threshold: string, custom_guardrail_ids?: string[]) — Create an Enterprise Lakera policy with built-in detectors and/or custom guardrails. Lakera may omit the new policy ID; if omitted, later retrieval, replacement, and deletion require external policy l - lakera_guard_create_project(name: string, action?: string, policy_id?: string, project_metadata?: object) — Create an Enterprise Lakera project, optionally assigning a policy, metadata, and detect-or-flag action. Omit policy_id to use the default policy. Lakera does not return the generated project ID, so l - lakera_guard_delete_policy(policy_id: string) — Permanently delete an Enterprise Lakera policy by ID. The provider rejects deletion while any project is assigned to the policy. - lakera_guard_delete_project(project_id: string) — Permanently and irreversibly delete an Enterprise Lakera project by ID. Historical requests lose their association with the project's metadata and assigned policy. - lakera_guard_evaluate_detectors(dev_info?: boolean, messages: object[], metadata?: object, project_id?: string) — Evaluate content and return one confidence result per configured detector without producing an aggregate flagging decision or Guard screening log. Use for analysis and tuning, not runtime allow/block - lakera_guard_get_policy(policy_id: string) — Retrieve an Enterprise Lakera policy by ID, including its detector configuration, custom guardrails, version, and assigned projects. - lakera_guard_get_project(project_id: string) — Retrieve an Enterprise Lakera project by ID, including its assigned policy, metadata, and detect-or-flag action. - lakera_guard_screen_content(payload?: boolean, dev_info?: boolean, messages: object[], metadata?: object, breakdown?: boolean, project_id?: string) — Screen the latest LLM or agent interaction with Lakera Guard and return the policy decision. Use this for runtime allow/block decisions; earlier messages provide context, but only the latest interacti - lakera_guard_update_policy(name: string, detectors?: object[], policy_id: string, default_threshold: string, custom_guardrail_ids?: string[]) — Replace an Enterprise Lakera policy's complete configuration and create a new policy version. Omitted detectors or custom guardrails are removed, so retrieve the policy first when preserving existing - lakera_guard_update_project(name: string, action?: string, policy_id?: string, project_id: string, project_metadata?: object) — Update an Enterprise Lakera project by ID. Name is required by the official request schema; retrieve the project first when preserving its current name or other optional settings. ## Example prompts - "What can I do in Lakera Guard?" - "Show me a summary of my Lakera Guard account" ## Links Docs: https://mcp.ai/docs/mcps/lakera_guard Website: https://mcp.ai/mcps/lakera_guard