# Enkrypt AI

- [Documentation](https://docs.enkryptai.com/home/introduction.md): Comprehensive AI security, guardrails, and risk management platform
- [Introduction](https://docs.enkryptai.com/get-started/introduction.md): Welcome to the Enkrypt AI Guardrails documentation
- [Quickstart](https://docs.enkryptai.com/get-started/quickstart.md): Start using Guardrails in under 5 minutes
- [OpenAI Compliance API Integration](https://docs.enkryptai.com/get-started/openai-compliance-api.md): Connect Enkrypt AI Guardrails to the OpenAI Compliance API to monitor your ChatGPT Enterprise workspace
- [Model Provider Integration](https://docs.enkryptai.com/get-started/Model_Provider_Integration.md)
- [Detect](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Detect.md)
- [Batch Detect](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Batch_Detect.md)
- [Batch Detect Using Policy](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Batch_Detect_Using_Policy.md)
- [Prompt Injection](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Prompt_Injection.md)
- [Topic Detector](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Topic_Detector.md)
- [Keyword Detector](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Keyword_Detector.md)
- [NSFW Detector](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/NSFW_Detector.md)
- [Toxicity Detector](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Toxicity_Detector.md)
- [PII Detector](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/PII_Detector.md)
- [System Prompt Leak Detector](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/System_Prompt_Leak_Detector.md)
- [Copyright IP Leak Detector](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Copyright_IP_Leak_Detector.md)
- [Policy Violation Detector](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Policy_Violation_Detector.md)
- [Bias Detector](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Bias_Detector.md)
- [Sponge Attack Detector](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Sponge_Attack_Detector.md)
- [Scan Url](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Scan_Url.md)
- [Scan Pdf](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Scan_Pdf.md)
- [Detect Image](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Detect_Image.md)
- [Detect Audio](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Detect_Audio.md)
- [Hallucination](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Hallucination.md)
- [Adherence](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Adherence.md)
- [Relevancy](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Relevancy.md)
- [PII Anonymization](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/PII_Anonymization.md)
- [Guardrails Guardrail](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Guardrails_Guardrail.md)
- [Guardrail Detect](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Guardrail_Detect.md)
- [Guardrail Batch Detect](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Guardrail_Batch_Detect.md)
- [Guardrail Scan Url](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Guardrail_Scan_Url.md)
- [Guardrail Scan Pdf](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Guardrail_Scan_Pdf.md)
- [Guardrail Detect Image](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Guardrail_Detect_Image.md)
- [Guardrail Detect Audio](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Guardrail_Detect_Audio.md)
- [Guardrails Policy](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Guardrails_Policy.md)
- [Policy Scan url](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Policy_Scan_url.md)
- [Policy Scan Pdf](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Policy_Scan_Pdf.md)
- [Policy Detect Image](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Policy_Detect_Image.md)
- [Policy Detect Audio](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Policy_Detect_Audio.md)
- [Policy Batch Detect](https://docs.enkryptai.com/api-introductions/guardrails-api-reference/guardrail-introductions/Policy_Batch_Detect.md)
- [Enkrypt AI Red Teaming](https://docs.enkryptai.com/get-started/redteam/introduction.md): Comprehensive security testing for AI models, agents, and applications
- [Quickstart](https://docs.enkryptai.com/get-started/redteam/quickstart.md): Submit your first red team run and read the vulnerability report
- [What's New](https://docs.enkryptai.com/get-started/redteam/changelog.md): What changed in the Red Team revamp — the current /rt API versus the previous /redteam API
- [Payload Guide](https://docs.enkryptai.com/get-started/redteam/payload-guide.md): Overview and quick reference for building Red Team API payloads
- [Risk Category Catalog](https://docs.enkryptai.com/get-started/redteam/test-catalog.md): The complete taxonomy of risk categories and sub-categories the Red Team API tests for, and the compliance frameworks they map onto
- [Agent Testing Guide](https://docs.enkryptai.com/get-started/redteam/agent-test-catalog.md): How to red team AI agents with tool use and autonomous capabilities — configuration, the risks that matter most, and how tool specifications shape the tests generated
- [Attack Methods Reference](https://docs.enkryptai.com/get-started/redteam/attack-methods-reference.md): All 21 attack techniques available in the Enkrypt AI Red Team API, what each does, and which modality it needs
- [Configuration Reference](https://docs.enkryptai.com/get-started/redteam/configuration-reference.md): Field-by-field reference for every block of a Red Team API payload
- [Payload Examples](https://docs.enkryptai.com/get-started/redteam/examples.md): Complete, ready-to-run payload examples for the Red Team API
- [Testing Models Across Providers](https://docs.enkryptai.com/get-started/RedTeam_Models.md): Target configuration for OpenAI, Anthropic, Bedrock, Azure, Gemini, Together, Replicate, HuggingFace and OpenAI-compatible endpoints
- [Red Teaming Through the Relay Bridge](https://docs.enkryptai.com/get-started/redteam/relay-bridge.md): End-to-end walkthrough: red-team an LLM inside your own network over a single outbound connection, with no inbound firewall rule
- [Quickstart](https://docs.enkryptai.com/get-started/ai-proxy-quickstart.md)
- [MCP Hub](https://docs.enkryptai.com/api-introductions/mcp-hub-api-reference/introduction.md)
- [MCP Registry Servers](https://docs.enkryptai.com/api-introductions/mcp-registry-servers-api-reference/introduction.md)
- [MCP Gateways](https://docs.enkryptai.com/api-introductions/mcp-gateways-api-reference/introduction.md)
- [MCP Playground](https://docs.enkryptai.com/api-introductions/mcp-playground-api-reference/introduction.md)
- [Skill Scanner](https://docs.enkryptai.com/api-introductions/skill-scanner-api-reference/introduction.md)
- [Introduction](https://docs.enkryptai.com/onprem-installation/introduction.md)
- [Infrastructure Requirements](https://docs.enkryptai.com/onprem-installation/infra-requirement.md)
- [Configuration and Installation](https://docs.enkryptai.com/onprem-installation/configuration-requirement.md)
- [Preflight Checks](https://docs.enkryptai.com/onprem-installation/preflight.md): Validate infrastructure and cluster requirements before installing the Helm chart.
- [Helm Installation](https://docs.enkryptai.com/onprem-installation/helm-installation.md)
- [Architecture Overview](https://docs.enkryptai.com/onprem-installation/architecture.md)
- [Post Installation](https://docs.enkryptai.com/onprem-installation/post-installation.md): Follow these steps after installing the helm chart.
- [Uninstallation](https://docs.enkryptai.com/onprem-installation/uninstall.md): Completely remove the Helm release and all associated Kubernetes resources.
- [Overview](https://docs.enkryptai.com/api-reference/introduction.md): Comprehensive API documentation for Enkrypt AI services
- [Infer Document](https://docs.enkryptai.com/api-reference/coc-api-reference/endpoint/infer-document.md): Infer a policy questionnaire from an uploaded PDF or pasted text (Policy Wizard API 1)
- [Generate Rules](https://docs.enkryptai.com/api-reference/coc-api-reference/endpoint/generate-rules.md): Generate guardrail rules from the questionnaire (Policy Wizard API 2)
- [Add Policy](https://docs.enkryptai.com/api-reference/coc-api-reference/endpoint/add-policy.md): Create a new Code of Conduct policy with the rules generated from the atomizer
- [Get Policy](https://docs.enkryptai.com/api-reference/coc-api-reference/endpoint/get-policy.md): Retrieve a Code of Conduct policy by name
- [Modify Policy](https://docs.enkryptai.com/api-reference/coc-api-reference/endpoint/modify-policy.md): Update an existing Code of Conduct policy
- [Delete Policy](https://docs.enkryptai.com/api-reference/coc-api-reference/endpoint/delete-policy.md): Delete an existing Code of Conduct policy
- [List Policies](https://docs.enkryptai.com/api-reference/coc-api-reference/endpoint/list-policies.md): List all Code of Conduct policies with pagination support
- [Health Check](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/health-check.md)
- [Status Check](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/status.md)
- [Models Loaded](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/models.md)
- [Guardrails Detect](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/detect.md): Runs the enabled detectors on a text input. For the policy_violation detector: if its config's `rules` array is present it takes precedence over `policy_text`, and the response's details.policy_violation includes a `violated_rules` array; if `rules` is absent, legacy `policy_text` behavior is unchan…
- [Guardrails Batch Detect](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/batch-detect.md): Runs the enabled detectors on multiple text inputs. For the policy_violation detector: if its config's `rules` array is present it takes precedence over `policy_text`, and each result's details.policy_violation includes a `violated_rules` array; if `rules` is absent, legacy `policy_text` behavior is…
- [Scan URL](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/scan-url.md): Scan a URL for security threats including injection attacks and policy violations
- [Scan PDF](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/scan-pdf.md): Scan a PDF for security threats including injection attacks and policy violations
- [Detect Image](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/detect-image.md): Analyze an image with text using individual multimodal guardrails detectors
- [Detect Audio](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/detect-audio.md): Analyze audio with text using individual multimodal guardrails detectors
- [Guardrail Detect Image](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/guardrail-detect-image.md): Analyze an image with text using a saved guardrail with input/output mode selection
- [Guardrail Detect Audio](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/guardrail-detect-audio.md): Analyze audio with text using a saved guardrail with input/output mode selection
- [PII anonymization and de-anonymization](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/pii.md)
- [Detect Hallucination](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/hallucination.md)
- [Guardrails Adherence](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/adherence.md)
- [Guardrails Relevancy](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/relevancy.md)
- [Add Guardrail](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/add-guardrail.md): Create a new guardrail with separate input and output detector configurations
- [Get Guardrail](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/get-guardrail.md): Retrieve a guardrail by name
- [Modify Guardrail](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/modify-guardrail.md): Update an existing guardrail
- [Delete Guardrail](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/delete-guardrail.md): Delete an existing guardrail
- [List Guardrails](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/list-guardrails.md): List all guardrails with pagination support
- [Detect with Guardrail](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/detect-using-guardrail.md): Detect threats in text using a saved guardrail with input/output mode selection
- [Batch Detect with Guardrail](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/batch-detect-using-guardrail.md): Analyze multiple text inputs using a saved guardrail with input/output mode selection
- [Guardrail Scan URL](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/guardrail-scan-url.md): Scan a URL for security threats using a saved guardrail
- [Guardrail Scan PDF](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/guardrail-scan-pdf.md): Scan a PDF for security threats using a saved guardrail
- [Create Model](https://docs.enkryptai.com/api-reference/models-api-reference/endpoint/add-model.md)
- [Get Model](https://docs.enkryptai.com/api-reference/models-api-reference/endpoint/get-model.md)
- [Modify Model](https://docs.enkryptai.com/api-reference/models-api-reference/endpoint/modify-model.md)
- [Delete Model](https://docs.enkryptai.com/api-reference/models-api-reference/endpoint/delete-model.md)
- [List Models](https://docs.enkryptai.com/api-reference/models-api-reference/endpoint/list-models.md): List all models with pagination support
- [Get Defaults](https://docs.enkryptai.com/api-reference/models-api-reference/endpoint/get-defaults.md)
- [Run Redteam](https://docs.enkryptai.com/api-reference/redteam-v2-api-reference/endpoint/run-redteam.md)
- [Run Redteam with saved model](https://docs.enkryptai.com/api-reference/redteam-v2-api-reference/endpoint/run-redteam-saved-model.md): Identical to `POST /rt/redteam`, except the system under test is a **saved model** named in the `X-Enkrypt-Model` / `X-Enkrypt-Model-Version` headers instead of an inline `target`. The gateway resolves the model and fills in `target` before the request reaches the Red Team service.
- [Run Threat Modeling](https://docs.enkryptai.com/api-reference/redteam-v2-api-reference/endpoint/run-threat-modeling.md): One-shot: analyze → generate composed inside the datagen worker.
- [Run Threat Modeling Categories](https://docs.enkryptai.com/api-reference/redteam-v2-api-reference/endpoint/run-threat-modeling-categories.md): Phase 1 (Analyze) — synchronous. Runs chunker → router and returns the reviewable profile. No run created, nothing persisted.
- [Run Threat Modeling Data](https://docs.enkryptai.com/api-reference/redteam-v2-api-reference/endpoint/run-threat-modeling-data.md): Phase 2 (Generate + Verify) — takes the edited profile back and runs the real pipeline via the datagen worker.
- [Run Playground](https://docs.enkryptai.com/api-reference/redteam-v2-api-reference/endpoint/run-playground.md)
- [Run Playground with saved model](https://docs.enkryptai.com/api-reference/redteam-v2-api-reference/endpoint/run-playground-saved-model.md): Identical to `POST /rt/playground`, except the system under test is a **saved model** named in the `X-Enkrypt-Model` / `X-Enkrypt-Model-Version` headers instead of an inline `target`. The gateway resolves the model and fills in `target` before the request reaches the Red Team service.
- [Submit Eval Batch](https://docs.enkryptai.com/api-reference/redteam-v2-api-reference/endpoint/submit-eval.md): Submit a batch of (query, response, test_type) rows to the evaluator.
- [Run Leaderboard](https://docs.enkryptai.com/api-reference/redteam-v2-api-reference/endpoint/run-leaderboard.md): Start a red team run whose results are published to the **LLM safety leaderboard**.
- [Run Leaderboard with saved model](https://docs.enkryptai.com/api-reference/redteam-v2-api-reference/endpoint/run-leaderboard-saved-model.md): Identical to `POST /rt/leaderboard`, except the system under test is a **saved model** named in the `X-Enkrypt-Model` / `X-Enkrypt-Model-Version` headers instead of an inline `target`. The gateway resolves the model and fills in `target` before the request reaches the Red Team service.
- [Get Run Status](https://docs.enkryptai.com/api-reference/redteam-v2-api-reference/endpoint/get-run-status.md): The run record's current state.
- [Get Run Records](https://docs.enkryptai.com/api-reference/redteam-v2-api-reference/endpoint/get-run-records.md): Return the rows produced/judged on a run.
- [Get Run Results](https://docs.enkryptai.com/api-reference/redteam-v2-api-reference/endpoint/get-run-results.md): The finished run's scored summary.
- [Get Compliance Report](https://docs.enkryptai.com/api-reference/redteam-v2-api-reference/endpoint/get-compliance-report.md)
- [Send Signal](https://docs.enkryptai.com/api-reference/redteam-v2-api-reference/endpoint/send-signal.md)
- [Resume Run](https://docs.enkryptai.com/api-reference/redteam-v2-api-reference/endpoint/resume-run.md)
- [Stream Run Events](https://docs.enkryptai.com/api-reference/redteam-v2-api-reference/endpoint/stream-run-events.md)
- [Stream Run Logs (WebSocket)](https://docs.enkryptai.com/api-reference/redteam-v2-api-reference/endpoint/stream-run-logs.md): Stream a run's live `app.log` over a **WebSocket** as the job progresses — the same log the dashboard's run view shows.
- [Get Dataset](https://docs.enkryptai.com/api-reference/redteam-v2-api-reference/endpoint/get-dataset.md): Return the generated dataset as an array of full DatasetRecord JSON.
- [Model Health](https://docs.enkryptai.com/api-reference/redteam-v2-api-reference/endpoint/model-health.md): Send one probe prompt to the target and report whether it answered.
- [Model Health with saved model](https://docs.enkryptai.com/api-reference/redteam-v2-api-reference/endpoint/model-health-saved.md): Same probe as `/rt/model-health`, against a **saved model** named in the `X-Enkrypt-Model` / `X-Enkrypt-Model-Version` headers. No request body — the gateway builds the target configuration from the stored model.
- [Connect a relay bridge (WebSocket)](https://docs.enkryptai.com/api-reference/redteam-v2-api-reference/endpoint/relay-bridge-connect.md): The socket a **relay bridge** opens to Enkrypt so that a model with no inbound network exposure can still be red-teamed. See `target.connect_via_relay` on `POST /rt/redteam` for the request side.
- [Relay bridge status](https://docs.enkryptai.com/api-reference/redteam-v2-api-reference/endpoint/relay-bridge-status.md): Report whether a **relay bridge** of yours currently holds a live connection to Enkrypt.
- [Get findings based on summary](https://docs.enkryptai.com/api-reference/redteam-v2-api-reference/endpoint/get-findings.md): Analyzes a run's results summary (the body of `GET /rt/runs/{run_id}/results`) and returns key findings highlighting vulnerabilities, risks and areas for ongoing monitoring.
- [Generate a system prompt for risk mitigation based on red teaming test results](https://docs.enkryptai.com/api-reference/redteam-v2-api-reference/endpoint/risk-mitigation-system-prompt.md): Given a run's results summary, returns a hardened system prompt that mitigates the risks the run surfaced. Pass the current `system_prompt` to have it revised rather than written from scratch.
- [Generate a guardrail and policy for risk mitigation based on summary](https://docs.enkryptai.com/api-reference/redteam-v2-api-reference/endpoint/risk-mitigation-guardrails-policy.md): Given a run's results summary, returns a Guardrails detector configuration that blocks the behaviours the run surfaced. Feed the returned `guardrails_policy` straight into the Guardrails APIs.
- [Red Team Health](https://docs.enkryptai.com/api-reference/redteam-v2-api-reference/endpoint/health.md): Liveness probe for the Red Team service.
- [Red Team Status Check](https://docs.enkryptai.com/api-reference/redteam-v2-api-reference/endpoint/status-check.md): Readiness probe for the Red Team service.
- [Create Deployment](https://docs.enkryptai.com/api-reference/deployments-api-reference/endpoint/add-deployment.md)
- [Get Deployment](https://docs.enkryptai.com/api-reference/deployments-api-reference/endpoint/get-deployment.md)
- [Modify Deployment](https://docs.enkryptai.com/api-reference/deployments-api-reference/endpoint/modify-deployment.md)
- [Delete Deployment](https://docs.enkryptai.com/api-reference/deployments-api-reference/endpoint/delete-deployment.md)
- [List Deployments](https://docs.enkryptai.com/api-reference/deployments-api-reference/endpoint/list-deployments.md): List all deployments with pagination support
- [Get Allowed Config](https://docs.enkryptai.com/api-reference/deployments-api-reference/endpoint/get-allowed-config.md)
- [AI Chat Completions Proxy Endpoint](https://docs.enkryptai.com/api-reference/ai-proxy-api-reference/endpoint/chat-completions.md)
- [AI Completions Proxy Endpoint](https://docs.enkryptai.com/api-reference/ai-proxy-api-reference/endpoint/completions.md)
- [Start a New Vulnerability Scan](https://docs.enkryptai.com/api-reference/mcp-hub-api-reference/endpoint/scan.md): Creates a new vulnerability scan job for an MCP server source repository (GitHub URL or npm package). The scan runs asynchronously in the background; use the returned `job_id` to check status and retrieve results.
- [Scan a Hosted MCP Server](https://docs.enkryptai.com/api-reference/mcp-hub-api-reference/endpoint/hosted-scan.md): Create a new hosted MCP server scan job. Connects to a live MCP server, discovers tools/resources/prompts, and runs security analysis on the metadata. The scan runs asynchronously in the background.
- [Scan MCP Servers from Config JSON](https://docs.enkryptai.com/api-reference/mcp-hub-api-reference/endpoint/hosted-scan-from-config.md): Parse an MCP config JSON (Claude/Cursor format with `mcpServers` key) and create one scan job per server entry. Each entry produces an independent hosted scan.
- [Get Scan Job Status](https://docs.enkryptai.com/api-reference/mcp-hub-api-reference/endpoint/get-status.md): Get the status of a scan job including progress information and per-tool scan results. Works for both source and hosted scans.
- [Get Complete Scan Results](https://docs.enkryptai.com/api-reference/mcp-hub-api-reference/endpoint/get-results.md): Get the complete results of a scan job including all vulnerabilities, tools scanned, and detailed analysis. Results are only available for completed jobs.
- [List Scans](https://docs.enkryptai.com/api-reference/mcp-hub-api-reference/endpoint/list-scans.md): List scan jobs (source and hosted) ordered by `(created_at DESC, job_id DESC)` with **opaque cursor pagination**. Supports filtering by visibility, status, scan type, repository name, `source_url`, `source_version`, and vulnerability count. Use `latest_only=true` to collapse repeated scans of the sa…
- [Get MCP Hub Scan Statistics](https://docs.enkryptai.com/api-reference/mcp-hub-api-reference/endpoint/dashboard-stats.md): Aggregate, read-only statistics across all MCP Hub scans — total servers and tools scanned, vulnerability totals, the severity breakdown, and the most common vulnerability types. Intended for dashboards and reporting.
- [Get MCP Hub API Usage Summary](https://docs.enkryptai.com/api-reference/mcp-hub-api-reference/endpoint/usage.md): Self-service usage insights for your organization's gated MCP Hub API calls over a time window — totals, the success count, a per-endpoint breakdown (plus the top endpoints), a per-project breakdown, an HTTP status-class split, and a daily time-series. Returns **aggregate counts only** — no request…
- [Create MCP Registry Server](https://docs.enkryptai.com/api-reference/mcp-registry-servers-api-reference/endpoint/add-server.md): Add a new MCP registry server whitelisted from MCP Hub. The server can be referenced by gateways to build complete MCP configurations. The server is scoped to the default registry; the registry is auto-created if it does not exist.
- [Bulk-create MCP Registry Servers (atomic)](https://docs.enkryptai.com/api-reference/mcp-registry-servers-api-reference/endpoint/bulk-add-servers.md): Insert up to 100 registry servers in a single atomic batch. **All-or-nothing** — if any row fails validation or violates a constraint (e.g., duplicate `saved_name`), no rows are inserted and the request returns an error. All servers in the batch are scoped to the default registry; the registry is au…
- [Get MCP Registry Server](https://docs.enkryptai.com/api-reference/mcp-registry-servers-api-reference/endpoint/get-server.md): Retrieve details of a specific MCP registry server by saved_name and version. Requires X-Enkrypt-MCP-Registry-Server header.
- [Update MCP Registry Server](https://docs.enkryptai.com/api-reference/mcp-registry-servers-api-reference/endpoint/modify-server.md): Update an existing MCP registry server. Only provided fields will be updated. Requires X-Enkrypt-MCP-Registry-Server header.
- [Delete MCP Registry Server](https://docs.enkryptai.com/api-reference/mcp-registry-servers-api-reference/endpoint/delete-server.md): Soft delete an MCP registry server (sets is_deleted flag). Requires X-Enkrypt-MCP-Registry-Server header.
- [List MCP Registry Servers](https://docs.enkryptai.com/api-reference/mcp-registry-servers-api-reference/endpoint/list-servers.md): List all MCP registry servers for the authenticated user with pagination support.
- [List Gateways by Registry Server](https://docs.enkryptai.com/api-reference/mcp-registry-servers-api-reference/endpoint/list-gateways-by-server.md): Returns all MCP gateways for the project whose servers_config.servers[] includes a server matching the given (saved_name, server_version). Requires X-Enkrypt-MCP-Registry-Server header.
- [Create MCP Gateway](https://docs.enkryptai.com/api-reference/mcp-gateways-api-reference/endpoint/add-gateway.md): Create a new MCP gateway that references one or more registry servers. Overrides can be applied at two levels: `servers_config.common_overrides` (applied to every server in the gateway) and per-server entries inside `servers_config.servers[]` (apply to just that server). Both may be set, but **`comm…
- [Get MCP Gateway](https://docs.enkryptai.com/api-reference/mcp-gateways-api-reference/endpoint/get-gateway.md): Retrieve details of a specific MCP gateway by gateway_saved_name and version. Requires X-Enkrypt-MCP-Gateway header.
- [Get Expanded MCP Gateway Configuration](https://docs.enkryptai.com/api-reference/mcp-gateways-api-reference/endpoint/get-gateway-config.md): Retrieve the complete expanded MCP gateway configuration. Each entry in `expanded_servers[]` carries `mcp_config` = registry server's base `mcp_config` merged with that entry's per-server overrides. **Gateway-wide `servers_config.common_overrides` always wins**: for any override key (`input_guardrai…
- [Update MCP Gateway](https://docs.enkryptai.com/api-reference/mcp-gateways-api-reference/endpoint/modify-gateway.md): Partially update an existing MCP gateway. The `servers_config` body is **deep-merged** onto the persisted config — fields you don't send are left untouched. Semantics:
- [Delete MCP Gateway](https://docs.enkryptai.com/api-reference/mcp-gateways-api-reference/endpoint/delete-gateway.md): Soft delete an MCP gateway (sets is_deleted flag). Requires X-Enkrypt-MCP-Gateway header.
- [List MCP Gateways](https://docs.enkryptai.com/api-reference/mcp-gateways-api-reference/endpoint/list-gateways.md): List all MCP gateways for the authenticated user with pagination support.
- [Test MCP Server Connectivity](https://docs.enkryptai.com/api-reference/mcp-playground-api-reference/endpoint/test-server.md): Tests connectivity to an MCP server by spawning it (inside a sandbox), running `session.initialize()`, and returning the server's reported name / version / description and connection latency.
- [Get MCP Server Tools](https://docs.enkryptai.com/api-reference/mcp-playground-api-reference/endpoint/get-tools.md): Discovers all tools exposed by an MCP server. Spawns the server inside a sandbox, initialises a session, calls `list_tools()`, and returns the server metadata together with every tool's name, description, and input schema.
- [Call MCP Server Tool](https://docs.enkryptai.com/api-reference/mcp-playground-api-reference/endpoint/call-tool.md): Executes a tool call on an MCP server — the playground API for testing and debugging tools by directly invoking them with parameters.
- [Submit a Skill Scan](https://docs.enkryptai.com/api-reference/skill-scanner-api-reference/endpoint/scan.md): Queues a security scan of one agent skill: a git repository plus the path of the skill directory inside it. The scan runs asynchronously (roughly 30–90 seconds); poll the returned `scan_id` with Get Skill Scan.
- [Get Skill Scan](https://docs.enkryptai.com/api-reference/skill-scanner-api-reference/endpoint/get-scan.md): Returns one scan: its status, the inputs, and — once `status` is `succeeded` — the verdict, risk level, findings count, token usage and the full `report`.
- [Get Skill Scan Report](https://docs.enkryptai.com/api-reference/skill-scanner-api-reference/endpoint/get-report.md): Returns only the report document for a completed scan — the same object as the `report` field of Get Skill Scan, without the surrounding record. Use this when you already have the metadata and want just the findings.
- [List Skill Scans](https://docs.enkryptai.com/api-reference/skill-scanner-api-reference/endpoint/list-scans.md): Lists your skill scans as summaries, without the full reports. Page with `limit` / `offset`.
- [Skill Scanner Health](https://docs.enkryptai.com/api-reference/skill-scanner-api-reference/endpoint/health.md): Liveness and configuration summary for the Skill Scanner service.
- [v2 Models List](https://docs.enkryptai.com/api-reference/leaderboard-api-reference/endpoint/v2/models/models-list.md): Retrieves a list of all the models
- [v2 Scores list](https://docs.enkryptai.com/api-reference/leaderboard-api-reference/endpoint/v2/scores/scores-list.md): Retrieves a list of scores of all the models
- [v2 Model Score](https://docs.enkryptai.com/api-reference/leaderboard-api-reference/endpoint/v2/scores/model-score.md): Retrieves score of a single model
- [v2 Model Detail](https://docs.enkryptai.com/api-reference/leaderboard-api-reference/endpoint/v2/details/model-detail.md): Retrieve details of a specific model based on the risk type and sub-type.
- [v2 Model Summary](https://docs.enkryptai.com/api-reference/leaderboard-api-reference/endpoint/v2/summary/model-summary.md): Retrieve summary of a specific model based on the risk type and sub-type.
- [v2 Model Rank](https://docs.enkryptai.com/api-reference/leaderboard-api-reference/endpoint/v2/rank/model-rank.md): Retrieves model rank
- [v2 Models Risk Percentiles](https://docs.enkryptai.com/api-reference/leaderboard-api-reference/endpoint/v2/percentiles/models-risk-percentiles.md)
- [Datasets Add Task](https://docs.enkryptai.com/api-reference/datasets-api-reference/endpoint/add-task.md)
- [Datasets Get Task Status](https://docs.enkryptai.com/api-reference/datasets-api-reference/endpoint/task-status.md)
- [Datasets Get Task](https://docs.enkryptai.com/api-reference/datasets-api-reference/endpoint/get-task.md)
- [Datasets Get Datacard](https://docs.enkryptai.com/api-reference/datasets-api-reference/endpoint/get-datacard.md)
- [Datasets Get Dataset](https://docs.enkryptai.com/api-reference/datasets-api-reference/endpoint/get-dataset.md)
- [Datasets Get Summary](https://docs.enkryptai.com/api-reference/datasets-api-reference/endpoint/get-summary.md)
- [List Tasks](https://docs.enkryptai.com/api-reference/datasets-api-reference/endpoint/list-tasks.md): List all dataset tasks with pagination support
- [Add Policy (Legacy)](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/add-policy.md): Create a new policy for guardrails
- [Get Policy (Legacy)](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/get-policy.md): Retrieve a policy by name
- [Modify Policy (Legacy)](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/modify-policy.md): Update an existing policy
- [Delete Policy (Legacy)](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/delete-policy.md): Delete an existing policy
- [List Policies (Legacy)](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/list-policies.md): List all policies with pagination support
- [Detect with Policy (Legacy)](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/detect-using-policy.md)
- [Detect Image with Policy (Legacy)](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/detect-image-using-policy.md): Analyzes an image with text using a saved policy.
- [Detect Audio with Policy (Legacy)](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/detect-audio-using-policy.md): Analyzes audio with text using a saved policy.
- [Policy Batch Detect (Legacy)](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/batch-detect-using-policy.md): Analyze multiple text inputs using a specific policy
- [Policy Scan URL (Legacy)](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/policy-scan-url.md): Scan a URL for security threats using a specific policy
- [Policy Scan PDF (Legacy)](https://docs.enkryptai.com/api-reference/guardrails-api-reference/endpoint/policy-scan-pdf.md): Scan a PDF for security threats using a specific policy
- [Redteam Health](https://docs.enkryptai.com/api-reference/redteam-api-reference/endpoint/health.md)
- [Model Health (V3)](https://docs.enkryptai.com/api-reference/redteam-api-reference/endpoint/v3-model-health.md)
- [Model Health of saved model](https://docs.enkryptai.com/api-reference/redteam-api-reference/endpoint/model-health-saved.md)
- [Add Custom Task (V3)](https://docs.enkryptai.com/api-reference/redteam-api-reference/endpoint/v3-add-custom-task.md)
- [Add Custom Task with saved model (V3)](https://docs.enkryptai.com/api-reference/redteam-api-reference/endpoint/v3-model-add-custom-task.md)
- [Cancel Task](https://docs.enkryptai.com/api-reference/redteam-api-reference/endpoint/cancel-task.md)
- [Get Task](https://docs.enkryptai.com/api-reference/redteam-api-reference/endpoint/get-task.md)
- [Get Task Status](https://docs.enkryptai.com/api-reference/redteam-api-reference/endpoint/get-task-status.md)
- [Get Download Link](https://docs.enkryptai.com/api-reference/redteam-api-reference/endpoint/get-download-link.md): Get a download link for red team test results
- [Get Task Results Summary](https://docs.enkryptai.com/api-reference/redteam-api-reference/endpoint/get-results-summary.md)
- [Get Task Results Summary of a specific test type](https://docs.enkryptai.com/api-reference/redteam-api-reference/endpoint/get-summary-test-type.md)
- [Get Task Results Details](https://docs.enkryptai.com/api-reference/redteam-api-reference/endpoint/get-all-details.md)
- [Get Task Results Details of a specific test type](https://docs.enkryptai.com/api-reference/redteam-api-reference/endpoint/get-details-test-type.md)
- [Get findings based on summary](https://docs.enkryptai.com/api-reference/redteam-api-reference/endpoint/get-findings.md): Analyzes the provided red team summary and returns a list of key findings highlighting vulnerabilities, risks, and areas for ongoing monitoring.
- [Generate a system prompt for risk mitigation based on red teaming test results](https://docs.enkryptai.com/api-reference/redteam-api-reference/endpoint/risk-mitigation-system-prompt.md): Analyzes vulnerabilities and produces a system prompt with safety and compliance guidelines tailored to the risks identified.
- [Generate a guardrail and policy for risk mitigation based on summary](https://docs.enkryptai.com/api-reference/redteam-api-reference/endpoint/risk-mitigation-guardrails-policy.md): Analyzes red teaming test results and produces a system prompt with safety and compliance guidelines tailored to the risks identified.
- [List All Tasks](https://docs.enkryptai.com/api-reference/redteam-api-reference/endpoint/list-all-tasks.md): List all redteam tasks with pagination support
- [Model Health](https://docs.enkryptai.com/api-reference/redteam-api-reference/endpoint/model-health.md)
- [Add Task](https://docs.enkryptai.com/api-reference/redteam-api-reference/endpoint/add-task.md)
- [Add Task with saved model](https://docs.enkryptai.com/api-reference/redteam-api-reference/endpoint/model-add-task.md)
- [Add Custom Task](https://docs.enkryptai.com/api-reference/redteam-api-reference/endpoint/add-custom-task.md)
- [Add Custom Task with saved model](https://docs.enkryptai.com/api-reference/redteam-api-reference/endpoint/model-add-custom-task.md)
- [v1 Models List](https://docs.enkryptai.com/api-reference/leaderboard-api-reference/endpoint/v1/models/models-list.md): Retrieves a list of all the models
- [v1 Scores list](https://docs.enkryptai.com/api-reference/leaderboard-api-reference/endpoint/v1/scores/scores-list.md): Retrieves a list of scores of all the models
- [v1 Model Score](https://docs.enkryptai.com/api-reference/leaderboard-api-reference/endpoint/v1/scores/model-score.md): Retrieves score of a single model
- [v1 Model Detail](https://docs.enkryptai.com/api-reference/leaderboard-api-reference/endpoint/v1/details/model-detail.md): Retrieve details of a specific model based on the risk type and sub-type.
- [v1 Model Summary](https://docs.enkryptai.com/api-reference/leaderboard-api-reference/endpoint/v1/summary/model-summary.md): Retrieve summary of a specific model based on the risk type and sub-type.
- [v1 Model Rank](https://docs.enkryptai.com/api-reference/leaderboard-api-reference/endpoint/v1/rank/model-rank.md): Retrieves model rank
- [v1 Models Risk Percentiles](https://docs.enkryptai.com/api-reference/leaderboard-api-reference/endpoint/v1/percentiles/models-risk-percentiles.md)
- [Policy Atomizer](https://docs.enkryptai.com/api-reference/coc-api-reference/endpoint/policy-atomizer.md): Atomize a policy and get rules after analyzing a PDF document. Superseded by the Policy Wizard APIs (Infer Document + Generate Rules); kept for backward compatibility.
- [Getting Started with Python SDK](https://docs.enkryptai.com/sdk-reference/python/introduction.md)
- [Enkrypt AI OpenAPI Schema and Postman Collection](https://docs.enkryptai.com/schema-and-postman/introduction.md)
- [Resources](https://docs.enkryptai.com/resources/introduction.md): Additional resources and information about Enkrypt AI
- [Credits and Usage](https://docs.enkryptai.com/resources/credits.md): How Enkrypt AI meters and prices Guardrails, Red Team and AI Proxy usage when credit-based billing is enabled on your account
- [LLM Safety Leaderboard](https://docs.enkryptai.com/resources/leaderboard.md): Comprehensive safety rankings and risk assessments for large language models
- [AI Security Blog](https://docs.enkryptai.com/resources/blog.md): Latest trends, thought leadership, and insights in AI security
- [Research](https://docs.enkryptai.com/resources/research.md): Latest research findings, papers, and studies on AI safety and security
- [AI Risk Categories](https://docs.enkryptai.com/resources/ai-risk-categories.md): The risk taxonomy Enkrypt AI tests against — 8 categories, 35 sub-categories, and the compliance frameworks they map onto
- [Glossary](https://docs.enkryptai.com/resources/glossary.md): Definitions and explanations of key terms and concepts in AI security

## OpenAPI Specs

- [enkrypt-openapi](/enkrypt-openapi.json)
- [openapi-guardrails](/guardrails-api-reference/openapi-guardrails.json)
- [openapi](/leaderboard-api-reference/openapi.json)
- [openapi-generator-config](/openapi-generator-config.yaml)
- [openapitools](/openapitools.json)
- [package-lock](/package-lock.json)
- [package](/package.json)
- [openapi-redteam](/redteam-api-reference/openapi-redteam.json)