Unity AI Gateway
Overview
Product details compiled from public sources, each with a citation.
Matrix Coverage
Where this product defends, by asset class and NIST CSF function. The Coverage column shows whether each asset is Primary, Secondary, or Adjacent to what the product does. The table omits empty rows and columns.
| Asset class | Identify | Protect | Detect | Coverage | Source |
|---|---|---|---|---|---|
| AI Orchestration Tools | Secondary | 3 | |||
| AI Gateways and Routers | Identify: Not covered | Primary | 2 | ||
| Runtime AI Data | Identify: Not covered | Secondary | 1 |
Framework Relevance
These frameworks include controls relevant to the asset classes Unity AI Gateway defends. This is an editorial inference from the AI Defense Matrix asset-level crossmap, not a statement that Databricks implements these controls or is certified against them.
Expand Collapse
| Framework | Asset class | Relevant controls |
|---|---|---|
| NIST IR 8596 | AI Orchestration Tools | Agents as deployed artifacts (orchestration view; see AI Agent Identities row for the principal view); system prompts and templates |
| AI Gateways and Routers | AI data flows; APIs; inference endpoints (traffic side); model registries and dataset sources | |
| Runtime AI Data | Prompts (runtime); inference data | |
| CSA AI Controls Matrix | AI Orchestration Tools | Application and Interface Security; Supply Chain Management |
| AI Gateways and Routers | Infrastructure Security; Interoperability and Portability | |
| Runtime AI Data | Data Security and Privacy Lifecycle Management; Application and Interface Security | |
| ISO 42001 | AI Orchestration Tools | A.6 AI system life cycle; A.5 Assessing impacts of AI systems |
| AI Gateways and Routers | A.8 Information for interested parties; A.9 Use of AI systems; A.10 Third-party and customer relationships | |
| Runtime AI Data | A.7 Data for AI systems; A.8 Information for interested parties | |
| Google SAIF | AI Orchestration Tools | Secure the AI supply chain; application and pipeline security; agent orchestration controls |
| AI Gateways and Routers | Harden and monitor infrastructure; network-level access and egress controls | |
| Runtime AI Data | Expand AI red-teaming; runtime input and output safety; prompt defense | |
| SANS Critical AI Security Guidelines | AI Orchestration Tools | Secure Agentic Systems and AI Autonomy Controls (defined function scope; execution isolation; API and function-call gating); Limit Model Behavior (focused functionality; access controls outside the model) |
| AI Gateways and Routers | Conventional Security Controls (authenticate and control access to inference APIs; API key management); Model I/O Handling (rate limiting; egress output filtering); Monitoring (interaction and API-usage logging) | |
| Runtime AI Data | Model I/O Handling (sanitize, validate, and filter inputs and outputs; segregate user and system prompts; multilayered prompt-injection defense); Conventional Security Controls (protect augmentation and RAG data with vector-store access controls and validation); Data Minimization and Obfuscation (limit sensitive prompt content; context-window management); Limit Model Behavior (AI guardrails) | |
| MITRE ATLAS | AI Orchestration Tools | AML.T0051 LLM Prompt Injection; AML.T0054 LLM Jailbreak; AML.T0016 Obtain Capabilities (malicious plugins) |
| AI Gateways and Routers | AML.T0057 LLM Data Leakage; AML.T0024 Exfiltration via AI Inference API (network-side observation) | |
| Runtime AI Data | AML.T0051 LLM Prompt Injection; AML.T0054 LLM Jailbreak; AML.T0056 Extract LLM System Prompt | |
| OWASP AI Exchange | AI Orchestration Tools | Development-time threats: agent framework supply chain; runtime threats: plugin abuse, prompt injection via tools |
| AI Gateways and Routers | Runtime threats: data leakage via AI egress; network-level access control gaps | |
| Runtime AI Data | Input threats: prompt injection, adversarial inputs, evasion; runtime threats: RAG poisoning, memory tampering | |
| OWASP LLM Top 10 | AI Orchestration Tools | LLM01 Prompt Injection; LLM05 Improper Output Handling; LLM07 System Prompt Leakage; LLM10 Unbounded Consumption |
| AI Gateways and Routers | LLM10 Unbounded Consumption (cost and rate control); shadow AI egress and output handling | |
| Runtime AI Data | LLM01 Prompt Injection; LLM02 Sensitive Information Disclosure; LLM08 Vector and Embedding Weaknesses; LLM05 Improper Output Handling | |
| OWASP Agentic Security Top 10 | AI Orchestration Tools | ASI01 Agent Goal Hijack; ASI02 Tool Misuse and Exploitation; ASI05 Unexpected Code Execution (RCE); ASI07 Insecure Inter-Agent Communication; ASI08 Cascading Failures; ASI10 Rogue Agents |
| AI Gateways and Routers | ASI07 Insecure Inter-Agent Communication; ASI02 Tool Misuse and Exploitation (egress and tool-invocation scope); ASI04 Agentic Supply Chain Vulnerabilities (MCP and tool-registry trust) | |
| Runtime AI Data | ASI06 Memory & Context Poisoning; ASI01 Agent Goal Hijack (via prompt injection in runtime inputs) |
Provenance
Last sourced 2026-06-14.
Expand Collapse
Sources
- Unity AI Gateway endpoint configuration documentation
- “Guardrails prevent the model from interacting with unsafe and harmful content that is detected in model inputs and outputs.”
- Unity AI Gateway serving endpoints documentation
- “It is a centralized service that brings governance, monitoring, and production readiness to model serving endpoints.”
- Model Context Protocol (MCP) on Databricks
- “Connect to MCP servers hosted outside Databricks using managed connections, and register them as Unity Catalog securables to govern access, filter tools, and apply service policies.”
- Databricks Unity AI Gateway product page
Changelog
-
Refreshed description and added MCP-server coverage; product is in beta.
-
Refined matrix coverage and primary function.
-
Added to the catalog from the Databricks documentation. Formerly documented as Mosaic AI Gateway; AI Guardrails are in public preview and the redesigned gateway experience is in beta.
Found an error? Corrections are welcome. Suggest an edit.