Lab Identity Governance Fabric · Learn

Agentic AI Gateways & Access Topology

what you'll learn: the third plane — agentgateway, Envoy AI Gateway, Cisco Secure Access, and how agents plug into the same identity truth

Topology at a glance

Agentic AI gateways and access topology across the three domains
The three gateways mediate agent→tool, agent→model, and user→app traffic; the identity fabric below governs every one of them, and the SSF bus revokes them in real time.
What we're solving for

The same identity truth that governs humans now governs agents, LLMs, and tools. Three gateways, each with a distinct job: agentgateway mediates MCP tools / servers, Envoy AI Gateway mediates LLM providers, and Cisco Secure Access mediates private apps (ZTNA) — every agent→tool, agent→model, and user→app call bound to an accountable human owner. Add a capability by speaking the gateway's protocol, not by wiring a bespoke connector — and revoke it in real time from the same signal bus that governs people.

Three planes, one identity

The fabric already splits into a slow, governed provisioning plane and a fast, event-driven signaling plane. Agentic AI adds a third: a mediation plane where gateways broker every agent/model/tool call — authorized against the same directory that provisions humans.

Plane 1 · Provisioning (state)

SCIM 2.0

Who has what. HRIS → IGA reconcile → ITSM change gate → grant/revoke on Duo, AD/Entra — and now agent identities into Duo Directory.

RFC 7643/7644 · create · update · deactivate
Plane 2 · Signaling (events)

SSF — CAEP / RISC

What just changed. One SSF transmitter, many receivers; each re-evaluates live. A session-revoked event reaches Duo, CII — and the gateways — at once.

SSF 1.0 · CAEP 1.0 · RISC · SET
Plane 3 · Agentic mediation (calls)

MCP · A2A · LLM · ZTNA

How agents act. Every MCP/A2A tool call, LLM call, and private-app reach is brokered by a gateway and authorized against the agent's identity and human sponsor.

agentgateway · Envoy AI Gateway · Secure Access

The mediation plane — components

Two of the gateways are open standards the lab now runs live — agentgateway for MCP tools and Envoy AI Gateway for the LLM plane; the rest are Cisco's agentic-security layer — one of which (Duo Agentic Identity) the lab already runs.

ComponentRoleOpen standard / productLab todayStatus
agentgatewayMCP tools / servers — routes, secures, observes agent↔tool & agent↔agent; per-tool-call Duo authorizationOSS · Solo.io → Linux Foundation / AAIF (Cisco-contributed)agentgateway + Duo Authorization Connector — live, federating a set of MCP tool servers (source control · docs · SIEM) behind per-call Duo authorizationlive
Envoy AI GatewayLLM providers — token limits, provider routing / fallback, model virtualization, guardrailsOSS · Envoy / CNCF (Tetrate + Bloomberg, v1.0)Envoy AI Gateway deployed as the LLM plane — fronts a model-proxy layer (multiple models, tiered keys: local / external / frontier), Duo-gatedlive
Cisco Secure AccessPrivate apps (ZTNA) — private-app access + device trust; Private-App API to grant/revoke appsCisco SSE (ZTNA/SWG/CASB) · AI-aware SASECF Access + Duo at the edgeedge live · API target
Duo Agentic IdentityPer-agent identity mapped to a human owner; fine-grained authz at the MCP gatewayCisco Duo IAM + MCP gatewayDuo Directory SCIM agents + sponsor + scoped tokenlive
Cisco AI DefenseScans MCP tool + A2A agent registrations for supply-chain threatsCisco (mcp-scanner · a2a-scanner)roadmap
Cisco Identity IntelligenceThe intelligence layer above — Oort scores humans; Astrix discovers/governs NHIs + agents; BloodHound Enterprise maps attack paths to Tier ZeroCisco (Oort = human ITDR · Astrix = NHI · SpecterOps BHE = attack-path APM)CII risk feed → IGA (live) · Astrix ↔ an NHI registry · BHE ↔ the tier-0 planehuman live · NHI + APM feeds
Cisco XDRDetection & response — correlates the identity vector (from CII) with endpoint · network · email · DNS; surfaces identity threats as incidents, then closes the loop — session-kill / quarantine enforced back through Duo, Secure Access, and ISECisco XDR · OCSF telemetry · ITDRSIEM detections + the SSF/CAEP bus stand in for the closed loop — detect → session-revokedlab stand-in
SSF/CAEPReal-time revoke — one signed SET drops the agent's token & its access (the enforcement leg XDR triggers)SSF 1.0 · CAEP · RISCSSF/CAEP-capable signaling — a signed SET drops the token & its accesslive

The agent request path

An agent never talks to a tool or a model directly. It presents its Duo Agentic Identity to a gateway, the gateway authorizes the call against Duo's engine (bound to the human sponsor), and only then does the request reach the tool or provider — every hop logged.

flowchart LR
  H[Human owner
accountable]:::h -->|sponsors| A[Agent
Duo Agentic Identity]:::a A -->|MCP tools| AGW{{agentgateway
MCP · live}}:::g A -->|LLM call| EAG{{Envoy AI Gateway
LLM · live}}:::g AGW --> DUO{Duo authz
allow / block per call}:::d EAG --> DUO DUO -->|allow| TOOL[MCP tools
GitHub · MS Learn · Splunk]:::t DUO -->|allow| LLM[LLM providers
Anthropic · OpenAI · local]:::t DUO -.deny.-> X[blocked + logged]:::x DEF[Cisco AI Defense]:::sc -.scans MCP/A2A on register.-> AGW classDef h fill:#101b16,stroke:#2c623a,color:#e6edf3; classDef a fill:#160f22,stroke:#3b3170,color:#e6edf3; classDef g fill:#1b2838,stroke:#a98f2a,color:#f0f6fc; classDef d fill:#25161a,stroke:#7a3038,color:#f0f6fc; classDef t fill:#16202e,stroke:#2c3e57,color:#e6edf3; classDef x fill:#25161a,stroke:#7a3038,color:#e5534b; classDef sc fill:#16202e,stroke:#31465f,color:#93a4bb;
Same on-behalf-of model as the human fabric: the agent is an NHI owned by a person; the gateway is the enforcement point; a denied call is blocked and logged, never silently dropped.

How it maps to the three domains

flowchart TB
  subgraph EDGE[apex / edge]
    CF[Cloudflare zone
+ tunnels]:::e ZT[CF Access + Duo
→ Cisco Secure Access]:::z end subgraph LAB[the lab] DIR[AD · Entra · Duo]:::l FAB[Identity fabric
HRIS→IGA→ITSM→CMDB + SSF]:::l GW[agentgateway MCP · live
Envoy AI GW = LLM · live]:::g end subgraph IDP[identity portal] PORT[Fabric portal]:::i CONS[governed consoles]:::i end CF --> ZT ZT -->|ZTNA private-app| CONS ZT --> PORT FAB -->|SCIM / Admin API| DIR FAB -->|grant → Private-App API| ZT FAB -->|CAEP / RISC revoke| ZT FAB -->|governs| GW classDef e fill:#16202e,stroke:#2c3e57,color:#e6edf3; classDef z fill:#1b2838,stroke:#3d6ea5,color:#f0f6fc; classDef l fill:#16202e,stroke:#2c3e57,color:#e6edf3; classDef g fill:#1b2838,stroke:#a98f2a,color:#f0f6fc; classDef i fill:#101b16,stroke:#2c623a,color:#e6edf3;
The apex domain is the edge (Cloudflare + ZTNA); the lab holds the directory, the fabric, and the gateways; the identity subdomain is the human front door. IGA drives Secure Access via the Private-App API; SSF drives real-time revoke.

How it ties to the identity model

Nothing here is a new trust model — it is the fabric's ownership model extended to non-human callers, enforced at a gateway instead of a login form.

Fabric conceptIn the agentic plane
Agent = NHI owned by a humanDuo Agentic Identity — each agent maps to an accountable human sponsor; a leaver cascades to the agents they own (re-own or retire)
The change gate (ITSM)A new tool/model/scope for an agent is an RFC — approved, then the gateway policy is updated; nothing self-grants
The grant (IGA)IGA drives Cisco Secure Access Private-App API — who may reach which console is a governed private-resource + ZTNA policy, not a firewall rule
The signal bus (SSF)A CAEP session-revoked / assurance-level-change pulls the agent's token at the gateway AND its ZTNA access — one event, both planes
Device trust (CMDB + Duo)Secure Access consumes Duo device trust; CMDB-Lite reconciles the hardware-ID so posture is part of the access decision
Identity intelligence (Oort + Astrix + BHE)Cisco Identity Intelligence becomes two-sided: Oort is the human ITDR (already the fabric's risk feed); Astrix is the non-human side — discover every NHI/agent, bind it to an owner, flag overprivilege, govern its lifecycle. That is the enterprise product for what an NHI registry + ownership model do by hand. And BloodHound Enterprise adds the attack-path view — which of those owned identities is a path to Tier Zero (the tier-0 plane) — so you govern by owner and prioritize by exposure.

Cisco Identity Intelligence is becoming three-sided: Oort (human ITDR), Astrix (non-human / agent), and BloodHound Enterprise (attack-path exposure to Tier Zero) — it discovers, owns, threat-detects, and prioritizes across every population, then feeds the gateways (Duo authz), Secure Access (ZTNA), and the SSF bus (real-time revoke). Who (Oort), what (Astrix), and how-they-reach-the-keys (BHE) — the same split this fabric is built on.

Cisco XDR closes the loop. CII gives XDR the identity vector; XDR correlates it with endpoint, network, email, and DNS, raises an identity threat as an incident, and drives the response back down — session-kill / quarantine through Duo, Secure Access, and ISE. In this lab, SIEM detections and the SSF/CAEP bus stand in for that detect → session-revoked loop: the same shape XDR runs at enterprise scale.

Companion view: see the as-built authZ → — the concrete request path and per-tool authorization behind the agentgateway plane.

Lane: personal lab · synthetic data — synthetic identities only, no customer data. The gateways and SSF plumbing shown are open-standards only.