--- title: "Govern AI & Agent Access" description: "Give every team AI access safely. One gateway in front of the MCP servers and LLM providers you approve — per-team dollar budgets, per-tool access, and every call audited per user, with the IdP you already run." canonicalUrl: "https://zuplo.com/solutions/govern-ai-access" sourceUrl: "https://zuplo.com/solutions/govern-ai-access" pageType: "use-case" generatedAt: "2026-10-08" --- # Give your teams AI access. Keep every call accountable. > One gateway in front of the MCP servers and models you approve. Teams sign in with your IdP, budgets keep spend in bounds, and every call has a name on it. ## Saying yes to AI shouldn't mean losing track of it. Your teams are already wiring AI into real systems. The job isn't to slow them down — it's to give them a front door you control. - **Approve once, publish one gateway** — Vet a server once and every team connects through the same governed endpoint. Saying yes gets faster. - **Budgets, not surprises** — Teams experiment freely inside limits you set — the bill never outruns the plan. - **Every call has a name on it** — When someone asks who did what, you answer from a dashboard — not a shrug. ## One front door for AI 1. **Put the gateway in front** — Add the MCP servers you approve — Linear, GitHub, your own — as routes on one gateway, with LLM traffic alongside them. 2. **Teams sign in with your IdP** — Claude, Cursor, and ChatGPT connect through the login you already run — no shared keys in desktop apps. 3. **Policies do the governing** — Per-tool allow-lists, budgets, and audit logging run on every call — written once, enforced at the edge, versioned in your repo. ## The MCP your teams use and the models your apps call Agent tool calls and LLM completions run through the same gateway and the same policy pipeline — one place to set the rules, one place to see what happened. Architecture: clients (Web Apps, AI Agents, Mobile, API Clients) flow through three gateways to services. - **API Gateway** (badge: MCP Server Support included): Routing & transformation; Auth & authorization; Rate limiting & quotas; Request validation; Developer portal; OpenAPI-native · GitOps - **AI Gateway**: LLM model routing; Prompt injection protection; Semantic caching; Budget & token control; Usage tracking by team; Auto-failover - **MCP Gateway**: Internal & external MCP servers; Virtual MCP servers; RBAC per team; Centralized audit logs; Prevent MCP sprawl; Sensitive tool access control Each gateway runs as its own project. MCP Server Support is built directly into the API Gateway — no extra deployment, no duplicate config. ### MCP — The MCP servers your teams use One route per approved server. The gateway holds the credentials; you choose the tools each team sees. [Explore MCP Gateway](/mcp-gateway) ### LLM — The models your apps call Swap model providers in config, not code — with per-team budgets and guardrails attached. [Explore AI Gateway](/ai-gateway) ## Per-tool access. Per-user answers. - **Per-tool access, enforced at the gateway** — Hidden tools stay blocked even when a client calls them by name — with finer-grained rules whenever you need them. - **Audited per user, not per key** — Who, which tool, what happened — in Zuplo or the dashboards you already watch. ## Works with the identity provider you already run Teams sign in with the accounts they already have — no new logins to manage. Okta, Microsoft Entra ID, Auth0, Google, Clerk, WorkOS, Amazon Cognito, Keycloak, Logto, OneLogin, PingOne, Any OIDC provider. ## FAQ Common questions from platform and IT teams governing AI and agent access. ### How do teams connect Claude, Cursor, or ChatGPT through the gateway? You publish gateway endpoints for the MCP servers you approve; employees add them to their client and sign in through a standard OAuth flow backed by your identity provider. No shared API keys pasted into desktop apps — the gateway issues its own short-lived tokens and keeps upstream credentials encrypted at rest. ### Can I control which tools a team can use? Yes. Capability filtering allow-lists the tools, prompts, and resources each gateway route exposes — and blocks hidden tools even if a client invokes them by name. For finer-grained rules, integrate OpenFGA, AuthZEN, or Okta FGA, or write custom authorization logic in TypeScript. ### How do LLM budgets and spend caps work? Route LLM traffic through the AI Gateway and assign dollar budgets per team, project, or environment. When a team hits its cap, requests stop at the gateway instead of showing up on next month's bill — and you can see spend by team in real time. ### Does this work with our identity provider? Yes — any client, any IdP, any auth method. First-class integrations cover Auth0, Okta, Microsoft Entra ID, Clerk, WorkOS, Amazon Cognito, Google, Keycloak, Logto, OneLogin, and PingOne, plus generic OIDC for everything else. ### What shows up in the audit trail? Every MCP request and tool call is recorded with the user behind it, the client they used, the capability invoked, the outcome, and latency — plus auth events like token issuance and consent. View it in Zuplo's MCP analytics or forward everything to Datadog, Splunk, New Relic, and other logging platforms. ## Give your teams AI access today Put one governed gateway in front of the MCP servers and models you approve. The MCP Gateway and AI Gateway are included in every plan. ## Next steps - [Start for Free](https://portal.zuplo.com/signup) - [Book a Demo](/schedule-call)