Speakeasy is the AI control plane for enterprise AI. The platform gives security and platform teams one governed path for every AI agent, MCP server, and Skill in a company, so they can understand how AI is used, define what it can access, and enforce those rules on every agent action. Identity providers were built for people signing in to apps, and agents fall back on borrowed credentials and shared service accounts. Speakeasy extends the identity provider a company already runs, including OKTA, Microsoft Entra ID, and any SAML or OIDC provider, to AI agents. Every agent acts under its own identity, with access scoped by existing teams and roles. Every prompt, response, and tool call is checked against policy in real time; threats like prompt injection, PII exposure, and leaked credentials are blocked in flight, and every allow-or-deny it. Speakeasy is trusted by teams at Google, Mistral, MoonPay, Fifth Third, and PlanetScale.