NewSkills management: security and system of record

Securely ScaleEnterprise AI.

The AI control plane for discovering, securing, and governing AI agents, MCP servers, and Skills across your enterprise.

Talk to usStart governingClaude
Trusted byGoogleMistralMoonPayFifth ThirdPlanetScaleLaunchDarkly

01 · The problem

AI adoption is accelerating across every company.

You need a platform that can keep pace.

Shadow AI
Without a control plane

AI tools spread team by team with no central approval. Nobody can list every agent, MCP server, and Skill in use

On the control plane

One catalog of approved agents, MCP servers, and Skills, so what's running is what's been approved

Identity
Without a control plane

Agents reach sensitive systems through borrowed credentials and shared service accounts, and security can't tell one agent from another

On the control plane

Every agent acts under its own identity, employee-driven or autonomous, with access scoped by team and role through the identity provider you already run

Visibility
Without a control plane

Security can't see what AI can access, what it did, or what data it exposed

On the control plane

Every prompt, response, and tool call crosses one governed path with a searchable record behind it

Policy
Without a control plane

Rules live in wiki pages and vary by team, with no way to enforce them consistently or prove they were followed

On the control plane

Policy is defined once and enforced on every action, with scanning for prompt injection, PII exposure, and leaked credentials, and every allow-or-deny decision logged for audit

We built our access controls on IAM. When we rolled out agents, the controls broke down. Speakeasy let us extend our identity management to all our AI usage.

Thierry Dang

Security Operations

MoonPay

Speakeasy was critical in launching our MCP server. Now we're giving agents the ability to feature flag their releases!

Benjamin Woskow

Senior Director of Engineering

LaunchDarkly

02 · The platform

Every Agent Action.
Governed on one control plane.

Speakeasy provides governance, security, identity, policy, and visibility across every AI agent, MCP server, and Skill in your enterprise, through a single governed path.

Read the guide: what is an AI control plane?

Govern AI

Define who AI can access, what it can do, and the policies it must follow. One catalog of approved tools and Skills, access scoped by team and role through the identity provider you already run, and an audit trail behind every decision.

Approved tools and Skills by team and roleAccess follows your identity providerEvery action in one audit trail

Secure AI

Enforce those policies across every AI agent, MCP server, and Skill. Every prompt, response, and agent action is inspected in real time. PII and credentials are blocked before they leave your environment, and injection attempts are caught in flight.

PII and secrets blocked in flightPrompt injection and shadow-tool detectionAlerts to Slack, PagerDuty, or your SIEM
Works with every identity providerOktaMicrosoft Entra IDAuth0WorkOSGoogle WorkspacePing IdentityAny SAML / OIDC

03 · Results

When AI is governed,
adoption grows

Numbers from teams running the control plane in production: full-company rollouts, MCP servers shipped in days, and usage that grows because governance stops being per-project work.

Read the Fivetran story

100%

Employee AI rollout

Fermatrolled out governed AI to the whole company.

60K

agent sessions governed per week

MoonPayenforces policy across every agent.

200%

MCP usage growth

PlanetScalecustomers are now agent-based.

04 · Enterprise

Certified and supported

The control plane meets the standards it helps you enforce. Audit reports and compliance documentation are available through the trust center.

Visit trust centerLearn about enterprise

Speakeasy is SOC 2 Type II, ISO 27001 and CSA STAR AI certified, GDPR compliant and HIPAA ready.

SOC 2 Type II

Audited controls for security, availability, and confidentiality of customer data.

Learn more

ISO 27001

Certified information security management system aligned with international standards.

Learn more

Forward-deployed engineering

A dedicated engineering team that works alongside yours to integrate, customize, and ship.

Every agent

One control plane for every agent

Teams rarely settle on a single agent. The same identity, guardrails, and audit trail apply across Anthropic, OpenAI, Google, and the agents your teams build and deploy themselves, whether an employee is at the keyboard or the agent runs autonomously.

AnthropicOpenAIGoogleCursor
GitHub Copilot
OpenCode
Devin
Custom agents

Becoming AI-native meant that we needed an entirely new governance & observability stack. You can't use old tools to cover your team's new way of working.

Shreyas Kumar

Co-founder, Fermat

Fermat

Questions

What is an AI control plane?
An AI control plane is a centralized platform that gives organizations governance and security over every AI agent, MCP server, and AI application across the company. Speakeasy provides a single layer to define who AI can access, what it can do, and which policies it must follow, and then enforces those policies on every action.
What AI agents does Speakeasy support?
Speakeasy works with Claude, ChatGPT, Cursor, GitHub Copilot, and any AI agent that supports the MCP protocol. A single policy layer governs all of them, so teams can use the tools they prefer without creating security gaps.
How are AI policies defined?
Policies are written once at the control plane, in language the owning team can read, and scoped to the person or agent, the system, and the action. Access follows teams and roles from your identity provider, reads and writes are treated as different privileges, permissions go down to the individual tool, and a matching deny always wins.
How are policies enforced?
Every prompt, response, and tool call crosses the control plane, where it's checked against policy in real time before it reaches your systems. There is no side channel to bypass, and enforcement is the same whether an employee is driving the agent or it runs autonomously. Every allow-or-deny decision is logged, and violations can alert Slack, PagerDuty, or your SIEM.
How does Speakeasy handle security and compliance?
Every prompt, response, and tool call is inspected in real time. Speakeasy detects and blocks PII, credentials, and prompt injection attempts before they leave your perimeter. The platform is SOC 2 Type II and ISO 27001 certified, with a full audit trail for every session.
How long does it take to deploy?
Most teams are up and running within a day. Speakeasy integrates with existing SSO providers like Okta and Entra ID, so access inherits your current groups and roles with no manual provisioning. Self-hosted and cloud deployment options are available.
What is MCP and why does it matter?
MCP (Model Context Protocol) is an open standard that lets AI agents connect to external tools and data sources. Speakeasy provides a managed platform for deploying, securing, and observing MCP servers at scale, turning any internal API or SaaS tool into a governed AI capability.
Can Speakeasy be self-hosted?
Yes. Speakeasy can be deployed in your own cloud or on-premises for full data residency control. The self-hosted option has no external dependencies and meets the requirements of teams that can't send data to third-party infrastructure.

AI everywhere.

Control here.

Talk to usExplore the AI Control Plane