[metadata]
description: The AI control plane for discovering, securing, and governing AI agents, MCP servers, and AI applications across your enterprise.
og:description: The AI control plane for discovering, securing, and governing AI agents, MCP servers, and AI applications across your enterprise.
og:image: https://www.speakeasy.com/api/og?title=Govern%20and%20secure%20enterprise%20AI
og:image:alt: Govern and secure enterprise AI — Speakeasy
og:image:height: 630
og:image:width: 1200
og:locale: en_US
og:site_name: Speakeasy
og:title: Govern and secure enterprise AI — Speakeasy
og:type: website
og:url: https://www.speakeasy.com/
twitter:card: summary_large_image
twitter:description: The AI control plane for discovering, securing, and governing AI agents, MCP servers, and AI applications across your enterprise.
twitter:image: https://www.speakeasy.com/api/og?title=Govern%20and%20secure%20enterprise%20AI
twitter:site: @speakeasydev
twitter:title: Govern and secure enterprise AI — Speakeasy
viewport: width=device-width, initial-scale=1

[canonical-links]
https://www.speakeasy.com/

[document-links]
AI Control Plane A single control plane to safely scale AI Connect Secure Distribute Observe: /docs/ai-control-plane
AI Control Plane: https://app.getgram.ai/
API Platform: https://app.speakeasy.com/
About us Our story, mission, and vision: /company
Account Executive: https://jobs.ashbyhq.com/Speakeasy/b0c122c2-f0db-46ed-8c43-7bb72a4638a0
Anthropic Claude Your control plane for Claude at work: /use-cases/claude-control
Anthropic ↗: /use-cases/claude-control
Blog Read our latest news and updates: /blog
CLI Your API in the terminal: /docs/cli-generation/create-cli
Careers 5 Shape the future with us: /careers
Code editor Cursor Guardrails for Cursor across every team: /use-cases/cursor-control
Connect Agent identity Govern every agent action with permissioned enterprise identity: /product/agent-identity
Contact us Get in touch with our team: /contact
Cursor ↗: /use-cases/cursor-control
Customers: /customers
Distribute MCP & Skills gateway Empower your team with centralized MCPs & skills: /product/mcp-gateway
Distribute Manage MCP with a Gateway One gateway for every agent and every MCP: /product/mcp-gateway
Docs MCP Docs agents understand: /docs/speakeasy-reference/cli/getting-started
Docs: /docs/ai-control-plane
Documentation Home Home for all Speakeasy product docs: /docs/speakeasy-reference/cli/getting-started
Enterprise OpenClaw Roll out OpenClaw agents safely: /use-cases/enterprise-openclaw
Explore the AI Control Plane: /product/ai-control-plane
Forward Deployed Engineer: https://jobs.ashbyhq.com/Speakeasy/def210b2-b6aa-421b-84c4-dcd278f95db9
Google Gemini Secure and observe Gemini usage: /use-cases/gemini-control
Google ↗: /use-cases/gemini-control
ISO 27001 Certified information security management system aligned with international standards. Learn more: /security/iso-27001
Learn about enterprise: /enterprise
New Skills management: security and system of record →: /blog/release-skills-management
Observe AI usage telemetry Track adoption, cost, and activity across the org: /product/agent-observability
Open source OpenCode Enterprise controls for OpenCode: /use-cases/opencode-control
OpenAI Codex Govern Codex usage across your org: /use-cases/codex-control
OpenAI ↗: /use-cases/codex-control
OpenCode ↗: /use-cases/opencode-control
Platform Engineer (SRE) - AI Control Plane: https://jobs.ashbyhq.com/Speakeasy/43904ba3-3792-4cc4-b097-6e98ca9a1b4b
Pricing: /pricing
Product changelog: /changelog
Read the Fivetran story: /customers/fivetran
Read the guide: what is an AI control plane?: /resources/ai-control-plane
Resource Library Reference architecture and working definitions for the AI control plane: /resources
SDKs Idiomatic, type-safe SDKs: /docs/sdks/create-client-sdks
SOC 2 Type II Audited controls for security, availability, and confidentiality of customer data. Learn more: /security/soc-2
Secure Agent Security Detect shadow AI, prevent risky actions, stop data leaks in real time: /product/agent-security
Secure Secure AI Usage Detect shadow AI, prevent risky actions, stop data leaks in real time: /product/agent-security
Speakeasy Logo: /
Start governing Claude Codex Cursor Gemini ChatGPT OpenCode Devin Mistral Bedrock Claude: /use-cases/claude-control
Talk to us >: /talk-to-us
Talk to us Unlock the right solution: /talk-to-us
Talk to us: /talk-to-us
Terraform Providers from OpenAPI: /docs/terraform/create-terraform
Visit trust center: https://trust.speakeasy.com/
What is an AI control plane?: /resources/ai-control-plane

[structured-data]
{"@context":"https://schema.org","@graph":[{"@id":"https://www.speakeasy.com/#organization","@type":"Organization","address":{"@type":"PostalAddress","addressCountry":"US","addressLocality":"San Francisco","addressRegion":"CA","postalCode":"94102","streetAddress":"1390 Market Street, Suite 200"},"contactPoint":[{"@type":"ContactPoint","areaServed":"Worldwide","availableLanguage":["English"],"contactType":"sales","email":"sales@speakeasy.com","url":"https://www.speakeasy.com/talk-to-us"},{"@type":"ContactPoint","areaServed":"Worldwide","availableLanguage":["English"],"contactType":"customer support","email":"support@speakeasy.com","url":"https://www.speakeasy.com/contact"},{"@type":"ContactPoint","areaServed":"Worldwide","availableLanguage":["English"],"contactType":"security","email":"security@speakeasy.com","url":"https://www.speakeasy.com/.well-known/security.txt"}],"description":"Speakeasy is the AI control plane for the AI-native enterprise. Connect, distribute, secure, and observe every AI agent and the systems they reach.","foundingDate":"2021","legalName":"Speakeasy API, Inc.","logo":{"@type":"ImageObject","height":630,"url":"https://www.speakeasy.com/assets/og-images/og-speakeasy.png","width":1200},"name":"Speakeasy","sameAs":["https://github.com/speakeasy-api","https://www.linkedin.com/company/speakeasyapi","https://x.com/speakeasydev","https://www.youtube.com/@SpeakeasyDev","https://www.crunchbase.com/organization/speakeasy-1c97","https://www.g2.com/products/speakeasy/reviews"],"url":"https://www.speakeasy.com"},{"@id":"https://www.speakeasy.com/#website","@type":"WebSite","description":"The AI control plane for the AI-native enterprise. Connect, distribute, secure, and observe every AI agent across the organization.","inLanguage":"en-US","name":"Speakeasy","publisher":{"@id":"https://www.speakeasy.com/#organization"},"url":"https://www.speakeasy.com"},{"@id":"https://www.speakeasy.com/#software","@type":"SoftwareApplication","applicationCategory":"BusinessApplication","applicationSubCategory":"AI Governance Platform","audience":{"@type":"BusinessAudience","audienceType":"Enterprise security, platform, and AI engineering teams"},"brand":{"@id":"https://www.speakeasy.com/#organization"},"description":"AI control plane that connects every AI agent (Claude, ChatGPT, Cursor, Copilot, Codex) to every system, with SSO, RBAC, runtime guardrails, and a full audit trail.","featureList":["MCP server provisioning and gateway","OAuth 2.1 with PKCE and Dynamic Client Registration","SSO integration (Okta, Microsoft Entra ID, Auth0, WorkOS, Google Workspace)","Role-based access control down to the tool level","Real-time prompt and tool-call inspection","PII and data exfiltration blocking","Prompt injection and shadow MCP detection","SIEM integration for security events","Token, adoption, and outcome analytics","OpenAPI to MCP, Terraform, and CLI generation"],"name":"Speakeasy AI Control Plane","offers":{"@type":"Offer","availability":"https://schema.org/InStock","priceCurrency":"USD","url":"https://www.speakeasy.com/pricing"},"operatingSystem":"Web, Cloud, Self-hosted","publisher":{"@id":"https://www.speakeasy.com/#organization"},"url":"https://www.speakeasy.com"},{"@id":"https://www.speakeasy.com/#webpage","@type":"WebPage","about":{"@id":"https://www.speakeasy.com/#software"},"inLanguage":"en-US","isPartOf":{"@id":"https://www.speakeasy.com/#website"},"name":"Speakeasy: the AI control plane","primaryImageOfPage":{"@type":"ImageObject","url":"https://www.speakeasy.com/assets/og-images/og-speakeasy.png"},"speakable":{"@type":"SpeakableSpecification","cssSelector":["h1","[data-speakable]",".bsmnt-text-display-lg"]},"url":"https://www.speakeasy.com"}]}

[content]
Govern and secure enterprise AI — Speakeasy
Speakeasy Logo
Products
AI Control Plane
Connect
Agent identity
Govern every agent action with permissioned enterprise identity
Secure
Agent Security
Detect shadow AI, prevent risky actions, stop data leaks in real time
Distribute
MCP & Skills gateway
Empower your team with centralized MCPs & skills
Observe
AI usage telemetry
Track adoption, cost, and activity across the org
What is an AI control plane?
Product changelog
Docs
AI Control Plane
AI Control Plane
A single control plane to safely scale AI
Connect
Secure
Distribute
Observe
API Platform
SDKs
Idiomatic, type-safe SDKs
Terraform
Providers from OpenAPI
CLI
Your API in the terminal
Docs MCP
Docs agents understand
Documentation Home
Home for all Speakeasy product docs
Resource Library
Reference architecture and working definitions for the AI control plane
Solutions
Use Cases
Distribute
Manage MCP with a Gateway
One gateway for every agent and every MCP
Secure
Secure AI Usage
Detect shadow AI, prevent risky actions, stop data leaks in real time
Agents
Anthropic
Claude
Your control plane for Claude at work
OpenAI
Codex
Govern Codex usage across your org
Google
Gemini
Secure and observe Gemini usage
Code editor
Cursor
Guardrails for Cursor across every team
Open source
OpenCode
Enterprise controls for OpenCode
Enterprise
OpenClaw
Roll out OpenClaw agents safely
Customers
Company
Careers
Careers
5
Shape the future with us
Account Executive
Forward Deployed Engineer
Platform Engineer (SRE) - AI Control Plane
Company
About us
Our story, mission, and vision
Contact us
Get in touch with our team
Talk to us
Unlock the right solution
Blog
Read our latest news and updates
Pricing
Log in
AI Control Plane
API Platform
Talk to us
New
Skills management: security and system of record
→
Securely Scale
Enterprise AI.
The AI control plane for discovering, securing, and governing AI agents, MCP servers, and Skills across your enterprise.
Talk to us
Start governing
Claude
Codex
Cursor
Gemini
ChatGPT
OpenCode
Devin
Mistral
Bedrock
Claude
Trusted by
01 · The problem
AI adoption is accelerating across every company.
You need a platform that can keep pace.
Without a control plane
On the control plane
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
“
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
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?
Speakeasy
/
Default
/
Home
N
Overview
Last 30 days
Total spend
$13,878.94
+27%
Agent sessions
1,131
+12%
Tool calls
111,402
+38%
Risk findings
29,622
-31%
Billing bug outreach
B7F2A1D4
·
daniel@speakeasy.com
claude-opus-4-8
Cost
$0.00
Calls
0
Tokens
0
Risk
0
Policy monitor
attached
Billing bug outreach
✓ Governed
+
New
Projects
Artifacts
Scheduled
Scheduled
Morning brief
3
Recents
Billing bug outreach
EU customer list export
Incident review follow-ups
NS
Nolan
Connected to Speakeasy
✓
12 MCP servers · 84 tools · session governed
Pull the contacts affected by yesterday's billing bug and draft an apology email.
Opus 5
↑
xv·-x xv-xxv··x-x-- --·x-v·-·x·vvxv·- v·vx·x vx--vv vxvxv -v·-- v-v- xxv· vv-x ·xvv xxv-x ·vxvx v-vxv -v·--x vvvx·vv x-xxvvvv vvv-vvvvxx-vxxxx-vx ·-x·-xxxv v·xv-v- x-v·-x vv·-vv -·xxvx x·vv-v- xv-
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 role
Access follows your identity provider
Every action in one audit trail
x-vvv·v ·-x·x-x·vxx v··x-x--vv··x ·-·x· --vvx ---·v vvvvx x·-- -xvx vvv-v v·xv- -vx-- xvvx· x-·x--xvxvvv·vxvxx··--v xvxvvv-x·vv-v·--xvvvv·· vx·vv-vvx vvv-xv-vv vv-vvvvxx x-vxvvv-x vx·-x·-xxx v·xv-v-xxx ··vv-·xx-v vvx-v·-xxv x··xxv-v-- vxxvvv·-vv xx-vxvv·-x·vv-vv·xv-·xx x-·xv-xx··-xx-x---·vx·v vvxvvvvxxv·x·x·-vx·vvvx
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 flight
Prompt injection and shadow-tool detection
Alerts to Slack, PagerDuty, or your SIEM
Works with every identity provider
Any 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
rolled out governed AI to the whole company.
60K
agent sessions governed per week
enforces policy across every agent.
200%
MCP usage growth
customers 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 center
Learn about enterprise
*===============* *===++::.........::++===* *===++::...........::++===* *===++::...........::++===* *===++::...........::++===* *===++::...........::++===* *===++::...........::++===* *===++::...........::++===* *===++::...........::++===* **==++::...........::++==** *==++::.........::++==* *==++:.........:++==* *==+:.......:+==* ==+:.....:+== =+:...:+= *+:::+* ===
SOC 2
Type II
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.
Anthropic
↗
OpenAI
↗
Google
↗
Cursor
↗
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
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 us
>
Explore the AI Control Plane
