Sabitlenmiş Tweet
Speakeasy
1.1K posts
Speakeasy
@speakeasydev
One platform to safely scale AI usage across your organization. Connect, secure, and monitor AI in real time. Every MCP, skill, and agent session governed.
SF & London 🍻 Katılım Mayıs 2022
72 Takip Edilen1.5K Takipçiler
PlanetScale is a Speakeasy customer 🤝
They don't just build a great database, they put in the work to build a great platform! Whether a developer is prompting an AI agent or writing infrastructure-as-code, PlanetScale just works.
We've loved collaborating with them to launch the initial versions of their Terraform provider and MCP server and look forward to many more years of partnership!
English
Most companies think AI governance is a policy problem.
It is. But it's also an architecture problem, a complicated one...
Here's what a proper AI control plane actually looks like, and why each layer matters:
Every AI interaction flows through 3 zones:
01 · Callers (who's asking)
→ People: engineers, sales, finance, ops
→ Machine callers: Cursor, Copilot, Devin, custom agents
→ Autonomous workers: role-based agents like OpenClaw running without a human in the loop
02 · Control plane (the governed path)
Identity & access: spans every call. SSO, role/team scoping, credential management via OIDC, SAML, SCIM. Not "who set up their personal account" but "who is this person in the org and what are they entitled to."
LLM gateway: sits in front of every model call. Multi-provider routing, rate limiting, caching. One lane for every prompt.
MCP gateway: sits in front of every tool call. Tool registry and routing, per-team scoping. One lane for every action.
Policy & threat: applied to every call. Executable allow/deny rules. Real-time detection of PII, data exfiltration, prompt injection, shadow tools. The policy that lives in a Confluence doc is not a control. This is.
Observability & audit: spans every call. Every prompt, response, and tool call captured. Adoption analytics. SIEM integration. OpenTelemetry-native.
03 · Destinations (what they reach)
→ LLMs: Claude, GPT, Gemini, internal models
→ Enterprise systems: SaaS apps, internal APIs, databases, data warehouses
Enterprises need to assemble a control plane that spans ALL traffic, not just some of it.
An LLM gateway that sees prompts but not tool calls isn't a control plane. An identity layer that covers Claude but not Cursor isn't a control plane. Governance only works when it's a property of the path itself, not bolted on per-tool.
That's what we're solving at Speakeasy
Link to the full reference architecture in the comments 👇
English
The best time to build a CLI was seven years ago. The next best time is today...
speakeasy.com/product/cli-ge…
Kenneth Auchenberg 🛠@auchenberg
We were a bit too early with that Stripe CLI. My first ship at Stripe.
English
We talked to 50+ tech executives in 30 days. Every single one had the same problem: AI rolling out faster than they can govern it.
The fix isn't one more tool. LLM gateways, MCP gateways, identity, observability. Each sees a slice. None sees the whole.
We wrote the reference: speakeasy.com/resources/ai-c…
English
Speakeasy retweetledi
Access control for MCP isn't one question. It's four.
1. Org — who at the company can use the platform
2. Team — which teams reach which tool groups
3. Server — which MCP servers a user can connect to
4. Tool — which specific tools a user can invoke
English
The top MCP question from enterprise leaders right now:
"How do I curate an approved list of servers for my org?"
With 13,000+ MCP servers out there and new ones shipping daily, "just let people install things" isn't a strategy.
So we teamed up with @tadasayy and @grumpygrowthguy from @pulsemcp to build a curated catalog of trusted MCP servers purpose-built for Speakeasy customers rolling out MCP at scale.
Production-grade, vetted, enterprise-ready. 🤝
English
End to end MCP authorisation now live ! Setup read vs write policies for your whole company and synced with your identity provider!
Sagar Batchu@sagar_batchu
MCP adoption inside companies right now looks like shadow IT on fast-forward. Devs installing servers wherever, IT with zero visibility, no policy enforcement. Today we're bridging the gap between your SSO and MCP. Speakeasy now syncs your IdP roles directly to MCP server permissions. Define who connects, who gets read-only, and who gets full access. Per server.
English
Salesforce leading the way. Come chat with us at @speakeasydev to get your product agent native!
Marc Benioff@Benioff
Welcome Salesforce Headless 360: No Browser Required! Our API is the UI. Entire Salesforce & Agentforce & Slack platforms are now exposed as APIs, MCP, & CLI. All AI agents can access data, workflows, and tasks directly in Slack, Voice, or anywhere else with Salesforce Headless 360. Faster builds, agentic everything. 🚀 #Salesforce #Agentforce #AI venturebeat.com/ai/salesforce-…
English
Dennis Babyak just joined Speakeasy to help build our AI control plane.
He's coming from Bird with deep experience building systems at scale. Exactly the kind of engineer you want working on infrastructure that gives teams real visibility and control over their AI integrations.
Welcome, Dennis 🤝
English
Autumn built an open-source billing layer that saves AI teams weeks of Stripe integration. 3 functions. No webhooks. Usage tracking that just works.
Now they're using Speakeasy to generate SDKs that match the quality of their API.
Welcome aboard, @autumnpricing 🍂
English
Speakeasy retweetledi
ClawHub went from 2,800 skills to 10,700 in two weeks. Anyone with a week-old GitHub account could publish.
1,400+ malicious skills found. Credential harvesters, cryptominers, backdoors, prompt injection loaders. Five of the top seven most-downloaded skills at peak were confirmed malware.
English
We're excited to welcome Alex Martin to the Speakeasy engineering team! Alex joins us from Render, where he was the first UX engineering hire. He's joining us to repeat the feat, by bringing his design and product chops to our SF office. Excited to make the pixels dance! 🕺
English
Speakeasy retweetledi
