Top all-time · #4776
Speakeasy
Company blog · speakeasy.com/blog · on HN as disintegratorprogrammingai
Speakeasy is the company blog at speakeasy.com, writing about programming and ai. Since 2024, 16 different Hacker News readers have linked it 67 times, most often “Reducing MCP token usage by 100x – you don't need code mode”. No feed was found, so read it on the site itself.
Too few sampled comments (12) to say how often HN recommends it.?
Why HN links it
Speakeasy's blog is linked for posts on generating SDKs and CLIs from OpenAPI, CLI design for AI agents, MCP server token use, and webhook and API security. Most comments are from Speakeasy staff pointing to their product.
Summarised by Claude from a sample of 12 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
The AI control plane for discovering, securing, and governing AI agents, MCP servers, and AI applications across your enterprise.
Most-linked posts?
- Reducing MCP token usage by 100x – you don't need code mode3 people · 4 mentions · first linked 2025-11-20
- /2 people · 4 mentions · first linked 2024-09-25
- Model Context Protocol (MCP) Hub2 people · 2 mentions · first linked 2025-05-16
- Distributing MCP Servers2 people · 2 mentions · first linked 2025-10-29
- Building a High-Performance OpenAPI Parser in Go2 people · 2 mentions · first linked 2025-12-14
- MCP: An in-depth introduction2 people · 2 mentions · first linked 2025-05-12
- Forward Compatible Unions in TypeScript2 people · 2 mentions · first linked 2026-01-12
- MCP for Skeptics2 people · 2 mentions · first linked 2025-07-14
- Python HTTP Clients: Requests vs. Httpx vs. Aiohttp – Speakeasy2 people · 2 mentions · first linked 2024-09-03
- How to factor cost into agentic tool design2 people · 2 mentions · first linked 2025-08-26
What Hacker News says?
Check out https://www.speakeasy.com/ . We generate fully type-safe SDK from OpenAPI and for our TS offering we delegate the type checking to Zod.
Comment linking /
on “Zod: TypeScript-first schema validation with static type inference”Submitted MCP: An in-depth introduction as a story · 210 points
HN discussionThere's a lot of new companies that have started to address this issue. One of which I work at: https://www.speakeasy.com/ I genuinely think that the quality is beyond what exists in the GraphQl ecosystem.
Comment linking /
on “Analyzing the OpenAPI Tooling Ecosystem”Submitted The double standard of webhook security and API security as a story · 122 points
HN discussionRe-reading the article, I'm confused about where I was coming from too. The article claims that it was last updated May 7th but the two Archive captures[0][1] seem to be broken for me ATM. The link to the blog source on GitHub[2] (linked from the page) just gave me a 404 and searching for the file didn't yield another location so I can't look for a commit timestamp or delta. There is a bit of switching back and fort…
Comment linking /_gh-redirect/src/content/blog/webhook-security/index.mdx
on “The double standard of webhook security and API security”Submitted Vitest vs. Jest as a story · 44 points
HN discussionWe've been a customer for the past year ( https://speakeasy.com/docs ). I was honestly highly skeptical about putting a RAG powered search in front of our documentation site instead of what we were using (FlexSearch / Nextra). Have been delighted to be proved wrong. The learning I've had is that whilst the majority of queries go through standard search patterns (i.e. users search for something that's covered by docu…
Comment linking /docs
on “Launch HN: Inkeep (YC W23) – Copilot for Support (think Cursor for help desks)”Submitted Building a High-Performance OpenAPI Parser in Go as a story · 39 points
HN discussionhttps://www.speakeasy.com/guides/api-frameworks/typespec This post has a bit more detail about why "we don't need more standards" might not be the correct take here (Disclaimer speakeasy is a client but I wasn't directly involved in writing this and just figured it's pretty relevant here)
Comment linking /guides/api-frameworks/typespec
on “Microsoft TypeSpec”Submitted Show HN: Gram Functions – Serverless platform for turning code into LLM tools as a story · 23 points
HN discussionSpeakeasy | San Francisco or London | https://www.speakeasy.com/ At Speakeasy we craft developer experiences with care for our customers. We have a suite of products focused on helping team's distribute their products. We build: - An API platform that helps teams generate and maintain high quality SDKs, Terraform Providers and CLIs for their users by leveraging OpenAPI. The complete platform is usable as a set of cl…
Comment linking /
on “Ask HN: Who is hiring? (February 2026)”Submitted There's no good reason for signing webhooks as a story · 18 points
HN discussionSpeakeasy | AI Control Plane | Product, Security and SRE Engineers | SF/London | Full-time Hey everyone! We're staffing up our AI control plane product to meet market demand. Come join a team in San Francisco or London focused on building core infrastructure to help companies securely scale agent use. Think security engineering, observability built on clickhouse, MCP oauth and protocol work, building out our serverl…
Comment linking /careers
on “Ask HN: Who is hiring? (June 2026)”Submitted Bundling MCP Servers in Every OpenAPI –> TypeScript SDK as a story · 16 points
HN discussionBTW Speakeasy support generating customizable CLIs written in Go from OpenAPI specs. https://www.speakeasy.com/docs/cli-generation/create-cli (Disclaimer: I work for Speakeasy)
Comment linking /docs/cli-generation/create-cli
on “Building a CLI for All of Cloudflare”Submitted Current state of MCP OAuth: A work in progress as a story · 9 points
HN discussionWe literally just did something like this on Gram, not exactly what you're saying, but it's pretty close... https://www.speakeasy.com/blog/how-we-reduced-token-usage-by... We have a platform (Gram) which is serverless MCP. Now users can launch MCP servers that only have 3 tools, search, describe, execute. Gram handles the tool routing, and execution (acting sort of like the sandbox). So the client only ever needs to…
Comment linking /blog/how-we-reduced-token-usage-by-100x-dynamic-toolsets-v2
on “Show HN: Code Mode for MCP in MCP-use's client”Submitted Forward compatibility and fault tolerance in TypeScript API Clients/SDKs as a story · 5 points
HN discussionI work at Speakeasy where we do a similar thing with the AI control plane ( https://www.speakeasy.com/product/ai-control-plane ), and we just rolled out on-device agents for the same reason. I think the point a few people are making is right that its not sufficient to be the best at one layer like the device endpoint. AI governance needs to be coordinated over a number of surfaces. We started with an MCP gateway and…
Comment linking /product/ai-control-plane
on “Launch HN: Traceforce (YC S26) – Company-wide security monitoring for AI apps”Submitted Show HN: OpenAPI Hub – everything you need to know about OpenAPI (and more) as a story · 5 points
HN discussionI work at Speakeasy. We build a CLI for SDK generation, and we noticed that features we designed for humans - interactive prompts, spinners, guided workflows - were actively breaking AI coding assistants. We wrote up what we learned from fixing this: - Non-interactive flags that bypass prompts entirely - Structured output modes (JSON, --quiet) to reduce token consumption - Machine-readable exit codes so agents can d…
Comment linking /blog/engineering-agent-friendly-cli
on “Your CLI's UX is probably broken for AI agents”Submitted Building a High-Performance OpenAPI Parser in Go as a story · 4 points
HN discussionHey there! Check out https://www.speakeasy.com/ . Our platform provides capabilities around managing MCP for your org. Easy identity and oauth management, centrally distribute a group of mcps to your team and manage permissions too. Would be happy to show you! (disclaimer: i'm one of the founders)
Comment linking /
on “Ask HN: How are you managing MCP servers across a team?”Submitted Preparing your repo for AI development as a story · 4 points
HN discussionSubmitted Reducing MCP token usage by 100x – you don't need code mode as a story · 4 points
HN discussionSubmitted Filtering large MCP tool responses with jq as a story · 4 points
HN discussionSubmitted MCP for Skeptics as a story · 4 points
HN discussionSubmitted Building a Model Context Protocol (MCP) Server for Discord as a story · 4 points
HN discussionSubmitted Model Context Protocol (MCP) Hub as a story · 3 points
HN discussionSubmitted Model Context Protocol (MCP) Hub as a story · 3 points
HN discussion