gertjandewilde

We built a unified API with a large surface area and ran into a problem when building our MCP server: tool definitions alone burned 50,000+ tokens before the agent touched a single user message.

The fix that worked for us was giving agents a CLI instead. ~80 tokens in the system prompt, progressive discovery through --help, and permission enforcement baked into the binary rather than prompts.

The post covers the benchmarks (Scalekit's 75-run comparison showed 4-32x token overhead for MCP vs CLI), the architecture, and an honest section on where CLIs fall short (streaming, delegated auth, distribution).

Most APIs were designed for human developers, not autonomous agents. As LLMs start selecting endpoints and generating arguments directly from your schema, ambiguity and weak error semantics become production issues. This post outlines practical API design patterns that make APIs more reliable for agent-driven workflows.

Analyze codebases using AI - generate architectural overviews, documentation, explanations, bug reports and more

Would love to hear your thoughts, feedback, and ideas for improvement!

We’ve overhauled our SDKs with Speakeasy, leaving the limitations of our old OpenAPI generator behind. The new versions deliver major upgrades in usability, error handling, and performance.

Great use case. Is the demo broken?

Yes, Portman can do this https://github.com/apideck-libraries/portman

Hehe, fair point! Most of those products have startup programs not to break the bank

In case you want to go the open-source route you have this handy overview https://www.btw.so/open-source-alternatives

Thanks for the feedback!

I agree some categories are indeed thin, which is one of the reasons why we made the submission so potentially valuable tools can get listed.

Thanks for sharing. RAFT looks great

Good question! To transform the OpenAPI spec to a Postman collection, we're using the handy openapi-to-postman package from Postman.

The test automation is where the real magic happens.

:)

Read the full blog post at https://blog.apideck.com/announcing-portman

Hi! Interesting point. At Apideck we're a happy (paying) Postman customer. We're not aware of any collaboration limits on the free tier. We created Portman with the intention to scratch our own itch by using OpenAPI as the canonical format to drive our API lifecycle and test automation.

https://www.enterpriseready.io/ is also a great resource

Thanks for sharing!

We also created the https://ccpacompliancechecklist.com/ and Sqreen created the https://www.sqreen.com/checklists/saas-cto-security-checklis...

After months of hard work, we’re ready to launch the updated Open Banking API Tracker. Last weekend marked an important milestone for banks and fintech providers due to the final PSD2 deadline on Saturday. The PSD2 regulation aims to simplify bank data integration, boost competition, and decrease fraud in Europe.

The tracker covers 64 countries with 130 banks, 350 APIs, 95 developer portals , 20 regulators, and 7 API Aggregators.

Thanks for sharing. Do you have any feedback?

We created this tracker to overcome the complexity of tracking the GDPR compliance & security practices of our SaaS vendors. We shared our story building the tracker in the following post: https://medium.com/privacy-radius/announcing-gdpr-tracker-tr....