Skip to content
All articles
Engineering2 September 2025·3 min read

From Pain Points to Solutions: How VSCode Solved MCP's Biggest Developer Challenges

Most of the difficulty with agents is not the model.

Paycux engineering

Most of the difficulty with agents is not the model. It is that an agent sits between a user and a system that was designed on the assumption a user would be there in person.

This piece walks through how we think about it at Paycux, what we have changed our minds about, and where the sharp edges are.

The Installation Nightmare is Over

That brings us to the installation nightmare is over. Consent is the part most implementations get wrong. Asking once at install time and then acting indefinitely is not consent; it is a standing grant with no expiry and no visibility.

Consent is the part most implementations get wrong. Asking once at install time and then acting indefinitely is not consent; it is a standing grant with no expiry and no visibility.

Making API Keys Actually Secure

That brings us to making api keys actually secure. An agent's credential should describe what it may do, not who owns it. Scope it to the narrowest set of operations that make the task possible, bind it to a single principal, and give it a lifetime measured in minutes rather than days.

Consent is the part most implementations get wrong. Asking once at install time and then acting indefinitely is not consent; it is a standing grant with no expiry and no visibility.

  • Scope every agent credential to one principal and one task
  • Give tokens minutes of life, not days
  • Record which agent acted, under whose authority, on what
  • Make revocation a single call that takes effect immediately

Beyond Secret Incantations: Intelligent Tool Discovery

That brings us to beyond secret incantations: intelligent tool discovery. The audit trail matters more here than in any human flow. When something goes wrong, the question is never "did the user intend this" in the abstract — it is which agent, acting under whose authority, made which call, and whether the record can prove it.

An agent's credential should describe what it may do, not who owns it. Scope it to the narrowest set of operations that make the task possible, bind it to a single principal, and give it a lifetime measured in minutes rather than days.

Scaling to Unlimited Tools

That brings us to scaling to unlimited tools. Consent is the part most implementations get wrong. Asking once at install time and then acting indefinitely is not consent; it is a standing grant with no expiry and no visibility.

The audit trail matters more here than in any human flow. When something goes wrong, the question is never "did the user intend this" in the abstract — it is which agent, acting under whose authority, made which call, and whether the record can prove it.

An agent's credential should describe what it may do, not who owns it.

Smart Context Management

Smart Context Management deserves its own treatment. Consent is the part most implementations get wrong. Asking once at install time and then acting indefinitely is not consent; it is a standing grant with no expiry and no visibility.

Consent is the part most implementations get wrong. Asking once at install time and then acting indefinitely is not consent; it is a standing grant with no expiry and no visibility.

Making Development Actually Enjoyable

Making Development Actually Enjoyable deserves its own treatment. Consent is the part most implementations get wrong. Asking once at install time and then acting indefinitely is not consent; it is a standing grant with no expiry and no visibility.

An agent's credential should describe what it may do, not who owns it. Scope it to the narrowest set of operations that make the task possible, bind it to a single principal, and give it a lifetime measured in minutes rather than days.

A Pattern for the Future

Consider a pattern for the future. An agent's credential should describe what it may do, not who owns it. Scope it to the narrowest set of operations that make the task possible, bind it to a single principal, and give it a lifetime measured in minutes rather than days.

An agent's credential should describe what it may do, not who owns it. Scope it to the narrowest set of operations that make the task possible, bind it to a single principal, and give it a lifetime measured in minutes rather than days.

Where this leaves us

If there is one thing worth taking away, it is that the expensive decisions are the ones made implicitly. Making them on purpose costs an afternoon.

If you are working through the same problem and want to compare notes, the docs cover the mechanics and the console shows the behaviour on your own data.

Everything here, already built

Sign-in, enterprise SSO, directory provisioning, roles and an audit trail behind one API. Start with the quickstart and have a working sign-in this afternoon.

Start selling to enterprise customers

Create an account, point sign-in at Paycux, and get back to the part of the product that is actually yours.