mcpField

Loops

40 looping workflows for coding agents. Copy the launch prompt to run one.

All 40Featured 40Verified 0Continuous Integration 10Code Quality 9Testing 13Dependencies 5Design & Frontend 0Docs 1Other 2

Code Quality

A11y Audit Until Clean
Code Quality

Manually started loop that fixes and re-audits until changed UI has no serious accessibility violations.

On demandUp to 8 rounds
De-Sloppify Pass
Code Quality

Reviews recent changes for unneeded or off-convention code, then confirms with lint and tests.

On demandUp to 4 rounds
npm Audit Fix Loop
Code Quality

Audits npm dependencies, applies safe fixes and runs tests until no high or critical issues remain.

On demandUp to 10 rounds
OpenAPI Sync Until Valid
Code Quality

Edits openapi.yaml round by round until Redocly lint passes and the spec matches the routes.

On demandUp to 8 rounds
API Contract Until Match
Code Quality

Runs contract tests and fixes the implementation until the API matches its published contract.

On demandUp to 10 rounds
Reflexion Debug Loop
Code Quality

Reproduce a failing test, reflect on each failure, and patch until it passes.

On demandUp to 8 rounds
PR Self-Review
Code Quality

Runs repeated self-review passes over the branch diff against main until no critical findings remain.

On demandUp to 3 rounds
Investigation Script Loop
Code Quality

Proves a bug's root cause round by round with a minimal repro script.

On demandUp to 8 rounds
Bundle Size Budget
Code Quality

Manually started loop that rebuilds and measures until the client bundle fits its size-limit budget.

On demandUp to 6 rounds
1–9 of 9

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.