Docs menu
Get started
Quickstart Install: Claude Code Install: Codex Install: other clients API keysConcepts
How a run works The app profile The severity model What a run does not sayTools
check_access claim_trial_key set_profile run_lint get_law resolve_domain_jurisdiction submit_feedback upload_lint_runGuides
A whole run, end to end Console TestPack in CIReference
Endpoint and transport lexlint.yml schema Errors ChangelogHelp
Support and feedbackTools
Tool reference
Eight tools. Five of them only read, and the rest write, so they run only from an agent session.
| Tool | Reads or writes | What it is for |
|---|---|---|
check_access | reads | The preflight: is the key good, and how current is the law library? |
claim_trial_key | writes | A 30-day trial key, from inside the session, with no account. |
set_profile | reads | Declare what the app does and where it operates. Nothing is stored. |
run_lint | reads | The findings, each with its citation and the date it was last checked. |
get_law | reads | One jurisdiction's law across all eight topics, with its sources. |
resolve_domain_jurisdiction | reads | Whose law a domain answers to, and how that is known. |
submit_feedback | writes | Tell the people who build LexLint what went wrong. |
upload_lint_run | writes | Send a finished run to my.lexlint.io, after you have seen it. |
What a lint costs
Every tool runs on your own UnGovr Open Data key, and the tools that read the LexLint law library spend requests from its daily allowance. Where a tool's page states a cost, it counts upstream requests, and the whole of a first lint is on How a run works.