Code review for people and agents
Know what every change touches.
LintCat indexes your repository and reviews each pull request against it. Your coding agent gets the same insight over MCP, before anything is pushed.
An example codebase map: five packages, the modules inside them, and the imports between them, with the three modules a pull request changed highlighted.
Two ways in
One index, read by your team and by your agent.
For your team
Install the GitHub App and label a pull request. LintCat leaves inline comments, an AI PR Review check run, and a record on your dashboard.
- Suggested fixes, checked against the latest commit
- Findings by severity and category, across every repository
- A codebase map for each review: what changed, and what depends on it
For your coding agent
Run the same reviewer as an MCP server in Claude Code or any MCP client. Your agent reviews its own work before it pushes, and asks the index how the code fits together.
- review_local_changes
- Review the working tree against its base branch.
- repository_overview
- Workspace packages and import coverage, from the working tree.
- find_references
- Which files import a file, or one of its exports.
- describe_file
- A file's role, its package, its importers and its test.
What it looks for
Where a change drifts from how your codebase already does things.
Naming
Names that break how the rest of the repository names the same kind of thing
Patterns
A re-implemented helper, a bypassed layer, a second way to do a solved job
Style
Export style, error shapes and module layout the neighbours share and no linter checks
Documentation
Docs, comments and links this change made wrong
Config
Settings and dependencies added differently from the ones already there
Getting started
Three steps, no workflow file.
- 1
Install the GitHub App
Pick the repositories LintCat may review. Nothing goes in your CI.
- 2
Add a model key
An owner saves an Anthropic or OpenAI key. Reviews bill to your provider.
- 3
Open a pull request
It is reviewed, and every later push is reviewed again.
FAQ
Frequently asked questions
What is LintCat?
An AI code reviewer. It reviews every pull request against the rest of your repository and leaves inline comments, and gives your coding agent the same review over MCP.
Do I need to change my CI?
No. Install the GitHub App and add a model key. Reviews run on LintCat's side, so your repository gets no workflow file and your Actions minutes go untouched.
Who pays for the model usage?
You do, through your own provider account. An owner saves one Anthropic or OpenAI API key on the dashboard, and reviews run on that key.
Can LintCat block or merge my pull requests?
No. The AI PR Review check is advisory, and the AI reviewer can only read your code. It never approves, merges or blocks anything.
Give your next pull request a second pair of eyes.
Install it on one repository or all of them. You bring the model key.