# Overview

Kerno KIT is a local code-intelligence layer for your AI coding agent. It gives your agent a complete, compiler-accurate map of your codebase so it can answer questions, navigate dependencies, and assess the impact of changes without exploring files one by one.

KIT is built on SCIP, a semantic index that understands types, call targets, and interface implementations across your entire codebase. Your agent queries it through a set of MCP tools that return precise answers in a single call.

### What KIT gives your agent

**Accurate code navigation.** Find definitions, references, and usages across modules with compiler-level precision. No guessing, no missed matches.

**Full dependency graph.** Query complete call chains across modules in a single tool call. Your agent understands how code connects without having to explore file by file.

**Blast radius discovery.** Before making a change, your agent can identify everything that change affects — across the entire codebase, not just the immediate file.

**Fewer tokens, faster responses.** Because your agent retrieves exactly what it needs instead of reading files broadly, sessions use significantly fewer input tokens.

### Supported languages

KIT currently supports the following languages. More are on the way.

* TypeScript
* Javascript
* Python
* Java (coming soon)

### Works with your existing agent

KIT connects to your coding agent via MCP (Model Context Protocol). It works with any agent that supports MCP, including Claude, Cursor, Copilot, and others. No changes to your codebase are required.

### What's next

* [Quick Start ](/docs/code-intelligence-tools-kit/quickstart.md)— install KIT and connect it to your agent in 60 seconds
* [Tools Reference](/docs/code-intelligence-tools-kit/kit-tools-reference.md) — full reference for all code intelligence MCP tools


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://kerno.gitbook.io/docs/code-intelligence-tools-kit/overview.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.