# mcp-code-context

> Use this tool when you need to analyze code structure efficiently, reducing token usage by 87% with tree-sitter and local-first LLM capabilities. It solves problems related to code comprehension and optimization, providing structured analysis for AI agents. Ideal for use with git, it takes in code repositories and outputs optimized, token-reduced analysis results.

Canonical page: https://skillsregistry.net/skills/nikondrat-mcp-code-context  
JSON: https://api.skillsregistry.net/v1/skills/nikondrat-mcp-code-context

## Description

MCP server for AI agents — structured code analysis that cuts token usage by 87% (tree-sitter, local-first LLM)

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/nikondrat/mcp-code-context)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "nikondrat-mcp-code-context"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/nikondrat-mcp-code-context` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/nikondrat-mcp-code-context/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt