# Tree-sitter

> Use this tool when you need to analyze and understand source code across multiple programming languages, and leverage its capabilities to solve problems such as code review, refactoring, and documentation generation. It takes in source code as input and outputs a traversable abstract syntax tree, enabling AI assistants to extract semantic information and perform code searches. Use Tree-sitter in workflows requiring deep code comprehension, where a unified interface for code analysis is necessary.

Canonical page: https://skillsregistry.net/skills/wrale-tree-sitter  
JSON: https://api.skillsregistry.net/v1/skills/wrale-tree-sitter

## Description

MCP Server Tree-sitter provides code analysis capabilities through the tree-sitter parsing library, enabling AI assistants to understand and manipulate source code across multiple programming languages. Built by Wrale, this implementation leverages the tree-sitter-language-pack to support a wide range of languages with a unified interface for traversing abstract syntax trees, performing code searches, and extracting semantic information. The server is designed for workflows requiring deep code comprehension, such as code review, refactoring suggestions, and documentation generation, allowing AI assistants to work with code in a structured way rather than treating it as plain text.

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** search
- **Updated:** 2026-09-01

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/wrale-tree-sitter)
- **Repository:** <https://github.com/wrale/mcp-server-tree-sitter>

## 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": "wrale-tree-sitter"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/wrale-tree-sitter` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/wrale-tree-sitter/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