# chunker-mcp

> chunker-mcp — tarjeir-chunker-mcp. Use this tool when you need to efficiently process and store large source code files by splitting them into manageable chunks. It solves problems related to code analysis and storage by utilizing LangChain's RecursiveCharacterTextSplitter and ChromaDB vector database, allowing for efficient querying and retrieval of code chunks with associated line range metadata. Ideal for use cases involving git-based code repositories, such as code search and analysis applications.

Canonical page: https://skillsregistry.net/skills/tarjeir-chunker-mcp  
JSON: https://api.skillsregistry.net/v1/skills/tarjeir-chunker-mcp

## Description

This cli tool/Model Context Protocol (MCP) server  chunks source code files using LangChain's RecursiveCharacterTextSplitter and stores the resulting chunks in a ChromaDB vector database, including line range metadata for each chunk.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-20

## Source

- **Source listing:** [GitHub](https://github.com/tarjeir/chunker-mcp)

## 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": "tarjeir-chunker-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/tarjeir-chunker-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/tarjeir-chunker-mcp/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