# io.github.joesaby/doctree-mcp

> Use this tool when you need to efficiently search and navigate large collections of markdown documents using BM25 search algorithms. It solves problems of information retrieval and document organization for AI agents, providing a tree-based navigation interface. Ideal for use cases where fast, embedding-free, and LLM-call-free search is required, with markdown documents as input and relevant search results as output.

Canonical page: https://skillsregistry.net/skills/io-github-joesaby-doctree-mcp  
JSON: https://api.skillsregistry.net/v1/skills/io-github-joesaby-doctree-mcp

## Description

BM25 search + tree navigation over markdown docs for AI agents. No embeddings, no LLM calls.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.1
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-04-17

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/io.github.joesaby%2Fdoctree-mcp)
- **Repository:** <https://github.com/joesaby/doctree-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": "io-github-joesaby-doctree-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/io-github-joesaby-doctree-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/io-github-joesaby-doctree-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