# Docy (Documentation Access)

> Use this tool when you need to access accurate and up-to-date technical documentation from various sources, eliminating outdated information and broken links. Docy provides AI assistants with direct access to documentation content, allowing them to search, retrieve, and navigate through it seamlessly. Ideal for developers working with technical frameworks and libraries, Docy enables efficient caching and hot-reload support for real-time documentation access.

Canonical page: https://skillsregistry.net/skills/docy  
JSON: https://api.skillsregistry.net/v1/skills/docy

## Description

Docy is an MCP server that provides AI assistants with direct access to technical documentation from configured sources. Built by Oliver Borchers, it uses crawl4ai to scrape documentation websites and diskcache for efficient caching, enabling LLMs to search, retrieve, and navigate through documentation content without leaving the conversation context. The server features hot-reload support for documentation sources, intelligent caching to reduce latency, and can be deployed as a shared SSE server across multiple projects. Particularly valuable for developers who need accurate, real-time documentation access during coding sessions, Docy helps eliminate outdated information and broken links when working with technical frameworks and libraries.

## Trust

- **Trust score (0–1):** 0.93
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** devops-ci
- **Updated:** 2026-09-28

## Source

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

## 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": "docy"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/docy` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/docy/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