# Documentation Search

> Use this tool when you need to quickly retrieve the latest documentation for popular Python libraries, such as LangChain, LlamaIndex, and OpenAI. It solves the problem of searching for up-to-date library information by performing targeted Google searches within specific documentation domains and extracting relevant content. The tool takes library names and keywords as input and returns relevant documentation results, making it ideal for developers seeking efficient access to library documentation without leaving their conversation.

Canonical page: https://skillsregistry.net/skills/documentation-search  
JSON: https://api.skillsregistry.net/v1/skills/documentation-search

## Description

This MCP server implementation provides a documentation search tool that allows Claude to retrieve the latest documentation for popular Python libraries including LangChain, LlamaIndex, and OpenAI. It uses the Serper API to perform targeted Google searches within specific documentation domains, then fetches and extracts the content from the search results. The implementation is lightweight, requiring only a few dependencies (BeautifulSoup, httpx, and MCP), making it easy to integrate into existing workflows for developers who need quick access to up-to-date library documentation without leaving their conversation with Claude.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-02

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/documentation-search)
- **Repository:** <https://github.com/graphfied/mcp-claude-desktop-connect>

## 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": "documentation-search"
    }
  }
}
```

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