mcp-documentation-server MCP — 사용 사례, 설치 & 라이브 데모

왜 쓰나요

핵심 기능

Local-first: no cloud DB, no external calls unless you enable Gemini
Parent-child chunking balances precision and context
Hybrid full-text + vector search
Built-in web dashboard on port 3080 for drag-and-drop uploads
Supports .txt, .md, and .pdf out of the box

라이브 데모

실제 사용 모습

documentation-server.replay ▶ 준비됨

0/0

설치

클라이언트 선택

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "documentation-server": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-documentation-server"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop → Settings → Developer → Edit Config 열기. 저장 후 앱 재시작.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "documentation-server": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-documentation-server"
      ],
      "_inferred": true
    }
  }
}

Cursor는 Claude Desktop과 동일한 mcpServers 스키마 사용. 프로젝트 설정이 전역보다 우선.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "documentation-server": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-documentation-server"
      ],
      "_inferred": true
    }
  }
}

Cline 사이드바의 MCP Servers 아이콘 클릭 후 "Edit Configuration" 선택.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "documentation-server": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-documentation-server"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "documentation-server",
      "command": "npx",
      "args": [
        "-y",
        "mcp-documentation-server"
      ]
    }
  ]
}

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.config/zed/settings.json

{
  "context_servers": {
    "documentation-server": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "mcp-documentation-server"
        ]
      }
    }
  }
}

context_servers에 추가. 저장 시 Zed가 핫 리로드.

claude mcp add documentation-server -- npx -y mcp-documentation-server

한 줄 명령. claude mcp list로 확인, claude mcp remove로 제거.

사용 사례

실전 활용법: mcp-documentation-server

Make a new framework's docs queryable by your AI

👤 Devs adopting a new library ⏱ ~20 min beginner

언제 쓸까: Official docs are huge; you want Claude to answer with grounded citations.

사전 조건

mcp-documentation-server installed — npx -y @andrea9293/mcp-documentation-server

흐름

Ingest the docs

Upload the library's docs .md files to the dashboard at http://localhost:3080.✓ 복사됨

→ Files processed into chunks
Ask targeted questions

search_documents for 'how to configure middleware' — give me the top 3 chunks with source paths.✓ 복사됨

→ Cited excerpts
Ask grounded synthesis

Given those chunks, write the minimum viable config for middleware in this framework.✓ 복사됨

→ Working config backed by cited doc lines

결과: A personal docs assistant that cites its sources.

함정

PDFs with scanned images aren't OCR'd — Pre-OCR with tools like ocrmypdf before upload
Huge doc sets without Gemini give noisy embeddings — Optional GEMINI_API_KEY unlocks higher-quality semantic search

함께 쓰기: filesystem

Turn an internal wiki export into a RAG source

👤 Teams with markdown-export-friendly wikis ⏱ ~25 min beginner

언제 쓸까: You've exported your Notion/Confluence content as Markdown and want AI access.

흐름

Bulk-ingest via process_uploads

process_uploads on ./wiki-export/ — process every .md.✓ 복사됨

→ Document count per folder
Full-scope search

search_all_documents: 'deployment runbook' — top 5.✓ 복사됨

→ Ranked list

결과: A local, private, searchable wiki.

Build a personal research-paper library

👤 Researchers, students ⏱ ~30 min beginner

언제 쓸까: You download papers and want them queryable instead of piled in Downloads/

흐름

Drop PDFs in

Upload all PDFs in ~/Papers/ to the documentation server.✓ 복사됨

→ Papers chunked and indexed
Ask across corpus

search_documents: 'attention variants with lower quadratic cost' — return authors + years.✓ 복사됨

→ Cited excerpts

결과: A local mini-perplexity over your own paper collection.

조합

다른 MCP와 조합해 10배 효율

documentation-server + filesystem

Automate ingest from a watched folder

Every time a new PDF lands in ~/Papers/Inbox, process_uploads it into the documentation server.✓ 복사됨

documentation-server + swarmvault

Compare: documentation-server is quick-ingest; swarmvault builds a structured wiki

Ingest my research PDFs into both systems; compare retrieval quality on the same query.✓ 복사됨

도구

이 MCP가 노출하는 것

도구	입력	언제 호출	비용
add_document	title, content, metadata?	Programmatic ingest	free (local embeddings)
list_documents	(none)	See what's indexed	free
get_document	id	Retrieve a specific doc	free
delete_document	id	Pruning	free
search_documents	query, top_k?	Query within a specific doc set	free
search_all_documents	query, top_k?	Global RAG query	free
get_context_window	chunk_id	Expand a narrow hit into broader context	free
search_documents_with_ai	query	One-shot answer synthesis	Gemini call (needs key)
process_uploads	path?: str	Batch import from the uploads folder	free

비용 및 제한

운영 비용

API 쿼터: None if local; Gemini usage if GEMINI_API_KEY set
호출당 토큰: Search returns 500-3000 tokens depending on top_k
금액: Free; Gemini is paid per-call if enabled
팁: Skip Gemini for exploratory work — local embeddings are good enough for known-item lookups.

보안

권한, 시크릿, 파급범위

자격 증명 저장: GEMINI_API_KEY (optional) in env

데이터 외부 송신: Local only unless Gemini is enabled; dashboard on port 3080

Dashboard on :3080 has no auth — bind to localhost only.
Document content sits in the MCP_BASE_DIR as JSON; treat it like any local data.

문제 해결

자주 발생하는 오류와 해결

Port 3080 in use

Set WEB_PORT env var to another port.

확인: lsof -i :3080

PDF parse error

Password-protected or scanned PDFs fail. Remove password or run OCR first.

확인: Try a plain PDF

search returns empty

Check documents ingested: list_documents. If empty, re-run process_uploads.

확인: list_documents

대안

mcp-documentation-server 다른 것과 비교

대안	언제 쓰나	단점/장점
swarmvault	You want a structured wiki + knowledge graph, not just search	Heavier; more upfront setup
Cloud RAG (Pinecone, Weaviate)	You need team-shared, scale	Paid; data leaves your machine
llm-context.py	You want per-task context, not persistent doc retrieval	Different problem

mcp-documentation-server