Nano PDF MCP
A memory-efficient Model Context Protocol (MCP) server for reading and splitting large PDF files.
Built with fastmcp and pymupdf (PyMuPDF).
Tools
| Tool | 설명 |
|---|---|
get_pdf_info |
파일 메타데이터 및 총 페이지 수 조회 — read_pdf 호출 전에 먼저 사용하세요 |
read_pdf |
지정 페이지 범위 텍스트 스트리밍 추출 |
split_pdf |
지정 페이지만 모아 새 PDF 생성 |
save_markdown_summary |
AI 정리 내용을 .md 파일로 저장 |
권장 사용 순서
1. get_pdf_info(filepath) → 총 페이지 수 확인
2. read_pdf(filepath, start_page, end_page) → 텍스트 읽기
3. save_markdown_summary(output_filepath, markdown_content) → 요약 저장
Installation
클론하거나 로컬에 설치하지 않아도 됩니다!
uv가 설치되어 있다면 아래 한 줄로 바로 실행됩니다.
Claude Desktop
claude_desktop_config.json에 아래 내용을 추가하세요:
{
"mcpServers": {
"nano-pdf-mcp": {
"command": "uvx",
"args": ["nano-pdf-mcp"]
}
}
}
Antigravity
.gemini/settings.json에 아래 내용을 추가하세요:
{
"mcpServers": {
"nano-pdf-mcp": {
"command": "uvx",
"args": ["nano-pdf-mcp"]
}
}
}
Architecture
- 메모리 효율: 페이지 단위 스트리밍으로 대용량 PDF 처리 (전체 로드 없음)
- 빠른 분할:
insert_pdf로 C 레벨 포인터만 복사 — 재인코딩 없음 - 안전한 로깅: 모든 로그는
stderr로 출력 (stdio 통신 오염 방지) - 명확한 오류: 잘못된 범위/경로 입력 시 즉각 오류 메시지 반환
1 maintainer
Metadata
1 maintainer
Release files for nano-pdf-mcp 0.2.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| nano_pdf_mcp-0.2.0.tar.gz | 3.9 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| nano_pdf_mcp-0.2.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 8.4 kB
Release files / nano_pdf_mcp-0.2.0.tar.gz
| Download URL | nano_pdf_mcp-0.2.0.tar.gz |
|---|---|
| Size | 3.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
62ae9f939462b8f193607654fcd497337f9a04ee9ec980e6789dbfa623a2addf
|
|
BLAKE2b-256 checksum How to use checksums |
6dc7fb6a48b7e656c7c1eb9acb957a32d4dcb509d8122a0c0f5366ba4d61cd55
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.0
|
Release files / nano_pdf_mcp-0.2.0-py3-none-any.whl
| Download URL | nano_pdf_mcp-0.2.0-py3-none-any.whl |
|---|---|
| Size | 4.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
f7d2256818cd944f8d2928e5db6ccd05b015e1e9266e03c7005e1b511cd37647
|
|
BLAKE2b-256 checksum How to use checksums |
9c54db2f07fb1698ad915daeac5084a089735e311e085494819d3289df9dbb47
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.0
|
Security for nano-pdf-mcp 0.2.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
