Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

Pustaka

MCP server that searches thesis full text from 75+ Indonesian university repositories.

Python License: AGPLv3 Universities MCP

Pustaka is an MCP server that searches thesis repositories at 75+ Indonesian universities (PTN, PTS, polytechnics). It uses OAI-PMH harvesting and HTML scraping, and reads the PDF content to work out which theses are available in full text.

Quick start

pip install "pustaka-mcp[pdf]"
pustaka

With uvx

uvx --from pustaka-mcp pustaka.exe

Claude Desktop config

{
  "mcpServers": {
    "pustaka": {
      "command": "uvx",
      "args": ["--from", "pustaka-mcp", "pustaka.exe"]
    }
  }
}

Tools

Tool Description
search_thesis Search by keyword, filter by university/type/province. Returns full/partial/locked status.
list_universities List all supported universities, filter by type (PTN/PTS) or province.
analyze_pdf Analyzes PDF content. Detects chapters, estimates page count, checks access.
search_and_analyze Combined search and PDF analysis in one call. Slower but returns accurate status immediately.

Resources

  • skripsi://universities: all universities as JSON
  • skripsi://stats: repository statistics

Status meanings

Status Meaning
FULL Chapters 1, 3, 4, 5 and bibliography detected inside the PDF
PARTIAL Some chapters found, incomplete or HTML-only detection
LOCKED PDF exists but requires login or embargo
UNKNOWN Cannot determine automatically

Environment variables

Variable Default Description
PUSTAKA_DELAY 1.2 Delay between requests (seconds)
PUSTAKA_WORKERS 5 Number of parallel threads
PUSTAKA_NO_CACHE 0 Set to 1 to disable local cache

Requirements

  • Python 3.10+
  • pdfminer.six (optional, for PDF content analysis)
pip install pustaka-mcp[pdf]

Without pdfminer.six, the server still works but uses HTML-only detection.

Original work

Pustaka is a port of Yingtze's pencari-skripsi-indonesia, which is MIT licensed. The repository configurations, OAI-PMH harvesting, HTML parsers, and PDF analysis heuristics come from that project.

License

This port is AGPL-3.0-only. See LICENSE.

Metadata

Release files for pustaka-mcp 0.1.1b3

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for pustaka-mcp 0.1.1b3
File Size Uploaded Provenance Actions
pustaka_mcp-0.1.1b3.tar.gz 120.9 kB Without provenance Details for pustaka_mcp-0.1.1b3.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for pustaka-mcp 0.1.1b3
File Interpreter ABI Platform Actions
pustaka_mcp-0.1.1b3-py3-none-any.whl Python 3 none any Details for pustaka_mcp-0.1.1b3-py3-none-any.whl

Total release size: 143.4 kB

Release files / pustaka_mcp-0.1.1b3.tar.gz

Download URL pustaka_mcp-0.1.1b3.tar.gz
Size 120.9 kB
Tags Source
SHA-256 checksum
How to use checksums
f1ee46446ac634dc39fb717b6c1650f59de207476a1d22dd1b825443022dc17d
BLAKE2b-256 checksum
How to use checksums
bd7fa9cff049716696903d3c1b354b79e155ba520bb09b5de171c0fc0e067aed
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via uv/0.13.5 {"installer":{"name":"uv","version":"0.13.5","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Release files / pustaka_mcp-0.1.1b3-py3-none-any.whl

Download URL pustaka_mcp-0.1.1b3-py3-none-any.whl
Size 22.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
5da2382a3d394d891ad38ca286af42fc7cfb6536cde5867d732e8dd33a93e001
BLAKE2b-256 checksum
How to use checksums
c4b61efc6063ac5927a0a76a61b1ee65418d280d61c522e2d6b089a81c3548cd
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via uv/0.13.5 {"installer":{"name":"uv","version":"0.13.5","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Security for pustaka-mcp 0.1.1b3

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.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page