asset-aware-mcp

v0.7.0 suspicious
4.0
Medium Risk

Medical RAG with Asset-Aware MCP - Precise PDF asset retrieval (tables, figures, sections) for AI Agents

🤖 AI Analysis

Final verdict: SUSPICIOUS

The package shows low risks in terms of obfuscation and credential harvesting, but incomplete author information and potential inactivity raise some concerns about its legitimacy.

  • Low obfuscation risk
  • Low credential risk
  • Incomplete author metadata
Per-check LLM notes
  • Obfuscation: No obfuscation patterns detected, indicating low risk of malicious activity.
  • Credentials: No credential harvesting patterns detected, indicating low risk of secret theft.
  • Metadata: The author information is incomplete and the account seems new or inactive, raising some suspicion but not conclusive evidence of malice.

📦 Package Quality Overall: Medium (6.8/10)

◈ Medium Test Suite 6.0

Partial test coverage signals detected

  • Test runner config found: pyproject.toml
◈ Medium Documentation 7.0

Some documentation present

  • Documentation URL: "Documentation" -> https://u9401066.github.io/asset-aware-mcp/#/overview-zh
  • Detailed PyPI description (15401 chars)
○ Low Contributing Guide 4.0

No contributing guide or governance files found

  • Development Status classifier >= Beta
◈ Medium Type Annotations 7.0

Partial type annotation coverage

  • Classifier: Typing :: Typed
  • 791 type-annotated function signatures detected in source
✦ High Multiple Contributors 10.0

Active multi-contributor project

  • 5 unique contributor(s) across 100 commits in u9401066/asset-aware-mcp
  • Active community — 5 or more distinct contributors

🔬 Heuristic Checks

⚠ Outbound Network Calls score 3.0

Found 2 network call pattern(s)

  • nt": prompt}) async with httpx.AsyncClient(timeout=timeout) as client: response = await client.
  • np.array([]) async with httpx.AsyncClient(timeout=timeout) as client: # Try the current batch
✓ Code Obfuscation

No obfuscation patterns detected

⚠ Shell / Subprocess Execution score 6.0

Found 3 shell execution pattern(s)

  • dir: result = subprocess.run( [ libreoffice_b
  • ame) result = subprocess.run( [ libreoffice_b
  • try: result = subprocess.run( ["tasklist", "/FI", f"PID eq {pid}", "/FO",
✓ Credential Harvesting

No credential harvesting patterns detected

✓ Typosquatting

No typosquatting candidates detected

✓ Registered Email Domain

Email domain looks legitimate: gap.kmu.edu.tw>

✓ Suspicious Page Links

All external links appear legitimate

✓ Git Repository History

Repository u9401066/asset-aware-mcp appears legitimate

⚠ Maintainer History score 4.0

2 maintainer concern(s) found

  • Author name is missing or very short
  • Author "" appears to have only 1 package on PyPI (new or inactive account)
✓ Known CVE Vulnerabilities

No known vulnerabilities found in OSV database.

💡 AI App Starter Prompt

Use this prompt to build a project with asset-aware-mcp 
Create a medical research assistant app using the 'asset-aware-mcp' package in Python. This app will serve as a powerful tool for researchers and medical professionals to quickly retrieve specific assets from medical research papers, such as tables, figures, and sections. The goal is to streamline the process of finding precise information within complex PDF documents, enhancing the efficiency of research and decision-making processes.

### Key Features:
- **PDF Document Upload**: Users should be able to upload multiple PDF files from their local machine or a cloud storage service.
- **Search Functionality**: Implement a search bar where users can input keywords or phrases to find relevant content within the uploaded PDFs. The app should return exact matches along with context from surrounding text.
- **Asset Retrieval**: Once a document is searched, the app should highlight and extract specific assets like tables, figures, and sections that contain the searched keyword(s). Each asset should be clearly labeled and presented in a user-friendly format.
- **Contextual Information**: Alongside the extracted assets, provide additional contextual information such as page numbers, section headings, and related paragraphs to give users a comprehensive view of the found content.
- **Bookmarking and Annotation**: Allow users to bookmark important findings and add annotations directly on the extracted assets for future reference.
- **Integration with External Tools**: Consider integrating the app with external tools commonly used in the medical field, such as citation managers or data analysis software.

### Utilizing 'asset-aware-mcp':
- Use the 'asset-aware-mcp' package to handle the extraction and identification of specific assets (tables, figures, sections) from the uploaded PDFs. This involves utilizing the package’s capabilities to accurately parse and retrieve these elements based on user queries.
- Ensure that the integration of 'asset-aware-mcp' enhances the precision and speed of asset retrieval, making the app more effective than traditional methods of searching through PDF documents.

### Development Steps:
1. Set up a development environment with Python and install necessary packages including 'asset-aware-mcp'.
2. Design a user interface that allows for easy file uploads and provides a clean layout for displaying search results.
3. Implement backend logic to handle file uploads, parsing with 'asset-aware-mcp', and search functionality.
4. Develop the asset retrieval system using 'asset-aware-mcp' to ensure accurate and efficient extraction of assets.
5. Add bookmarking and annotation features to enhance usability.
6. Test the app thoroughly to ensure reliability and performance, especially focusing on accuracy of asset retrieval.
7. Deploy the app either as a web application or a desktop application depending on target user preferences.

💬 Discussion Feed

Leave a comment

No discussion yet. Be the first to share your thoughts!