amfs-mcp-server

v0.7.3 suspicious
4.0
Medium Risk

AMFS MCP Server — expose Agent Memory as MCP tools for Cursor and Claude Code

🤖 AI Analysis

Final verdict: SUSPICIOUS

The package exhibits low maintenance and poor metadata quality, raising concerns about its legitimacy and purpose. While direct security risks like shell execution and obfuscation are minimal, these factors combined with the lack of a clear description warrant further investigation.

  • Low maintenance and poor metadata quality
  • Lack of package description
Per-check LLM notes
  • Network: The network calls appear to be standard API interactions and may be part of the package's intended functionality.
  • Shell: No shell execution patterns were detected, indicating no immediate risk from this aspect.
  • Obfuscation: No obfuscation patterns detected, indicating low risk.
  • Credentials: No credential harvesting patterns detected, indicating low risk.
  • Metadata: The package shows low maintenance and poor metadata quality, which may indicate low effort or potential malicious intent.

📦 Package Quality Overall: Low (2.0/10)

○ Low Test Suite 1.0

No test suite detected

  • No test files or test-runner configuration detected
○ Low Documentation 1.0

No documentation detected

  • No documentation URL, doc files, or meaningful description found
○ Low Contributing Guide 2.0

No contributing guide or governance files found

  • No CONTRIBUTING, CODE_OF_CONDUCT, or governance files found
◈ Medium Type Annotations 5.0

Partial type annotation coverage

  • 35 type-annotated function signatures detected in source
○ Low Multiple Contributors 1.0

Unable to verify contributor count: no GitHub repository found

  • No GitHub repository linked — contributor count unavailable

🔬 Heuristic Checks

⚠ Outbound Network Calls score 4.5

Found 3 network call pattern(s)

  • ntity_paths[0] resp = httpx.get(f"{base_url}/api/v1/pro/export", params=params, headers=head
  • == "GET": resp = httpx.get(f"{base_url}{path}", params=params, headers=headers, timeout
  • else: resp = httpx.post(f"{base_url}{path}", params=params, json=body or {}, headers
✓ Code Obfuscation

No obfuscation patterns detected

✓ Shell / Subprocess Execution

No shell execution patterns detected

✓ Credential Harvesting

No credential harvesting patterns detected

✓ Typosquatting

No typosquatting candidates detected

✓ Registered Email Domain

No author email provided

✓ Suspicious Page Links

All external links appear legitimate

✓ Git Repository History

No GitHub repository linked

  • No GitHub repository link found
⚠ Maintainer History score 6.0

3 maintainer concern(s) found

  • Author name is missing or very short
  • Author "" appears to have only 1 package on PyPI (new or inactive account)
  • Package has no PyPI classifiers (low effort / metadata quality)
✓ Known CVE Vulnerabilities

No known vulnerabilities found in OSV database.

💡 AI App Starter Prompt

Use this prompt to build a project with amfs-mcp-server 
Create a mini-application named 'AMFSClaudeHelper' that integrates the 'amfs-mcp-server' package to facilitate interaction between Agent Memory and the Claude AI system. This application will serve as a bridge, allowing users to leverage Agent Memory data within the Claude AI environment through MCP tools. Here’s a detailed guide on how to build it:

1. **Setup**: Begin by installing the 'amfs-mcp-server' package using pip. Ensure you have a basic understanding of how Agent Memory works and how it can be interfaced with through MCP tools.
2. **Design**: Design the application to allow users to input queries or commands that can then be processed and executed against the Agent Memory via the MCP server. Consider implementing a simple GUI or command-line interface for user interaction.
3. **Core Functionality**:
   - Implement a function to connect to the MCP server using 'amfs-mcp-server'. This function should handle authentication and establish a stable connection.
   - Develop a method to query Agent Memory for specific data points based on user inputs. This could involve keyword searches, date ranges, or other filters.
4. **Features**:
   - Include a feature to display results from Agent Memory in a readable format (e.g., JSON, plain text).
   - Allow users to update or modify entries in Agent Memory directly from the application.
   - Implement error handling to manage issues such as invalid queries, connection failures, or data access errors.
5. **Integration with Claude**:
   - Utilize Claude's capabilities to analyze the retrieved data from Agent Memory and provide insights or summaries.
   - Enable users to send the analyzed data back to Agent Memory for future reference or updates.
6. **Testing**: Conduct thorough testing to ensure all functionalities work as expected. Test different scenarios including edge cases to ensure robustness.
7. **Documentation**: Provide clear documentation on how to use the application, including setup instructions, usage examples, and troubleshooting tips.
8. **Deployment**: Prepare the application for deployment. Consider packaging it as a standalone executable or a web-based service depending on your target audience and use case.

By following these steps, you'll create a powerful tool that leverages the capabilities of both Agent Memory and the Claude AI system, enhancing data retrieval, analysis, and management processes.

💬 Discussion Feed

Leave a comment

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