aimemory-mcp-server

v1.5.0 suspicious
7.0
High Risk

AI Memory MCP Server — persistent memory for AI assistants via Model Context Protocol

🤖 AI Analysis

Final verdict: SUSPICIOUS

The package exhibits moderate risk due to obfuscation and metadata concerns, but lacks clear evidence of malicious activity or network/shell execution risks.

  • High obfuscation risk (6/10) suggesting possible attempts to hide functionality.
  • Metadata issues including lack of maintainer details and low repository engagement.
Per-check LLM notes
  • Network: No network calls detected, which is normal if the package does not require external communication.
  • Shell: No shell execution patterns detected, indicating no immediate signs of executing system commands.
  • Obfuscation: The code uses unusual formatting and imports to obscure its functionality, which could indicate an attempt to hide malicious behavior.
  • Credentials: No clear patterns of credential harvesting are present in the provided snippets.
  • Metadata: Suspicious due to lack of maintainer details, low repository engagement, and presence of non-secure external links.

📦 Package Quality Overall: Low (4.4/10)

○ Low Test Suite 1.0

No test suite detected

  • No test files or test-runner configuration detected
◈ Medium Documentation 7.0

Some documentation present

  • Documentation URL: "Documentation" -> https://aimemory.pro/docs/mcp
  • Detailed PyPI description (10387 chars)
○ Low Contributing Guide 4.0

No contributing guide or governance files found

  • Development Status classifier >= Beta
◈ Medium Type Annotations 5.0

Partial type annotation coverage

  • 32 type-annotated function signatures detected in source
◈ Medium Multiple Contributors 5.0

Limited contributor diversity

  • 1 unique contributor(s) across 100 commits in jingchang0623-crypto/aimemory
  • Single author but highly active (100 commits)

🔬 Heuristic Checks

✓ Outbound Network Calls

No suspicious network call patterns found

⚠ Code Obfuscation score 6.0

Found 3 obfuscation pattern(s)

  • y: for tag in __import__("json").loads(row[0]): tag_counts[tag] = tag_co
  • ories, "exported_at": __import__("datetime").datetime.now(__import__("datetime").timezone.utc).isoformat
  • rt__("datetime").datetime.now(__import__("datetime").timezone.utc).isoformat(), } @mcp.tool() def import_m
✓ Shell / Subprocess Execution

No shell execution patterns detected

✓ Credential Harvesting

No credential harvesting patterns detected

✓ Typosquatting

No typosquatting candidates detected

✓ Registered Email Domain

Email domain looks legitimate: aimemory.pro>

⚠ Suspicious Page Links score 2.0

Found 1 suspicious link(s) on the package page

  • Non-HTTPS external link: http://your-server:8090/sse
⚠ Git Repository History score 2.5

Git history flags: Repository has zero stars and zero forks

  • Repository has zero stars and zero forks
⚠ 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 aimemory-mcp-server 
Develop a personal AI assistant named 'MemoBot' that leverages the 'aimemory-mcp-server' package to maintain a persistent context across conversations. MemoBot should be able to remember previous interactions and use this information to provide more personalized and relevant responses over time. Here’s a step-by-step guide on how to build MemoBot:

1. **Setup Environment**: Begin by setting up your Python development environment and installing the necessary packages, including 'aimemory-mcp-server'. Ensure you have a server running to host the 'aimemory-mcp-server'.
2. **Design User Interface**: Create a simple CLI or web-based interface for users to interact with MemoBot. This interface should allow users to initiate new conversations, view past interactions, and manage their data.
3. **Integrate 'aimemory-mcp-server'**: Use the 'aimemory-mcp-server' API to store and retrieve conversation contexts. Each interaction between the user and MemoBot should update the context stored in the server, allowing MemoBot to recall past details and continue conversations seamlessly.
4. **Implement AI Logic**: Develop the core logic of MemoBot using an AI model that can understand natural language and generate appropriate responses based on the context retrieved from the server. Consider integrating existing NLP models like GPT-3 or BERT for advanced functionality.
5. **User Data Management**: Implement features that allow users to manage their data securely, such as deleting past conversations or opting out of storing certain types of information.
6. **Testing and Iteration**: Test MemoBot thoroughly to ensure it maintains accurate and useful context throughout conversations. Gather feedback and make iterative improvements to enhance its performance and user experience.
7. **Deployment**: Once satisfied with the functionality, deploy MemoBot to a public server or cloud service so others can access it. Ensure all security measures are in place to protect user data.

Suggested Features:
- Persistent Conversation Context: MemoBot remembers previous interactions to provide contextually relevant responses.
- Personalization Options: Users can customize MemoBot's behavior and appearance according to their preferences.
- Data Privacy Controls: Users have full control over their data, including options to delete past conversations.
- Multilingual Support: Extend MemoBot’s capabilities to support multiple languages for a wider audience.

💬 Discussion Feed

Leave a comment

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