arcanna-mcp-server

v0.1.36 suspicious
3.0
Low Risk

The Arcanna MCP server allows user to interact with Arcanna's AI use cases through the Model Context Protocol (MCP).

🤖 AI Analysis

Final verdict: SUSPICIOUS

The package shows low risks across most categories, but the non-standard network calls and concerns about the maintainer's metadata suggest potential issues that warrant further scrutiny.

  • Non-standard network calls
  • Concerns over maintainer's metadata
Per-check LLM notes
  • Network: The observed network calls could be legitimate if the package is designed to communicate with external services or APIs. However, the URLs are not standard and may require further investigation.
  • Shell: No shell execution patterns were detected.
  • Obfuscation: No obfuscation patterns detected, indicating low risk of malicious activity.
  • Credentials: No credential harvesting patterns detected, indicating low risk of secret theft.
  • Metadata: Low risk due to lack of suspicious elements, but concerns over maintainer's metadata suggest potential low effort or new account.

📦 Package Quality Overall: Low (4.6/10)

○ Low Test Suite 1.0

No test suite detected

  • No test files or test-runner configuration detected
◈ Medium Documentation 5.0

Some documentation present

  • Detailed PyPI description (2959 chars)
○ 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

  • 49 type-annotated function signatures detected in source
✦ High Multiple Contributors 10.0

Active multi-contributor project

  • 12 unique contributor(s) across 100 commits in siscale/arcanna-mcp-server
  • Active community — 5 or more distinct contributors

🔬 Heuristic Checks

⚠ Outbound Network Calls score 9.0

Found 6 network call pattern(s)

  • on/json" } response = requests.post(CUSTOM_CODE_BLOCK_TEST_URL, json=body, headers=headers)
  • on/json" } response = requests.post(CUSTOM_CODE_BLOCK_SAVE_URL, json=body, headers=headers)
  • = session_id response = requests.post( ADD_AGENTIC_NOTES_URL.format(job_id=str(job_id), ev
  • on/json" } response = requests.post(FILTER_FIELDS_URL, json=body, headers=headers) return re
  • on/json" } response = requests.post(FIELDS_MAPPING_URL, json=body, headers=headers) return r
  • torage_name}' response = requests.put(formatted_url, headers=headers) return response.json()
✓ 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

Email domain looks legitimate: siscale.com>

✓ Suspicious Page Links

All external links appear legitimate

✓ Git Repository History

Repository siscale/arcanna-mcp-server appears legitimate

⚠ 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 arcanna-mcp-server 
Create a Flask-based web application that leverages the 'arcanna-mcp-server' package to provide users with interactive access to various AI use cases provided by Arcanna. This application will serve as a bridge between the Arcanna platform and end-users, allowing them to query and receive responses from AI models in real-time. Here’s a step-by-step guide on how to develop this mini-application:

1. **Set Up Your Development Environment:** Ensure you have Python installed along with Flask and the 'arcanna-mcp-server' package. Set up a virtual environment if necessary.

2. **Initialize the Project Structure:** Create a directory for your project and set up the basic Flask structure including app.py, templates, and static directories.

3. **Configure Arcanna MCP Server:** Use 'arcanna-mcp-server' to establish a connection to Arcanna's AI services. Configure the server settings according to the documentation provided by Arcanna, ensuring secure communication and authentication.

4. **Develop User Interface:** Design a simple yet intuitive UI using HTML/CSS within the templates folder. Include forms for users to input queries and display areas for AI-generated responses.

5. **Implement Core Functionality:** In app.py, write functions to handle incoming HTTP requests from the UI. These functions will utilize 'arcanna-mcp-server' to send user queries to Arcanna’s AI models and return the results back to the client.

6. **Enhance with Additional Features:** Consider adding features such as:
   - User Authentication: Allow users to register/login before interacting with AI services.
   - History Log: Keep a record of user interactions and previous queries/responses.
   - Customizable Models: Enable users to choose from different AI models available through Arcanna.

7. **Testing & Deployment:** Thoroughly test the application locally to ensure all functionalities work as expected. Once satisfied, deploy the application to a hosting service like Heroku or AWS.

Remember, the key goal is to create a seamless user experience where users can easily interact with complex AI technologies through a straightforward interface.

💬 Discussion Feed

Leave a comment

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