anthropic-admin-mcp

v0.1.1 suspicious
5.0
Medium Risk

MCP server for the Anthropic Admin API — manage your Claude org from any MCP-compatible client.

🤖 AI Analysis

Final verdict: SUSPICIOUS

The package appears to have legitimate purposes but exhibits suspicious metadata activity, raising concerns about its provenance and integrity.

  • Suspicious metadata risk
  • Potential issues with git repository and maintainer history
Per-check LLM notes
  • Network: The network call pattern indicates the package is likely communicating with an external service, which could be legitimate if documented and necessary for its functionality.
  • Shell: No shell execution patterns were detected, suggesting no immediate risk from command execution.
  • Obfuscation: No obfuscation patterns detected, indicating low risk.
  • Credentials: No credential harvesting patterns detected, indicating low risk.
  • Metadata: Suspicious activity around the git repository and maintainer history suggest potential risk.

📦 Package Quality Overall: Low (4.4/10)

◈ Medium Test Suite 6.0

Partial test coverage signals detected

  • 1 test file(s) detected (e.g. test_safety.py)
◈ Medium Documentation 5.0

Some documentation present

  • Detailed PyPI description (5780 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

  • 64 type-annotated function signatures detected in source
○ Low Multiple Contributors 2.0

Single-author or unverifiable project

  • 1 unique contributor(s) across 3 commits in Trushtonfactory/anthropic-admin-mcp
  • Single author with few commits — possibly a personal or throwaway project

🔬 Heuristic Checks

⚠ Outbound Network Calls score 1.5

Found 1 network call pattern(s)

  • ) self._client = httpx.Client( base_url=BASE_URL, 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 score 7.5

Git history flags: Repository has zero stars and zero forks

  • Repository has zero stars and zero forks
  • Single contributor with only 3 commit(s) — possibly throwaway account
  • All 3 commits happened within 24 hours
⚠ Maintainer History score 2.0

1 maintainer concern(s) found

  • Author "Tyler Rushton" 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 anthropic-admin-mcp 
Develop a Python-based command-line tool that allows users to interact with their Claude organization via the Anthropic Admin API using the 'anthropic-admin-mcp' package. This tool should serve as a versatile interface for managing various aspects of the Claude org such as user management, access control, and resource allocation. Here’s a detailed outline of the project steps and features:

1. **Setup Environment**: Begin by setting up a virtual environment for your Python project. Ensure you have Python 3.8 or higher installed.
2. **Install Dependencies**: Use pip to install the 'anthropic-admin-mcp' package along with other necessary libraries such as 'requests' for handling HTTP requests.
3. **Authentication Module**: Implement an authentication module that securely handles API keys or tokens required to communicate with the Anthropic Admin API. This should include a method for securely storing these credentials.
4. **Command-Line Interface (CLI)**: Develop a CLI where users can input commands to perform various actions on their Claude org. For example, they should be able to add new users, modify permissions, and view current resource usage.
5. **User Management**: Allow users to create, update, delete, and list members within their Claude organization through the CLI.
6. **Access Control**: Provide options for adjusting access levels for different users or groups within the organization.
7. **Resource Management**: Enable users to monitor and adjust resource allocations such as API call limits, data storage, etc.
8. **Logging & Error Handling**: Implement robust logging and error handling mechanisms to ensure that all interactions are recorded and errors are gracefully handled.
9. **Documentation**: Create comprehensive documentation for the CLI, including setup instructions, command reference, and examples of common use cases.

The 'anthropic-admin-mcp' package will be crucial for establishing the connection to the Anthropic Admin API and facilitating the communication between your CLI and the API endpoints. It simplifies the process of sending requests and receiving responses, making it easier to implement the functionalities listed above.

💬 Discussion Feed

Leave a comment

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