Nuanced

🚀 Nuanced MCP Server

An MCP (Model Context Protocol) server that provides code structure analysis capabilities through the nuanced library.

Overview

This MCP server enables LLMs to access function call graphs through standardized tools and resources, thereby understanding code structures. It allows AI assistants to:

• Initialize a code graph for a Python repository.
• Explore function call relationships.
• Analyze dependencies between functions.
• Provide more context-aware code assistance.

API

Tools

• initialize_graph

  • Initialize the code graph for a given repository path.
  • Input: repo_path (string)

• switch_repository

  • Switch to a different initialized repository.
  • Input: repo_path (string)

• list_repositories

  • List all initialized repositories.
  • No input required.

• get_function_call_graph

  • Get the call graph for a specific function.
  • Input:
    • file_path (string)
    • function_name (string)
    • repo_path (string, optional) — If not specified, the active repository is used.

• analyze_dependencies

  • Find all module or file dependencies in the codebase.
  • Input (at least one is required):
    • file_path (string, optional)
    • module_name (string, optional)

• analyze_change_impact

  • Analyze the impact of changing a specific function.
  • Input:
    • file_path (string)
    • function_name (string)

Resources

• graph://summary

  • Get a summary of the currently loaded code graph.
  • No parameters required.

• graph://repo/{repo_path}/summary

  • Get a summary of the code graph for a specific repository.
  • Parameters:
    • repo_path (string) — Repository path

• graph://function/{file_path}/{function_name}

  • Get detailed information about a specific function.
  • Parameters:
    • file_path (string) — Path to the file containing the function
    • function_name (string) — Name of the function to analyze

Prompts

• analyze_function

  • Create a prompt to analyze a function with a call graph.
  • Parameters:
    • file_path (string) — Path to the file containing the function
    • function_name (string) — Name of the function to analyze

• impact_analysis

  • Create a prompt to analyze the impact of changing a function.
  • Input parameters:
    • file_path (string) — Path to the file containing the function
    • function_name (string) — Name of the function to analyze

• analyze_dependencies_prompt

  • Create a prompt to analyze module or file dependencies.
  • Input parameters (at least one is required):
    • file_path (string, optional) — Path to the file to analyze
    • module_name (string, optional) — Name of the module to analyze

Using Claude Desktop

Add the following to your claude_desktop_config.json:

UV

{
  "mcpServers": {
    "nuanced": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/nuanced-mcp",
        "run",
        "nuanced_mcp_server.py"
      ]
    }
  }
}