Back to MCP Directory
Filescopemcp
Model Context Protocol moderate risk

Filescopemcp

Analyzes codebase structure, ranks file importance, tracks dependencies, and provides summaries for enhanced code understanding by AI assistants.

Connections & Capabilities

Connects To

GitHubFilesystem

Capabilities

readwrite

Quickstart

Config

{
  "mcpServers": {
    "FileScopeMCP": {
      "command": "node",
      "args": ["<build script sets this>/mcp-server.js","--base-dir=C:/Users/admica/my/project/base"],
      "transport": "stdio",
      "disabled": false,
      "alwaysAllow": []
    }
  }
}

Exposed MCP Tools (15)

safe
list_saved_trees

Lists all saved file tree configurations.

Read-only operation, no modification of data.

moderate
create_file_tree

Creates a new file tree configuration for a specific directory.

Creates a new configuration file, but does not access sensitive data.

safe
select_file_tree

Selects an existing file tree to work with.

Read-only operation, selects a configuration file.

high
delete_file_tree

Deletes a file tree configuration.

Deletes a configuration file, potentially losing analysis data.

safe
list_files

Lists all files in the project with their importance rankings.

Read-only operation, no modification of data.

safe
get_file_importance

Gets detailed information about a specific file, including dependencies and dependents.

Read-only operation, no modification of data.

safe
find_important_files

Finds the most important files in the project based on configurable criteria.

Read-only operation, no modification of data.

safe
read_file_content

Reads the content of a specific file.

Read-only operation, accesses file content.

safe
recalculate_importance

Recalculates importance values for all files based on dependencies.

Read-only operation, recalculates values based on existing data.

safe
get_file_summary

Gets the stored summary of a specific file.

Read-only operation, retrieves stored summary.

moderate
set_file_summary

Sets or updates the summary of a specific file.

Writes a summary to the configuration file.

moderate
toggle_file_watching

Toggles file watching on/off.

Modifies the file watching configuration.

safe
get_file_watching_status

Gets the current status of file watching.

Read-only operation, retrieves file watching status.

moderate
update_file_watching_config

Updates file watching configuration.

Modifies the file watching configuration.

moderate
generate_diagram

Creates Mermaid diagrams with customizable options.

Generates diagram files based on project structure.

Safety Assessment

The FileScopeMCP server is relatively safe for read-only operations and code analysis. Risks are elevated when enabling file watching or when AI is used to generate summaries, as this could expose sensitive information. Ensure the base directory is properly scoped and file watching is configured with appropriate exclusions.

  • Read-only access to file contents by default.
  • Persistent storage of file tree data in JSON format.
  • No direct execution of code within the server.
  • File watching can be toggled off for increased security.
  • Potential for information leakage through file summaries.
  • File system access based on configured base directory.
  • Dependency on external libraries (Mermaid.js) for diagram generation.
  • File watching feature could introduce performance overhead and potential vulnerabilities if not configured carefully.
Filescopemcp Review, Pricing & Alternatives (2026) | Flaex AI