Skip to content
Back to search

ls-mcp

List MCP Server configurations in your system used by AI applications like Cursor, Claude Desktop, VS Code and others

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/lirantal/ls-mcp with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/lirantal/ls-mcp'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/lirantal--ls-mcp/badge.svg)](/listings/lirantal--ls-mcp)

HTML

<a href="/listings/lirantal--ls-mcp"><img src="/api/listings/lirantal--ls-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 125 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <!-- markdownlint-disable -->
  2. <p align="center"><h1 align="center">
  3. ls-mcp
  4. </h1>
  5. </p>
  6. <p align="center">
  7. Detect Configured MCP (Model Context Protocol) in your local dev environment
  8. </p>
  9. <p align="center">
  10. <a href="https://www.npmjs.com/package/ls-mcp"><img src="https://badgen.net/npm/v/ls-mcp" alt="npm version"/></a>
  11. <a href="https://www.npmjs.com/package/ls-mcp"><img src="https://badgen.net/npm/license/ls-mcp" alt="license"/></a>
  12. <a href="https://www.npmjs.com/package/ls-mcp"><img src="https://badgen.net/npm/dt/ls-mcp" alt="downloads"/></a>
  13. <a href="https://github.com/lirantal/ls-mcp/actions/workflows/ci.yml"><img src="https://github.com/lirantal/ls-mcp/actions/workflows/ci.yml/badge.svg?branch=main" alt="build"/></a>
  14. <a href="https://app.codecov.io/gh/lirantal/ls-mcp"><img src="https://badgen.net/codecov/c/github/lirantal/ls-mcp" alt="codecov"/></a>
  15. <a href="./SECURITY.md"><img src="https://img.shields.io/badge/Security-Responsible%20Disclosure-yellow.svg" alt="Responsible Disclosure Policy" /></a>
  16. </p>
  17. <div align="center">
  18. <img src="https://raw.githubusercontent.com/lirantal/ls-mcp/refs/heads/main/.github/ls-mcp-logo.png" alt="ls-mcp logo"/>
  19. </div>
  20. ## Features
  21. - **🔍 MCP Discovery**: Automatically detect MCP servers across various AI applications and agentic IDEs
  22. - **📁 Directory Bubbling**: Intelligent discovery of project-scoped MCP configs from nested directories, supporting project-scoped MCP Server configuration and global configurations
  23. - **🔄 Process Detection**: Real-time status of running MCP servers
  24. - **🔒 Credential Analysis**: Security analysis of environment variables and API keys for potentially exposed credentials in MCP Servers
  25. ## Usage: CLI
  26. ```bash
  27. npx ls-mcp
  28. ```
  29. ### Analyze Specific Files
  30. To analyze specific MCP configuration files instead of using automatic discovery, use the `--files` flag. This flag **replaces** automatic discovery and only analyzes the files you specify:
  31. ```bash
  32. # Single file
  33. npx ls-mcp --files ./mcp-config.json
  34. # Multiple files (comma-separated)
  35. npx ls-mcp --files ./config1.json,./config2.json
  36. # Multiple files (space-separated)
  37. npx ls-mcp --files ./config1.json ./config2.json
  38. ```
  39. The `--files` flag automatically detects the configuration structure in your files, supporting various formats including:
  40. - `servers` - Standard MCP configuration key
  41. - `mcpServers` - Alternative MCP configuration key
  42. - `mcp.servers` - Nested configuration format
  43. - `context_servers` - Context-based configuration format
  44. ### Show All Providers
  45. By default, `ls-mcp` hides providers that have zero configured servers to reduce clutter. To show all providers including those with empty configurations, use the `--all` or `-a` flag:
  46. ```bash
  47. # Show all providers including empty ones
  48. npx ls-mcp --all
  49. # Short form
  50. npx ls-mcp -a
  51. # Combine with JSON output
  52. npx ls-mcp --all --json
  53. ```
  54. **Note**: When using `--files` to analyze specific configuration files, the custom group is always shown even if it contains zero servers, as you explicitly requested to analyze those files.
  55. ### JSON Output
  56. To output results in JSON format (useful for programmatic consumption):
  57. ```bash
  58. npx ls-mcp --json
  59. # Combine with --files flag
  60. npx ls-mcp --files ./config.json --json
  61. ```
  62. This will return a structured JSON object containing:
  63. - `mcpFiles`: Complete MCP server configurations organized by provider (only includes providers with configured servers unless `--all` is specified)
  64. - `summary`: Statistics including total servers, running servers, credential warnings, and transport breakdown
  65. ### Debug Mode
  66. To enable verbose debugging output, set the `NODE_DEBUG` environment variable:
  67. ```bash
  68. # Enable debug logging for ls-mcp
  69. NODE_DEBUG=ls-mcp npx ls-mcp
  70. # Enable all debug logging
  71. NODE_DEBUG=* npx ls-mcp
  72. ```
  73. ## Documentation
  74. For detailed information about the project architecture and features:
  75. - **[Project Overview](./docs/project.md)**: Comprehensive project analysis and architecture
  76. - **[Design Documentation](./docs/design.md)**: Technical design decisions and implementation details
  77. - **[Requirements](./docs/requirements.md)**: Functional and non-functional requirements
  78. - **[Custom File Analysis](./docs/custom-files-analysis.md)**: Analyze specific MCP configuration files with the `--files` flag
  79. - **[Directory Bubbling](./docs/directory-bubbling.md)**: Intelligent directory traversal feature
  80. - **[URL Hostname Extraction](./docs/url-hostname-extraction.md)**: Clean display of hostnames for URL-based servers
  81. - **[Credential Detection](./docs/credential-detection.md)**: Security analysis features
  82. ## Documentation
  83. - [Project documentation](./docs/README.md) - development, testing, architecture, and conventions.
  84. ## Contributing
  85. Please consult [CONTRIBUTING](./CONTRIBUTING.md) for guidelines on contributing to this project.
  86. ## Author
  87. **ls-mcp** © [Liran Tal](https://github.com/lirantal), Released under the [Apache-2.0](./LICENSE) License.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.