Stop Searching. Start Trusting.

The curated directory of MCP servers, vetted for security, efficiency, and quality.

Browse DirectoryWhy Us?

Tired of the MCP "Marketplace" Chaos?

We built MCPScout.ai to solve the ecosystems biggest pain points.

No Insecure Dumps

We manually analyze every server for basic security flaws.

Easy Setup

Our gotcha notes warn you about complex setups.

Avoid "Token Hogs"

We estimate token costs for cost-effective agents.

Products, Not Demos

We filter out "Hello World" demos.

CATEGORIES:
SORT:

Vetted Servers(2)

0
0
Medium Cost
chef72max icon
Sec9

An AI-powered digital reading companion application that assists users with note-taking, highlighting, goal tracking, and provides AI-driven insights and summaries for various document types like PDFs and EPUBs.

Setup Requirements

  • ⚠️Requires Node.js 18+ to run the development server.
  • ⚠️AI features are currently placeholders ('TODO: Replace with actual AI API call') and require custom implementation and potential API key integration (e.g., OpenAI, Gemini) for full functionality, which would incur external costs.
Verified SafeView Analysis
The application primarily operates client-side, storing user data (books, notes, highlights) in IndexedDB and localStorage, which limits direct server-side vulnerabilities from the provided code. The AI features are currently placeholders, meaning actual AI API keys/integrations are not present and thus no hardcoded secrets or immediate network risks associated with AI calls exist in this version. File upload is simulated. Loading PDF worker from CDN (jsdelivr) is a common practice but relies on CDN integrity. Overall, the code appears to be clean and focuses on client-side functionality, making it relatively safe to run.
Updated: 2025-12-15GitHub→
0
0
Low Cost
mamaamacrivi icon

docker-mcp-tutorial

by mamaamacrivi

Sec9

Provides comprehensive dice rolling functionality for tabletop games, RPGs, and general randomization tasks for AI assistants via the Model Context Protocol.

Setup Requirements

  • ⚠️Requires Docker Desktop with the MCP Toolkit enabled (Beta Feature).
  • ⚠️Requires manual editing of Docker MCP CLI configuration files (~/.docker/mcp/catalogs/custom.yaml, ~/.docker/mcp/registry.yaml).
  • ⚠️Requires manual editing of the Claude Desktop client configuration file (claude_desktop_config.json) with platform-specific user paths.
Verified SafeView Analysis
The server is self-contained, using Python's `random` module for number generation without external API calls or persistent data storage. It employs input validation for all parameters (e.g., range checks on dice counts/sides). The Dockerfile adheres to security best practices by creating and switching to a non-root user (`mcpuser`). No `eval`, `exec`, or similar dangerous functions are used, and no hardcoded credentials are present. A broad `except` in `parse_dice_notation` could be more specific but does not pose a direct security vulnerability in this context.
Updated: 2025-12-15GitHub→