Stop Searching. Start Trusting.

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

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(9120)

0
0
Low Cost
abboahene icon

mcp-gateway

by abboahene

Sec3

Aggregates multiple Model Context Protocol (MCP) servers into a single endpoint for clients like Claude Desktop or VS Code.

Setup Requirements

  • ⚠️Requires Node.js 18+ to run the CLI and server.
  • ⚠️Relies on a user-editable configuration file (`~/.mcp-gateway/config.json`) where malicious entries could lead to Remote Code Execution (RCE) if the file is compromised.
  • ⚠️Requires manual configuration in client applications (e.g., Claude Desktop, VS Code) to point to the gateway, and each proxied MCP server will have its own setup requirements, dependencies, and potential API key costs.
Review RequiredView Analysis
The core functionality of the MCP Gateway involves executing user-defined commands and arguments for each configured MCP server using `child_process.spawn`. These commands are sourced directly from the `~/.mcp-gateway/config.json` file, which is user-editable. If this configuration file is compromised or a malicious entry is injected (e.g., through a malicious marketplace server listed in the desktop app, or by direct file modification), it could lead to arbitrary code execution (RCE) on the host system. Environment variables specified in the config are also passed directly to these spawned child processes, posing a risk of credential exfiltration if a malicious command is executed. While the user explicitly configures these commands, the gateway itself does not provide sandboxing for them, making configuration integrity critical. The README correctly advises securing the config file permissions (e.g., `chmod 600`).
Updated: 2025-11-23GitHub→
0
0
Medium Cost
kiki830621 icon

che-ical-mcp

by kiki830621

Sec9

Manage macOS Calendar events and Reminders tasks for AI agents through 20 specialized tools, including batch operations, search, and conflict detection.

Setup Requirements

  • ⚠️Requires macOS 13.0+.
  • ⚠️Requires explicit macOS permissions for Calendar and Reminders access, which will be prompted on first use.
  • ⚠️Installation to cloud-synced folders (Dropbox, iCloud, OneDrive) is discouraged due to potential MCP connection timeouts from file sync operations.
Verified SafeView Analysis
The server operates locally using Apple's native EventKit framework. The `PRIVACY.md` explicitly states that 'No data is stored outside of macOS EventKit', 'No data is transmitted to external servers or cloud services', and 'No network connections are made by this server'. Communication happens locally via `StdioTransport`. The code itself does not contain `eval` or similar dangerous patterns, nor does it appear to have hardcoded secrets. It requires explicit macOS permissions for Calendar and Reminders access, which is necessary for its functionality. The primary security risk is granting access to potentially sensitive local calendar/reminder data to an AI agent if the user is not aware of the permissions or the AI's capabilities.
Updated: 2026-01-19GitHub→
0
0
Low Cost

Tracks Amazon Q sessions, preserves context, monitors progress toward goals, and provides crash recovery capabilities for development workflows.

Setup Requirements

  • ⚠️Requires `npm install` for dependencies.
  • ⚠️Requires `git` to be installed on the system for the `log_git_commits` tool.
  • ⚠️Requires configuration in `.amazon-q-history/config.json` in the project root to define storage mode, allowed paths, and tool permissions.
  • ⚠️Needs to be registered as an Amazon Q CLI MCP server, with the `cwd` parameter in `mcp-server.json` correctly pointing to the server's installation directory.
Verified SafeView Analysis
The server employs robust input validation, path traversal protection, sensitive file blocking, and input length limits. All file operations are serialized via an async queue, preventing race conditions. Tool permissions allow fine-grained access control. The use of `child_process.execSync` for Git operations is carefully constructed with controlled arguments and input validation to prevent command injection. No clear hardcoded secrets or direct network vulnerabilities (operates via stdio) were identified.
Updated: 2025-12-10GitHub→
0
0
Low Cost

dev-mcp

by cisaacstern

Sec1

A server component, likely for a game development environment, given the 'MCP' (Minecraft Coder Pack) and 'dev' context.

Review RequiredView Analysis
No code or README content was provided for analysis (README: 404 Not Found), making a security audit impossible. The lowest score is assigned due to unknown risks.
Updated: 2025-11-18GitHub→
0
0
Low Cost
Cipheeer icon

MCP_server

by Cipheeer

Sec9

This server provides a set of string manipulation tools as microservices using the FastMCP framework.

Setup Requirements

  • ⚠️Requires 'fastmcp' Python package to be installed
  • ⚠️Python 3+ is required
Verified SafeView Analysis
The provided source code for string manipulation tools is simple and does not contain 'eval', 'exec', direct shell commands, or obvious hardcoded secrets. Its overall security largely depends on the underlying 'fastmcp' library and how it handles SSE transport and incoming requests. No apparent malicious patterns within the provided snippet.
Updated: 2025-12-02GitHub→
0
0
Low Cost
itsniazahmad icon

demo-mcp-server-yt

by itsniazahmad

Sec7

A basic, in-memory demo server designed to mimic a Minecraft server using the 'minecraft-protocol' Node.js library for development, testing, or educational purposes.

Setup Requirements

  • ⚠️Requires Node.js runtime environment
  • ⚠️Requires 'minecraft-protocol' npm package to be installed
  • ⚠️Requires a Minecraft Java Edition client (version 1.16.4) to connect and test
Verified SafeView Analysis
The server is set to 'online-mode: false' and listens on '0.0.0.0' (all network interfaces), meaning it does not perform Mojang authentication and could allow anyone to connect with any username if exposed publicly. For a 'demo' server, this setup is common for ease of local development and testing, but it is critical to understand these implications and to avoid exposing it to untrusted networks without additional security measures.
Updated: 2025-11-29GitHub→
0
0
Medium Cost
PugazhTheHacker icon

kali-mcp

by PugazhTheHacker

Sec1

Provides a web-based remote terminal for Kali Linux, integrated with a Gemini AI assistant and full filesystem access for cybersecurity tasks.

Setup Requirements

  • ⚠️Requires Google Gemini API key for AI features.
  • ⚠️Designed for and requires a Kali Linux environment for the backend tools (Nmap, Hydra, Metasploit, etc.).
  • ⚠️Requires running two separate Python servers (`server.py` and `kali-server.py`) simultaneously.
Review RequiredView Analysis
CRITICAL: The `kali-server.py` component uses `subprocess.Popen(self.command, shell=True)` to execute user-provided commands directly. The `command` variable originates from `request.json` and is passed without any sanitization. This allows for arbitrary command injection and full remote code execution by any user who can access the Kali server API endpoint. While the README warns about using it only on trusted networks, the fundamental vulnerability remains in the code. No strong authentication or authorization mechanisms are present for the API endpoints.
Updated: 2025-12-01GitHub→
0
0
High Cost
stevenpto icon

MCP

by stevenpto

Sec8

Extracts text from PDF documents, including support for OCR on scanned pages, and summarizes the extracted content using context-aware guidance.

Setup Requirements

  • ⚠️Requires Tesseract OCR installation for image-based PDFs to enable full OCR functionality (optional for text-based PDFs).
  • ⚠️May perform NLTK data downloads (punkt, stopwords) on first run if not already present, which requires internet access.
Verified SafeView Analysis
The server processes local PDF files. Potential risks primarily arise from vulnerabilities within the PyMuPDF or Tesseract libraries when handling malformed or malicious PDF inputs, or if the `file_path` parameter is not properly controlled by the calling agent, potentially exposing unintended local files. The server code itself does not contain 'eval', obfuscation, or hardcoded secrets. NLTK data downloads are handled quietly.
Updated: 2025-12-02GitHub→
0
0
Medium Cost
kiki830621 icon

che-duckdb-mcp

by kiki830621

Sec8

Provides an integrated Model Context Protocol (MCP) server for DuckDB documentation search and local database operations.

Setup Requirements

  • ⚠️Requires macOS 13.0+ for operation.
  • ⚠️Requires Swift 5.9+ toolchain for building from source.
  • ⚠️An internet connection is needed for the initial download and refresh of DuckDB documentation.
Verified SafeView Analysis
The `db_query` tool implements a prefix-based validation to restrict query types (SELECT, WITH, SHOW, DESCRIBE, EXPLAIN, PRAGMA) and applies a default row limit (1000). While this prevents direct DDL/DML, it is not a full SQL parser and could potentially allow complex SELECT queries to be resource-intensive or exploit advanced SQL features if not handled by the underlying DuckDB driver. The `db_execute` tool is explicitly for DDL/DML and correctly marked as destructive, requiring explicit intent. Database connections are restricted to local files only, and read-only mode is supported. Documentation is downloaded from a trusted, hardcoded DuckDB URL. No hardcoded secrets or obvious malicious patterns were found in the provided source code.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
vxvomar123 icon

gmail-mcp-server

by vxvomar123

Sec8

Automates Gmail operations like sending, reading, organizing, and filtering emails through an AI assistant like Claude Desktop via the Model Context Protocol.

Setup Requirements

  • ⚠️Requires manual creation and configuration of a Google Cloud Project with OAuth 2.0 Client ID and enabling the Gmail API.
  • ⚠️For personal use, the Google Cloud project's OAuth consent screen must have the user's email address explicitly added as a 'Test User' to avoid '403 Access Blocked' errors.
  • ⚠️Requires manual configuration in Claude Desktop's `claude_desktop_config.json` with the absolute file path to the server's `dist/index.js` executable.
  • ⚠️The local port 3000 must be available for the OAuth authentication callback, which can conflict with other running applications.
Verified SafeView Analysis
The server utilizes direct file system operations for attachment handling (reading local files for sending, writing downloaded attachments to specified paths). While tool inputs are validated via Zod schemas, a compromised AI could theoretically direct file operations to sensitive areas or write malicious content. OAuth tokens are stored in plaintext with restricted file permissions (~/.gmail-mcp/credentials.json, chmod 600). However, the project provides comprehensive security documentation (SECURITY.md) detailing these risks, recommending best practices for users and developers (e.g., input validation for file paths, never committing credentials), and outlining a clear vulnerability reporting process. The local web server for OAuth runs only on localhost during authentication and shuts down immediately.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
uddin-rajaul icon

mcp-sql-optimizer

by uddin-rajaul

Sec9

Analyzes, optimizes, and suggests indexes for SQL queries across multiple dialects.

Setup Requirements

  • ⚠️Requires Python 3.10 or higher.
  • ⚠️Docker is the recommended installation method for easier setup; otherwise, careful management of a Python virtual environment and PYTHONPATH is necessary.
Verified SafeView Analysis
The server primarily performs static analysis and transformation of SQL queries using the `sqlglot` library. It does not execute arbitrary SQL against a database, nor does it make external network requests from its core logic. User-provided `sql` and `explain_plan` inputs are parsed and processed internally without dangerous execution. No 'eval' or direct shell commands are used. The generated DDL for indexes is returned as a string, not executed.
Updated: 2025-12-05GitHub→
0
0
Medium Cost

The server provides an LLM with structured information about a codebase, including file listings, directory trees, and file contents, acting as a context provider for development agents.

Setup Requirements

  • ⚠️Requires `ALLOWED_DIR` (C:\Users\alark\OneDrive\Documentos\GitHub\Procedural-World-Simulation-Engine) to be explicitly configured or changed for deployment on different systems or locations, as it's hardcoded.
  • ⚠️Intended for use with a `FastMCP` client, specifically noted as compatible with 'Continue'.
Verified SafeView Analysis
The server implements robust path sanitization using `resolve_safe_path` to prevent path traversal vulnerabilities, ensuring all file operations are confined within the `ALLOWED_DIR`. File read operations are limited to 200KB, mitigating potential denial-of-service from reading excessively large files. The primary security concern is the hardcoded `ALLOWED_DIR` which, while restricting scope, could expose system information if the repository itself contains sensitive data.
Updated: 2026-01-18GitHub→
PreviousPage 522 of 760Next