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(9120)

0
0
Medium Cost
zzw4257 icon
Sec7

A backend server providing API endpoints for user management and authentication, likely serving as a component for a larger "seed emulator" project or similar client application.

Setup Requirements

  • ⚠️Requires a database (e.g., MongoDB, PostgreSQL) for data persistence.
  • ⚠️Requires Node.js installed or Docker for deployment.
  • ⚠️Requires environment variables for configuration (e.g., database connection string, JWT secret).
Verified SafeView Analysis
Standard web application security concerns apply (e.g., input validation, secure session management, dependency vulnerabilities). The presence of authentication middleware and reliance on environment variables for sensitive configurations (`.env.example` implies this) are good practices. Without inspecting the actual implementation details of security mechanisms, a perfect score cannot be guaranteed.
Updated: 2026-01-17GitHub→
0
0
Medium Cost
M4F-S icon

WP-WC-MCP

by M4F-S

Sec9

Enables LLMs like Claude to interact with and manage WordPress and WooCommerce sites via natural language.

Setup Requirements

  • ⚠️Requires Node.js 20+ to run.
  • ⚠️Requires an existing WordPress 5.6+ site with HTTPS enabled and WooCommerce 8.0+ for e-commerce features.
  • ⚠️Requires manual configuration of a WordPress Application Password for the server to authenticate securely.
Verified SafeView Analysis
This project implements a 'security-first' architecture with robust measures. It features extensive input validation using Zod schemas and custom `InputValidator` for SSRF protection (blocking internal IPs and dangerous protocols), SQL injection, XSS, and path traversal prevention. Authentication uses WordPress Application Passwords with a circuit breaker pattern and re-authentication logic. Authorization is enforced via WordPress capability checks mapped to specific tools. Sensitive data is automatically redacted from logs using Winston. Rate limiting (token bucket algorithm), batch operation limits, and secure Docker configurations (non-root user, resource limits, dropped capabilities) are also in place. Error messages are sanitized to prevent information disclosure. While highly secure, no system is 100% impervious to all possible attack vectors, hence a 9.
Updated: 2026-01-19GitHub→
0
0
Low Cost
FrontMage icon

screenshot_mcp

by FrontMage

Sec7

This server provides screenshot and screen recording capabilities for macOS, acting as a tool for a Model Context Protocol (MCP) agent.

Setup Requirements

  • ⚠️Requires macOS 12+ (CoreGraphics APIs)
  • ⚠️Requires Swift (Xcode CLI tools) for compilation
  • ⚠️Requires Node.js 18+
  • ⚠️Screen Recording permission must be granted to the terminal or host app for functionality
Verified SafeView Analysis
The server uses `execFile` and `spawn` to run a Swift CLI for its core functionality. While numeric arguments are sanitized, the `output_path` argument can be fully controlled by the caller. This means a user could specify an absolute path (e.g., `/Users/user/some_file.png` or `/etc/passwd`) as the output destination. If the server process has write permissions to that location, it could overwrite arbitrary files, leading to data loss or denial of service. The server does not expose a network interface directly, communicating over stdin/stdout via MCP, which reduces external attack surface. It relies on macOS's built-in Screen Recording permissions.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
Ajsalemo icon

mcp

by Ajsalemo

Sec6

Provides weather information (forecasts, alerts, radar station data) by integrating with the National Weather Service (NWS) API as a Model Context Protocol (MCP) server.

Setup Requirements

  • ⚠️This repository contains multiple implementations (Java, Node.js, Python), requiring the appropriate runtime environment for the chosen server.
  • ⚠️The NWS API (used by all implementations) primarily provides data for US locations.
  • ⚠️The `t.sh` file contains sensitive hardcoded credentials which should be removed or handled securely if this repository is intended for public use or deployment.
Verified SafeView Analysis
The core weather server implementations (Java, Node.js, Python) themselves do not appear to contain hardcoded secrets for their operation against the NWS API. However, the repository includes a file `t.sh` which contains hardcoded `client_id`, `client_Secret`, `email`, and `password` for `home-api.eufylife.com`. This is a severe security vulnerability for the owner of those credentials and the repository if these are live secrets, as they are exposed publicly. No other malicious patterns, `eval` usage, or obfuscation were found.
Updated: 2025-11-22GitHub→
0
0
Low Cost
authn8 icon

mcp-server

by authn8

Sec9

Provides AI agents with programmatic access to Authn8 2FA (TOTP) codes via a secure Personal Access Token.

Setup Requirements

  • ⚠️Requires an Authn8 account.
  • ⚠️Requires an Authn8 Personal Access Token (PAT).
  • ⚠️Requires Node.js and npm for `npx` or Docker if running via container.
Verified SafeView Analysis
The server securely handles the Authn8 Personal Access Token (PAT) via an environment variable. Input validation is performed using Zod to prevent common injection vulnerabilities. All API communication uses HTTPS. No 'eval' or other dynamic code execution is found. Robust error handling for API failures is implemented. Security relies on the PAT being kept secret and managed appropriately by the user.
Updated: 2025-12-08GitHub→
0
0
High Cost
omdv icon
Sec9

Provides a rigorous 3-Stage Crude Oil Stabilization Facility simulation as an API for AI agents to optimize production parameters.

Setup Requirements

  • ⚠️Requires Java Runtime Environment (for NeqSim).
  • ⚠️NeqSim simulations can be CPU-intensive, requiring adequate resource allocation in Kubernetes deployments (resource limits are commented out by default).
  • ⚠️Requires container image to be built and pushed to a registry for Kubernetes deployment.
Verified SafeView Analysis
The Python codebase (`server.py`) is clean, using Pydantic for input validation and not exhibiting common vulnerabilities like `eval` or direct system calls. The Kubernetes deployment practices are robust, explicitly enforcing non-root user execution, read-only root filesystem, dropped capabilities, and no privilege escalation. Resource limits are recommended for production but are commented out by default, which is a minor risk. The underlying NeqSim library is Java-based, introducing external dependency considerations, but the Python wrapper itself appears secure.
Updated: 2025-12-01GitHub→
0
0
Low Cost
dvalley56 icon

envshield-mcp

by dvalley56

Sec8

Securely expose environment variables to AI coding assistants by acting as a Model Context Protocol (MCP) server, preventing direct access to sensitive data while enabling execution of commands with injected secrets.

Setup Requirements

  • ⚠️Requires Node.js 18+.
  • ⚠️Modifies '.claude/settings.json' (local or global) to register itself as an MCP server and deny direct .env file access, which is crucial for its security model.
  • ⚠️Relies on a '.envshield.json' configuration file (project-local or global) for custom behaviors like additional redaction patterns or command blocking, otherwise defaults are used.
Verified SafeView Analysis
The server employs robust scrubbing of secrets from command output, includes pre-defined and custom regex patterns for detection, and validates custom regexes against ReDoS attacks. Dangerous commands like 'rm -rf' and 'sudo' are blocked by default, using word-boundary-aware matching. A rate limiter helps prevent command flooding, protecting against abuse. The core functionality involves `child_process.spawn` with `shell: true`, which is an inherent risk vector when executing arbitrary commands, but this is mitigated by the command blocking list and the design's focus on containing AI access. A security warning is logged if scrubbing is detected to be ineffective. Overall, it implements a strong set of controls for its stated purpose.
Updated: 2026-01-17GitHub→
0
0
Low Cost
manyalawy icon

MCP-server

by manyalawy

Sec9

This server provides a Micro-Capability Platform (MCP) exposing simple programmatic tools via an HTTP interface, along with a custom health check endpoint.

Setup Requirements

  • ⚠️Requires Python 3.12 or newer
Verified SafeView Analysis
The code is simple, directly implements basic tools and a health check, and does not contain 'eval', obfuscation, hardcoded secrets, or complex logic that could introduce common vulnerabilities. It leverages the 'fastmcp' framework for API exposure.
Updated: 2025-12-05GitHub→
0
0
High Cost
mbarki-abd icon

mcp-agent-server

by mbarki-abd

Sec4

The MCP Agent Server orchestrates a multi-agent AI platform, enabling the creation, management, communication, and real-time monitoring of AI agents, their workspaces, projects, tasks, and secure credentials.

Setup Requirements

  • ⚠️Requires root/sudo privileges for full functionality (agent provisioning, terminal execution).
  • ⚠️Requires a PostgreSQL database instance to be set up and accessible.
  • ⚠️Requires AI CLI tools (e.g., 'claude', 'ollama', 'gemini') to be installed on the host system or within agent environments.
  • ⚠️Critical environment variables (MCP_API_KEY, ENCRYPTION_KEY, DB_NAME, DB_USER, DB_PASSWORD) MUST be configured securely, especially in production.
Review RequiredView Analysis
CRITICAL VULNERABILITIES IDENTIFIED: 1. **Information Leak on Public Endpoints**: The `/ws/dashboard`, `/api/dashboard/state`, `/api/presence/ws`, and `/api/presence/sse` endpoints are explicitly marked as public routes in `auth.ts`. These endpoints expose sensitive system information including server details, a list of all agents, their statuses, active tasks, system metrics, projects, and session metadata, all without any authentication. This allows unauthenticated users to gain comprehensive visibility into the operational state of the entire multi-agent platform. 2. **Secret Master API Key Exposure**: The `/key` endpoint (path configured by `SECRET_KEY_PATH`) returns the master API key. While the code includes a warning to 'keep this path secret', relying on obscurity for access to a critical secret is a significant security risk. If this path is discovered (e.g., through scanning, misconfiguration, or leaks), the master API key is exposed. 3. **Root Privileges Required**: Core functionalities such as agent provisioning (creating Unix users and their home directories), setting file ownership (`chown`), and running commands as other users (`su`) require the server to operate with root privileges or highly permissive sudoer configurations. This introduces a substantial attack surface, as a compromise of the server could lead to full system compromise. RECOMMENDATIONS: Implement robust authentication/authorization for all dashboard and presence endpoints. Remove or severely restrict the `/key` endpoint, ideally replacing it with a secure token issuance/rotation mechanism for master access.
Updated: 2025-12-13GitHub→
0
0
Medium Cost
dacionxo icon

mcp-server

by dacionxo

Sec9

This server provides a Model Context Provider (MCP) interface to the Repliers API, enabling natural language access to real estate listings, property data, market analytics, and AI-powered tools.

Setup Requirements

  • ⚠️Requires Repliers API Key (Paid API)
  • ⚠️Requires Node.js v22+ (as specified in package.json and recommended by README)
Verified SafeView Analysis
The server demonstrates strong security practices including explicit environment variable loading from a .env file, mandatory checks for critical API keys (REPLIERS_API_KEY), and robust error handling. All external API calls use the fetch API with properly constructed URLs and headers, minimizing injection risks. There are no evident uses of 'eval' or other dynamic code execution from untrusted input, nor any hardcoded secrets in the provided source.
Updated: 2025-12-14GitHub→
0
0
High Cost
physics91 icon

ai-code-review-mcp

by physics91

Sec9

This project provides a Model Context Protocol (MCP) server for AI-powered code analysis, leveraging both Codex and Gemini CLIs to perform and aggregate code reviews.

Setup Requirements

  • ⚠️Requires Node.js 20.0.0 or higher.
  • ⚠️Requires separate installation and configuration of Codex CLI and Gemini CLI, which may involve obtaining API keys for these services.
  • ⚠️Needs an MCP client (e.g., Claude Desktop) to interact with the server after setup.
Verified SafeView Analysis
The project demonstrates a very strong security posture. It employs extensive input validation using Zod schemas, critical CLI path whitelisting for both Codex and Gemini services, utilizes 'execa' with 'shell: false' to prevent shell injection, and implements comprehensive sensitive data redaction (code, API keys, secrets) from logs and error messages. Codex CLI execution is further hardened with '--sandbox read-only' and dangerous argument filtering. Control characters are stripped from inputs for display safety. A test for prototype pollution is present, indicating awareness. Overall, a highly security-conscious design.
Updated: 2025-12-26GitHub→
0
0
Low Cost
SachdevaVansh icon

MCP_Server_n8n_

by SachdevaVansh

Sec3

Provides a Python-based Model Context Protocol (MCP) server to bridge an AI client (e.g., Claude Desktop) with a PostgreSQL database hosted on NeonDB and integrate with n8n for workflow automation.

Setup Requirements

  • ⚠️Requires Python 3.13 or higher.
  • ⚠️A NeonDB (PostgreSQL) database instance and its credentials are required.
  • ⚠️The hardcoded `psqlurl` in `postgresql.py` must be manually replaced with your NeonDB connection string, preferably using environment variables for security (though not implemented by default in code).
Review RequiredView Analysis
CRITICAL: The `postgresql.py` file contains a hardcoded PostgreSQL connection string (`psqlurl`) including database credentials (owner username and password). This is a severe security vulnerability. While the README suggests using environment variables, the code does not implement this. Additionally, the project encourages public exposure via ngrok, which, while noted as optional, combined with hardcoded credentials and the direct database query capabilities, poses a significant risk if not handled with extreme care. The `mcp.tool()` functions use parameterized queries, mitigating direct SQL injection for the defined tools, but the general `query_db` function could be misused if new tools are added without proper parameterization.
Updated: 2025-12-04GitHub→
PreviousPage 475 of 760Next