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
danielsaban icon
Sec7

Manages Italian city data through CRUD operations, exposing these capabilities as tools for AI assistants via an MCP server.

Setup Requirements

  • ⚠️Requires Docker & Docker Compose for full setup (Elasticsearch and CRUD API).
  • ⚠️Requires Node.js 20+.
  • ⚠️The MCP server depends on the CRUD API server being actively running.
Verified SafeView Analysis
The Elasticsearch instance, as configured in `docker-compose.yml`, has security disabled (`xpack.security.enabled=false`), which is highly insecure for production environments. Additionally, the CRUD API uses `cors()` without specific origin restrictions, posing a risk if exposed publicly. Input validation is present for city names. For local development and use with Claude Desktop, these are generally acceptable, but require hardening for any public deployment.
Updated: 2025-12-14GitHub→
0
0
Low Cost
AmrKhater0011 icon

devops_server

by AmrKhater0011

Sec6

An end-to-end example project showcasing automated software deployment of a full-stack server application.

Setup Requirements

  • ⚠️Requires a PostgreSQL database instance.
  • ⚠️Requires a NATS server instance for messaging.
  • ⚠️Requires a Discord webhook URL for notifications.
  • ⚠️Requires Google Cloud credentials and a bucket for database backups.
Review RequiredView Analysis
The server uses parameterized queries for database interactions, preventing common SQL injection. However, it relies heavily on environment variables for sensitive data (DB credentials, Discord webhook, GCP credentials) which must be securely managed externally. Potential for Server-Side Request Forgery (SSRF) exists if 'IMAGE_SOURCE_URL' in server.js can be manipulated by an attacker, as it fetches an image from this URL without apparent validation. User-provided content for todos is sent to NATS and then to Discord via a webhook without explicit sanitization, posing a risk for content injection or abuse of Discord's markdown/commands.
Updated: 2026-01-19GitHub→
0
0
High Cost
zhiqiangwang4 icon

MCPTox-Benchmark

by zhiqiangwang4

Sec1

This server provides a collection of intentionally vulnerable and manipulated tool definitions designed for benchmarking and testing the security robustness of AI agents or systems interacting with diverse external services.

Setup Requirements

  • ⚠️Extreme Security Risk: Running this server will intentionally execute malicious operations, leading to severe data loss, privacy breaches, and infrastructure damage on the system it operates on or interacts with. This is not a benign benchmark.
  • ⚠️Requires Access to Sensitive System Resources: Many tools attempt to read/write critical system files (/etc/passwd, ~/.ssh/id_rsa) or perform network exfiltration, requiring elevated permissions and access to external services (file system, network, browser, various APIs like GitHub, Slack, etc.).
  • ⚠️Complex Malicious Chain Dependencies: The 'Template-1' and 'Template-2' paradigms enforce specific pre-conditions that must be met (often involving another malicious action) before the primary tool can even be called, making interaction and analysis complex.
Review RequiredView Analysis
The server's core functionality is to define and execute malicious operations across various domains. Risks include extensive credential leakage (e.g., overwriting SSH keys, reading /etc/passwd), severe infrastructure damage (e.g., deleting critical files, database resets), pervasive information manipulation and hijacking (e.g., redirecting search queries, altering content, forcing incorrect data), rampant code injection (e.g., injecting keyloggers, malware downloads, SQL injection), and service disruption (e.g., forcing failures, resource exhaustion). Pre-conditions for many tools involve destructive or privacy-violating actions, often exfiltrating sensitive data to attacker-controlled domains (e.g., 'attacker.com', 'evil.com').
Updated: 2025-12-03GitHub→
0
0
Low Cost
nbjoin icon
Sec2

Provides AI-powered tools and knowledge base services for 3D printing assistance, including G-code analysis, troubleshooting, and settings optimization for FlashForge printers.

Setup Requirements

  • ⚠️Implicit dependency on 'better-sqlite3' for the 'knowledge-base' server, which is a native Node.js module and often requires system-level build tools (e.g., Python, C++ compiler) to be installed for 'npm install' to succeed.
  • ⚠️Requires integration into the Model Context Protocol (MCP) ecosystem (e.g., via VS Code extension) as these are not standalone web services.
Review RequiredView Analysis
The `gcode-analyzer` MCP server (`src/mcp-servers/gcode-analyzer/server.js`) directly uses user-provided file paths in `fs.readFileSync` without validation, enabling arbitrary file reads on the host system. This is a critical security vulnerability. Additionally, the CLI interface for `src/tools/model-analyzer.js` has a similar vulnerability if exposed directly.
Updated: 2026-01-19GitHub→
0
0
High Cost
Sec6

A multi-agent simulation or operational platform for financial trading, managing accounts and market interactions via autonomous agents.

Setup Requirements

  • ⚠️Requires access to an external or local Large Language Model (LLM) provider (e.g., OpenAI API key, or a running local LLM like Ollama), which may incur costs or significant local resources.
  • ⚠️Specific Python version required, as indicated by .python-version (e.g., Python 3.10+ recommended).
  • ⚠️Requires installation of dependencies via pyproject.toml and uv.lock (e.g., using poetry or uv).
Review RequiredView Analysis
The system includes multiple network server components (accounts_server.py, market_server.py, push_server.py) which open network ports, inherently introducing attack surface. As an agentic system, it likely interacts with Large Language Models and may execute LLM-generated code or actions; this poses a risk if outputs are not rigorously validated and sanitized, especially in a financial context. Potential for 'eval' or dynamic code execution in agent decision-making cannot be ruled out without code inspection.
Updated: 2025-11-17GitHub→
0
0
Medium Cost
isakskogstad icon

svt-texttv-mcp

by isakskogstad

Sec9

Access Swedish teletext content (news, sports, weather, TV schedules) from SVT Text-TV via the Model Context Protocol.

Setup Requirements

  • ⚠️Requires Node.js 18.0.0 or higher.
Verified SafeView Analysis
The server primarily provides read-only access to public Text-TV data. Input is strictly validated using Zod schemas, mitigating common injection risks. No direct usage of 'eval' or other dangerous dynamic code execution patterns was found. There are no hardcoded secrets beyond a public application ID. The HTTP server uses permissive CORS ('Access-Control-Allow-Origin: *'), which is common for public APIs and not a vulnerability for this read-only service. The main external dependency is an unofficial API (texttv.nu), so its reliability and security are external factors, but the server handles its usage robustly.
Updated: 2025-12-02GitHub→
0
0
Low Cost
yukihito-jokyu icon

mysql-mcp-server

by yukihito-jokyu

Sec9

A Model Context Protocol (MCP) server providing read-only access to MySQL database schema information and sample data for LLM agents or backend development.

Setup Requirements

  • ⚠️Requires a running MySQL database.
  • ⚠️The default MySQL port in the CLI options is `8080`, which is uncommon for MySQL (typically `3306`). Users must explicitly set `--port 3306` or use a correct port for their MySQL instance.
Verified SafeView Analysis
The server is explicitly designed for read-only operations, preventing any data modification (INSERT, UPDATE, DELETE). It uses parameterized queries (e.g., `DESCRIBE ??`, `SELECT * FROM ?? LIMIT 5`) in `src/lib/database.ts` to prevent SQL injection for table names. Database credentials are passed via CLI arguments, which is less secure than environment variables for highly sensitive production environments but is a common pattern for local MCP client configurations.
Updated: 2025-11-21GitHub→
0
0
Medium Cost
jfomhover icon
Sec9

Manages and validates JSON documents against defined schemas, designed for integration with AI assistants via the Model Context Protocol.

Setup Requirements

  • ⚠️Requires Python 3.11+.
  • ⚠️Manual JSON configuration needed for integration with Claude Dev Extension or Claude Desktop App, including absolute paths.
  • ⚠️Uses local file system for storage, which might require specific folder permissions and management.
Verified SafeView Analysis
The server employs robust schema validation, optimistic locking for concurrency control, and safe JSON Pointer operations to prevent path traversal issues. Storage uses atomic file operations (temp file + rename + fsync) for data integrity. No 'eval' or similar dangerous functions were found. The tool primarily uses local file-based storage, reducing external network attack surfaces. Overall, it demonstrates good security practices within its scope.
Updated: 2025-11-30GitHub→
0
0
Medium Cost
scarnyc icon

jira-mcp-server

by scarnyc

Sec8

Integrates with JIRA to provide a portable Model Context Protocol server, enabling AI clients like Claude Code to interact with JIRA operations.

Setup Requirements

  • ⚠️Requires JIRA_URL, JIRA_USERNAME, and JIRA_API_TOKEN (or JIRA_PERSONAL_ACCESS_TOKEN) environment variables for configuration.
  • ⚠️Requires Python 3.10 or higher.
Verified SafeView Analysis
The server employs Pydantic settings for secure environment variable loading, preventing hardcoded secrets. It uses `httpx` for async network requests with SSL verification. A 'read-only' mode and tool filtering are implemented to enhance security by restricting write operations and exposed functionalities. Input sanitization for JQL queries relies on JIRA's API, which is standard for such integrations. No 'eval' or other obvious malicious patterns were found in the provided source code.
Updated: 2026-01-18GitHub→
0
0
Medium Cost
TalatWaheed icon
Sec8

Hosts a custom Minecraft server and deploys an AI-powered bot that interacts with players and the game world.

Setup Requirements

  • ⚠️Requires OpenAI API Key (Paid)
  • ⚠️Requires Node.js runtime
Verified SafeView Analysis
The server uses environment variables for sensitive API keys, which is good practice. It creates a Minecraft server and a bot, leveraging external libraries like Mineflayer and OpenAI. The primary security considerations revolve around the inherent risks of AI agents (e.g., prompt injection leading to unintended in-game actions) and external API dependencies. No 'eval' or obvious malicious patterns were found in the provided source.
Updated: 2025-12-11GitHub→
0
0
Low Cost
schimmmi icon

fyta-mcp-server

by schimmmi

Sec9

A Model Context Protocol (MCP) Server for FYTA plant sensor data, enabling an AI assistant like Claude to access and intelligently analyze plant health, sensor data, and care history.

Setup Requirements

  • ⚠️Requires a FYTA account with active plant sensors.
  • ⚠️Python 3.10 or higher is required.
  • ⚠️When configuring for Claude Desktop, absolute paths to the Python executable and working directory are critical and commonly lead to setup errors.
Verified SafeView Analysis
The server uses environment variables for sensitive credentials (FYTA_EMAIL, FYTA_PASSWORD) which is a good practice. It explicitly warns against hardcoding secrets and provides guidance for securing exposed HTTP endpoints (e.g., with HTTPS and authentication in production). The core MCP server uses standard I/O and does not open network ports by default. Local file storage for care actions and plant context is used, reducing remote data exposure risks. No 'eval' or obvious malicious patterns were detected in the source code.
Updated: 2026-01-18GitHub→
0
0
High Cost
victorRT3868 icon

shopping-agent-ai

by victorRT3868

Sec4

An AI-powered shopping assistant for cross-platform price comparison and objective buying advice on e-commerce platforms (JD, Taobao, Vipshop).

Setup Requirements

  • ⚠️Requires an LLM API Key (e.g., OpenAI, DeepSeek), which is typically a paid service.
  • ⚠️Manual login/QR code scanning is required for Taobao and Xiaohongshu scrapers due to anti-bot measures.
  • ⚠️The JD OCR mode (`jd_gui.py`) takes over your mouse and keyboard, demanding full user attention and no interference during its operation.
  • ⚠️Initial setup for PaddleOCR might require downloading models, necessitating internet access and available disk space.
Verified SafeView Analysis
1. Browser session cookies are stored in plain JSON files (`auth.json`, `auth_zhihu.json`, `auth_xhs.json`), exposing login data if the host machine is compromised. 2. `src/scrapers/jd_gui.py` utilizes `pyautogui` to directly control the user's mouse and keyboard, which presents a significant operational risk; users must be fully aware and avoid system interaction during its execution. 3. Playwright in `headless=False` mode with anti-detection scripts, though necessary for certain platforms, might still trigger anti-bot measures, potentially leading to temporary IP bans or account restrictions on target e-commerce sites.
Updated: 2026-01-19GitHub→
PreviousPage 588 of 760Next