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(8554)

0
0
Low Cost
Harryc6 icon

ProxmoxMCP

by Harryc6

Sec9

The Proxmox MCP server provides read-only access to Proxmox cluster, guest, and storage information for agents to update documentation and monitoring systems.

Setup Requirements

  • ⚠️Requires Node.js runtime environment.
  • ⚠️Requires a Proxmox API token with read-only permissions.
  • ⚠️The environment variables PROXMOX_API_URL, PROXMOX_API_TOKEN_ID, and PROXMOX_API_TOKEN_SECRET must be set.
  • ⚠️If Proxmox uses a self-signed TLS certificate, PROXMOX_TLS_INSECURE=1 must be set, which bypasses TLS verification.
Verified SafeView Analysis
The server is designed to be read-only, connecting to Proxmox via a dedicated API token with limited (e.g., PVEAuditor) permissions, which is a strong security practice. Secrets are handled via environment variables, preventing hardcoding. The `PROXMOX_TLS_INSECURE` flag allows bypassing TLS verification for self-signed certificates, which is noted in the README as a potential security risk if misused but provides flexibility for lab environments. No 'eval' or direct arbitrary code execution patterns are observed.
Updated: 2025-12-10GitHub→
0
0
Low Cost
ghaidaa-24 icon

stocks-mcp

by ghaidaa-24

Sec9

Access comprehensive stock market data and analysis tools, optimized for LLMs, including technical analysis, screeners, pivot points, and support for Turkish stocks.

Setup Requirements

  • ⚠️Requires Node.js version 18.0.0 or higher.
  • ⚠️Relies on Yahoo Finance data, which may be subject to rate limits or API changes that could affect data availability or accuracy.
Verified SafeView Analysis
The server utilizes the `yahoo-finance2` library for data retrieval, which handles external API interactions. Input arguments for tools are validated by schema types and simple checks (e.g., `count` parameter is capped at 50). A `getTicker` helper provides basic sanitization for stock symbols, including auto-detection for BIST tickers. No direct use of `eval`, obfuscation, or hardcoded secrets were identified in the provided source code. The `@ts-ignore` for suppressing a Yahoo survey notice is not a security concern.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
kairapavan icon
Sec9

Provides National Provider Identifier (NPI) data as an external tool for integration with Spring AI applications.

Setup Requirements

  • ⚠️Requires Java Development Kit (JDK) to build and run.
  • ⚠️The 'national_provider_identifier.json' file must be present at 'src/main/resources/static/' for successful application startup.
  • ⚠️The application will fail to start due to a JSON parsing error if any 'BigInteger' field in the 'Npi' record (e.g., Npi, Entity_Type_Code, Postal_Code, Telephone_Number, Fax_Number) corresponds to an empty string ('""') in the 'national_provider_identifier.json' file.
Verified SafeView Analysis
The code primarily loads and exposes static NPI data. No dynamic code execution (like 'eval') or obvious malicious patterns were found. No hardcoded secrets are present. The NPI data itself is publicly available, so exposing it via a tool is not a direct security risk, assuming appropriate access controls are implemented at the consuming Spring AI application level.
Updated: 2025-12-03GitHub→
0
0
High Cost
jonathanjacka icon

agent-trading-platform

by jonathanjacka

Sec8

An autonomous AI-powered stock trading platform featuring multiple AI agents with distinct trading strategies for researching markets, making trading decisions, and learning from experiences.

Setup Requirements

  • ⚠️Requires OpenAI API Key (Paid service)
  • ⚠️Requires Polygon.io API Key (Paid service, Starter tier is 15-min delayed)
  • ⚠️Requires Brave Search API Key (Paid service)
  • ⚠️Requires Anthropic API Key (Paid service, implied for ConsultantAgent via AI SDK)
  • ⚠️API_SECRET environment variable is crucial for protecting server endpoints in production; otherwise, they are publicly accessible.
Verified SafeView Analysis
The application uses environment variables for all API keys and secrets, which is good practice. API key authentication is implemented for protected endpoints, and rate limiting is in place for expensive operations like AI trades. Global error handling suppresses detailed stack traces in production. A critical security note is that API_SECRET authentication is disabled if the environment variable is not configured, which could lead to unprotected endpoints in a production environment if overlooked.
Updated: 2025-12-24GitHub→
0
0
Medium Cost
clydewatts1 icon

prototype_chameleon

by clydewatts1

Sec7

A dynamic, self-modifying MCP server enabling autonomous AI agents to evolve their capabilities at runtime through database-backed tool, resource, and prompt management, complemented by an AI-powered debugger.

Setup Requirements

  • ⚠️Requires Python 3.12+.
  • ⚠️LLM integration for the client debugger (e.g., Google Gemini or Ollama) requires an API key or a locally running Ollama server, respectively.
  • ⚠️Using the SSE transport for the server requires installing additional Python packages: 'uvicorn' and 'starlette'.
Review RequiredView Analysis
The server uses `exec()` to dynamically run code from the database, which is an inherent high-risk operation allowing arbitrary code execution. This risk is extensively mitigated by: AST-based validation for Python code to block dangerous imports/functions (e.g., `subprocess`, `eval`, `os.system`); `sqlglot` AST parsing for mathematically verified read-only SQL queries and single-statement validation; SHA-256 hash integrity checks for all code; and a database-driven, configurable security policy system. Advanced data tools (e.g., `general_merge_tool` for upserts, `execute_ddl_tool` for schema changes) are provided but include robust input validation, require explicit confirmation for DDL, and leverage SQLAlchemy's secure parameter binding. The project's documentation transparently acknowledges these security implications and strongly advises additional OS-level sandboxing (e.g., Docker, VMs) for production environments with untrusted code. Hardcoded API keys are avoided, relying on environment variables or configuration files.
Updated: 2026-01-19GitHub→
0
0
Low Cost
LuluBeatson icon

mcp-test-repo-nov24

by LuluBeatson

Sec10

This repository serves as a test bed for an MCP server, designed to validate the functionality of 18 associated tools.

Verified SafeView Analysis
The provided source code consists only of a README.md file. This file contains no executable logic, sensitive information, or patterns like 'eval', obfuscation, or network calls. Therefore, no security risks are identifiable within the provided content. A comprehensive security audit of the actual MCP server or its tools would require their full source code, which is not provided.
Updated: 2025-11-24GitHub→
0
0
Low Cost
AhmedAbdelmaksood65 icon

MonkeyApp

by AhmedAbdelmaksood65

Sec6

An MCP server core implementation for managing player connections, world generation, chat, and game logic in a Minecraft-like environment.

Setup Requirements

  • ⚠️Requires a `config.json` file to be manually created and configured for server settings (e.g., port, max players, world name).
  • ⚠️Requires Python 3.x and dependencies listed in `requirements.txt` to be installed (`pynbt`, `pyglet`, `websockets`). The `pyglet` library may necessitate specific system-level graphics libraries (e.g., OpenGL) depending on the operating system.
Review RequiredView Analysis
The server handles external input via network packets and in-game commands. The summaries for `NetworkManager.py`, `PacketHandler.py`, and especially `CommandManager.py` do not detail input sanitization, validation, or sandboxing mechanisms. Lack of robust handling in these areas could lead to vulnerabilities like command injection or malformed packet exploits. No explicit 'eval', obfuscation, or hardcoded secrets were mentioned in the provided summary, which is a positive, but the inherent risks of a server handling untrusted external input remain significant without further detail.
Updated: 2025-11-20GitHub→
0
0
Low Cost
jurgen178 icon

esp32-mcp

by jurgen178

Sec8

Enables AI assistants to control physical hardware devices via the Model Context Protocol (MCP).

Setup Requirements

  • ⚠️Requires Arduino Nano ESP32 hardware.
  • ⚠️Requires Arduino IDE or PlatformIO for compilation and flashing to the ESP32 board.
  • ⚠️WiFi network name and password must be configured in `arduino_secrets.h`.
Verified SafeView Analysis
The server runs on an embedded device (ESP32) and exposes HTTP endpoints (/mcp and /sse) over WiFi, which is standard for IoT but implies network accessibility. WiFi credentials (`SECRET_SSID`, `SECRET_PASS`) are defined directly in `arduino_secrets.h`, which is a common practice for Arduino projects but requires careful handling to prevent exposure if the file is shared or committed to public repositories. The project claims 'memory-safe execution' and uses standard protocols (JSON-RPC 2.0, MCP). No 'eval' or malicious patterns are evident in the provided code snippets.
Updated: 2025-12-16GitHub→
0
0
Low Cost
stigenai icon

mcp-servers

by stigenai

Sec9

This repository provides standardized Docker images for various Model Context Protocol (MCP) servers, enabling their seamless deployment on orchestrator platforms like Stigen.io.

Setup Requirements

  • ⚠️Docker must be installed and running
Verified SafeView Analysis
The repository demonstrates a strong commitment to security, as evidenced by the `SECURITY.md` file which outlines best practices such as non-root execution, minimal base images, automated vulnerability scanning (Trivy), and regular dependency updates (Dependabot). No 'eval', obfuscation, hardcoded secrets, or overtly malicious patterns were found in the provided code snippets. Environment variables are used for configuration, and server images are tagged with specific versions and Git commits for traceability. The primary inherent risk comes from the capabilities of certain servers (e.g., Playwright's browser automation) if misused by the end-user or deployed without proper network policies, which the `SECURITY.md` also advises against.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
CyprianFusi icon
Sec8

Provides intelligent research data management using vector embeddings and semantic search via a Model Context Protocol (MCP) server.

Setup Requirements

  • ⚠️Requires `OPENAI_API_KEY` (paid API usage for embeddings).
  • ⚠️Requires Python 3.13 or higher.
  • ⚠️Requires `RESEARCH_DB_PATH` environment variable for local ChromaDB storage.
Verified SafeView Analysis
The server requires `RESEARCH_DB_PATH` to be configured as an environment variable. If an attacker can control this variable, they could potentially direct the server to write or delete files in arbitrary locations outside the intended database directory. However, the code itself does not contain `eval`, hardcoded secrets, or obvious direct command injection vulnerabilities. Topic names are normalized to prevent path traversal within the designated database root. Proper configuration of `RESEARCH_DB_PATH` to an isolated directory is crucial for security.
Updated: 2025-12-14GitHub→
0
0
Low Cost
PaulGG-Code icon

kali_mcp-mcp-server

by PaulGG-Code

Sec7

A Model Context Protocol (MCP) server that exposes common pentest tools as FastMCP tools for educational and internal testing purposes.

Setup Requirements

  • ⚠️Requires Docker for a reproducible environment (as implied by README)
  • ⚠️Requires S3/MinIO for artifact storage (defaults to MinIO) or a local path to be mounted/available.
  • ⚠️Default API keys and MinIO credentials are insecure and must be changed for production or any non-isolated testing environment.
Review RequiredView Analysis
The server uses `subprocess.run` with argument lists, mitigating shell injection risks. Input sanitization is mentioned and observed in command construction. However, it ships with insecure default API keys ('changeme_admin_key', 'changeme_operator_key') and MinIO credentials ('minioadmin'). The README explicitly warns against exposing the server publicly without proper network controls and advises rotating API keys. Artifacts containing sensitive information are stored and require proper retention policies. The tools themselves (nmap, sqlmap, etc.) are powerful and inherently risky if misused or pointed at unintended targets. The `binwalk_extract` and `apk_static` tools process files by path inside the container, requiring careful management of container mounts.
Updated: 2025-11-30GitHub→
0
0
Low Cost
DeepthiR2405 icon

mcp-weather-server

by DeepthiR2405

Sec4

Provides a simple FastAPI server for querying current weather information for a specified city.

Setup Requirements

  • ⚠️Requires an OpenWeatherMap API Key (free tier available, but registration is needed).
  • ⚠️The 'API_KEY' must be replaced with a valid key; it is currently hardcoded as a placeholder.
  • ⚠️Implicitly requires `uvicorn` and `requests` libraries (likely specified in a `requirements.txt` file not provided).
Verified SafeView Analysis
The OpenWeatherMap API key is hardcoded as 'YOUR_API_KEY_HERE' in `app.py`. This is a critical security vulnerability; secrets should always be stored in environment variables, not directly in the source code.
Updated: 2025-12-03GitHub→
PreviousPage 301 of 713Next