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
eagleisbatman icon

tips-mcp-server

by eagleisbatman

Sec8

Serve AI-generated farming tips, categorized by region and context (weather, season), with bilingual support and interaction tracking.

Setup Requirements

  • ⚠️Requires Node.js 18+ runtime.
  • ⚠️Requires a PostgreSQL database with specific 'tip_categories', 'tips', and 'tip_interactions' tables, whose schema is defined in a migration file from a related project (`nong-tri`). Manual setup or prior deployment of that project's migrations is necessary.
  • ⚠️Requires an external Weather API (WEATHER_API_URL) to provide contextual weather data for tips.
Verified SafeView Analysis
The server uses parameterized queries, which effectively prevents SQL injection. Environment variables are used for sensitive configurations (DATABASE_URL), avoiding hardcoded secrets. CORS is configurable. The direct passing of user-provided 'location' to an external weather API could be a minor concern if the external API itself is vulnerable to injection, but the server's code doesn't directly introduce this vulnerability. The `rejectUnauthorized: false` for SSL is correctly conditionalized for non-production environments.
Updated: 2025-12-01GitHub→
0
0
Low Cost
selvasv icon

adk-docs

by selvasv

Sec9

Python Flask microservice template for Kubernetes deployments with multi-profile traffic management (stable, canary, preview) and integrated Azure Data Factory pipelines for data movement.

Setup Requirements

  • ⚠️Requires Docker for building and packaging the microservice, although the Dockerfile content is not provided.
  • ⚠️Full deployment and traffic management (stable, canary, preview profiles) necessitate a Kubernetes cluster with Ambassador installed.
  • ⚠️Azure Data Factory setup, including Azure Blob Storage and Azure Key Vault, is required for the data pipeline functionalities.
Verified SafeView Analysis
The Flask application (`app.py`) is very simple, containing a basic 'Hello World' endpoint with no evident security vulnerabilities, 'eval' usage, or obfuscation. The Azure Data Factory configurations (`linkedService` files) demonstrate a secure practice by using Azure Key Vault to manage sensitive connection strings, preventing hardcoded secrets in the repository. The application binds to '0.0.0.0', which is standard for containerized services.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
azharlabs icon
Sec9

A FastAPI and MCP server designed to expose Retrieval-Augmented Generation (RAG) knowledge bases for chat interactions and document ingestion.

Setup Requirements

  • ⚠️Requires an active API key for a compatible Large Language Model (LLM) service (e.g., Gemini, OpenAI), which is typically a paid service. The `MODEL_API_KEY` environment variable is mandatory.
  • ⚠️The default Qdrant vector database is configured for in-memory storage, meaning all indexed document data will be lost upon server restart unless `QDRANT_URL` (for remote) or `QDRANT_PATH` (for local persistent) is explicitly configured.
  • ⚠️The `extractanything` library (which uses MarkItDown) for document processing might require additional system-level dependencies (e.g., LibreOffice) for effective parsing of various file formats (e.g., .docx, .pptx) beyond standard Python packages. These are not specified in the `requirements.txt`.
Verified SafeView Analysis
The server demonstrates good security practices: sensitive configurations like API keys and database URLs are loaded from environment variables or a configuration file, not hardcoded. User passwords are hashed using `hashlib.sha256`, and API keys are generated securely with `secrets.token_urlsafe`. File uploads are size-limited and use temporary UUIDs to prevent path traversal. Frontend markdown rendering is sanitized using `DOMPurify` to mitigate XSS risks. Authentication and authorization checks are implemented for API endpoints. The primary remaining risk would involve potential vulnerabilities within third-party libraries (e.g., `extractanything` or `MarkItDown`) for document parsing, but the direct application code is robust.
Updated: 2026-01-03GitHub→
0
0
Low Cost
rohitvish07 icon
Sec9

Manages and tracks personal expenses by providing an API to add, list, and summarize financial transactions.

Setup Requirements

  • ⚠️Requires `DB_URL` environment variable pointing to a PostgreSQL database (e.g., Neon).
  • ⚠️Requires Python 3.12 or higher.
Verified SafeView Analysis
The server uses parameterized queries with `asyncpg` to prevent SQL injection vulnerabilities. The database connection URL (`DB_URL`) is correctly loaded from environment variables, avoiding hardcoded secrets. Basic input validation is present for numeric amounts. The server listens on all network interfaces (`0.0.0.0`), which is typical for containerized deployments but should be secured with a firewall in production environments.
Updated: 2025-12-07GitHub→
0
0
Low Cost
paularlott icon

mcp

by paularlott

Sec8

A Go library for building Model Context Protocol (MCP) servers with a fluent API, especially for integrating with Large Language Models (LLMs) to provide and execute tools efficiently.

Setup Requirements

  • ⚠️LLM integration (via `openai` subpackage) typically requires an OpenAI API Key (or equivalent for other LLMs), which can incur costs.
  • ⚠️The `openai` subpackage's examples are configured to use LM Studio (a local LLM server) running on `127.0.0.1:1234` with a specific model (`qwen/qwen3-1.7b`). This local setup is required for the examples to work out-of-the-box.
Verified SafeView Analysis
The library adheres to good Go practices, utilizing standard networking and JSON handling with internal error handling for invalid requests/parameters. Key security features include default `InsecureSkipVerify: false` for TLS, and `MAX_TOOL_CALL_ITERATIONS` to prevent infinite tool loops in LLM integration. Potential risks typically stem from user-implemented tool handlers (e.g., unsafe file I/O or OS command execution without validation) rather than the core library itself. While tool search could be a DoS vector for very long inputs if not protected by an upstream API gateway, the internal implementation does not show immediate vulnerabilities.
Updated: 2026-01-17GitHub→
0
0
Medium Cost
CR-AudioViz-AI icon

crav-mcp-vercel

by CR-AudioViz-AI

Sec8

Vercel deployment automation and resource management for AI applications, enabling autonomous deployments, real-time build monitoring, log retrieval, error parsing, and resource management.

Setup Requirements

  • ⚠️Requires a Vercel access token (`VERCEL_TOKEN`) with deployment permissions.
  • ⚠️Requires a secure, user-defined API key (`MCP_API_KEY`) for this server's authentication.
Verified SafeView Analysis
The server employs standard security middleware (`helmet`, `cors`, `express-rate-limit`) and uses API key authentication (`MCP_API_KEY`) for all sensitive endpoints. The Vercel access token (`VERCEL_TOKEN`) is correctly sourced from environment variables. No obvious hardcoded secrets or malicious patterns were found in the core server logic. The primary security relies on the confidentiality and integrity of the `MCP_API_KEY` and `VERCEL_TOKEN`.
Updated: 2026-01-09GitHub→
0
0
High Cost
peakmojo icon
Sec7

Automate software development tasks using Claude Code AI agents within isolated E2B sandboxes, providing a fixed set of skills and a job-level API.

Setup Requirements

  • ⚠️Requires E2B API Key (Paid service)
  • ⚠️Requires Claude API Access (Paid service, implied by 'Claude Code')
  • ⚠️Assumes a pre-built E2B base image with Claude Code installed and configured
Review RequiredView Analysis
The system design leverages E2B for sandbox isolation, which is a strong security principle for running arbitrary code. Skills are bundled and fixed, reducing injection risks. However, the actual server-side code (MCP implementation) for provisioning sandboxes, handling client input, managing secrets (like E2B/Claude API keys), and securely copying/mounting user-provided repositories is not available for audit. Without reviewing the implementation, critical vulnerabilities related to input validation, secret management, or sandbox escape cannot be ruled out. The 'eval' keyword, obfuscation, or hardcoded secrets cannot be checked without the full source code. The security score reflects the robust design intent, not an audited implementation.
Updated: 2025-12-02GitHub→
0
0
Medium Cost
eagleisbatman icon

traduora-mcp-server

by eagleisbatman

Sec8

An MCP server for managing translations in Traduora via its API, acting as a tool for a larger model or system.

Setup Requirements

  • ⚠️Requires a running Traduora instance (e.g., deployed on Railway with a MySQL database).
  • ⚠️Requires generation and configuration of OAuth2 client ID and client secret within Traduora for the MCP server to authenticate.
  • ⚠️Critical environment variables (TRADUORA_API_URL, TRADUORA_CLIENT_ID, TRADUORA_CLIENT_SECRET) must be set for full functionality; a warning is logged if missing.
Verified SafeView Analysis
The server correctly uses environment variables for sensitive configurations (Traduora API URL, client ID, client secret). It employs `zod` for robust input validation of tool arguments, mitigating common injection risks. CORS is enabled, defaulting to '*' if `ALLOWED_ORIGINS` is not explicitly set in environment variables, which is a potential security risk in a production environment if not configured to restrict origins. There are no direct uses of `eval` or obvious malicious patterns in the provided source code. The OAuth2 client credentials flow is standard.
Updated: 2025-11-29GitHub→
0
0
Medium Cost
manuel2f icon

mcp-servers-manu

by manuel2f

Sec8

This server provides tools for searching and exploring internal CDN documentation, including specific components, DTS, and Wiki content.

Setup Requirements

  • ⚠️Requires access to an internal CDN documentation server at `http://cdn-docs.cdn.hi.inet` (or a custom URL via `CDN_DOCS_BASE_URL`).
  • ⚠️Requires Node.js and npm installed to run the TypeScript server.
  • ⚠️For full integration, it needs to be configured in a Model Context Protocol (MCP) client like VS Code's `mcp.json`.
Verified SafeView Analysis
The server primarily functions as a web scraper for internal documentation, using `axios` and `cheerio`. The default `BASE_DOCS_URL` points to an internal network address (`cdn-docs.cdn.hi.inet`), limiting external exposure. No `eval` or dynamic code execution is observed, and no hardcoded secrets are present. The main security considerations would be ensuring the internal documentation source itself is trusted and not susceptible to content injection that could bypass `cheerio`'s sanitization, or potential SSRF if `CDN_DOCS_BASE_URL` is set to an untrusted external URL via environment variable.
Updated: 2025-12-01GitHub→
0
0
Medium Cost
jorgearturoyap-debug icon

metatrader-5-for-Chatgpt-Desktop

by jorgearturoyap-debug

Sec7

A Model Context Protocol (MCP) server for MetaTrader 5, specifically adapted for ChatGPT Desktop integration to enable trading and market data analysis.

Setup Requirements

  • ⚠️Requires a ChatGPT Plus subscription or higher (Free tier does not support MCP).
  • ⚠️Requires MetaTrader 5 terminal installed on Windows, limiting its use to Windows OS.
  • ⚠️Requires ngrok setup (account, auth token) for public tunneling, and the dynamically generated ngrok HTTPS URL must be manually updated in ChatGPT Desktop settings upon each new ngrok session (free ngrok sessions expire frequently).
Verified SafeView Analysis
The server explicitly warns that it is publicly exposed via ngrok and recommends setting an `MCP_API_KEY` for authentication. If `MCP_API_KEY` is not configured, the server is open to all connections, which is a significant security risk. The `start_chatgpt.bat` script binds the server to `0.0.0.0` (all interfaces) which is necessary for ngrok but requires careful network security. There are no 'eval' or obvious malicious patterns, and the code relies on the official MetaTrader5 Python API. Users are strongly advised to use a demo account first and configure the API key.
Updated: 2025-11-19GitHub→
0
0
Medium Cost
Aliimran14 icon

prop_crm

by Aliimran14

Sec1

A server component for property customer relationship management, designed to integrate with a GitHub MCP (Microservice Communication Protocol) environment.

Review RequiredView Analysis
Crucial source code (application logic, dependencies, server configuration, etc.) was not provided beyond the README.md. Therefore, a comprehensive security audit for 'eval', obfuscation, network risks, hardcoded secrets, or malicious patterns is impossible. The low score reflects an inability to verify safety due to missing code, rather than identified vulnerabilities.
Updated: 2025-12-05GitHub→
0
0
Low Cost
darkdragonsastro icon

dda-mcp-server

by darkdragonsastro

Sec8

The DDA MCP Server controls astronomy equipment, including proprietary Dark Dragons Astronomy devices and any ASCOM Alpaca-compatible hardware, by exposing their functionalities as Model Context Protocol (MCP) tools for agent interaction.

Setup Requirements

  • ⚠️Requires Node.js and npm/npx to run.
  • ⚠️Requires physical Dark Dragons Astronomy devices or ASCOM Alpaca-compatible hardware on the local network to be functional.
  • ⚠️ASCOM Alpaca devices must be explicitly connected using the `alpaca_device_connect` tool before other operations can be performed.
Verified SafeView Analysis
The server uses `fetch` to interact with user-provided IP addresses and ports on the local network for device control and discovery. While inherent to its function of controlling local astronomy equipment, this pattern could pose a Server-Side Request Forgery (SSRF) risk if the MCP server itself were exposed to untrusted external requests. However, given its intended execution context (local MCP server via stdio, often by an agent like Claude Desktop), the risk is mitigated as it primarily interacts with trusted local network devices. No `eval`, code obfuscation, or hardcoded secrets were found.
Updated: 2025-11-27GitHub→
PreviousPage 648 of 713Next