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
Low Cost
BACH-AI-Tools icon

taiwan-holiday-mcp

by BACH-AI-Tools

Sec8

Provides a Model Context Protocol (MCP) server for querying accurate Taiwan national holidays and make-up workdays.

Setup Requirements

  • ⚠️Requires Node.js 18.0.0 or higher.
  • ⚠️Requires `npm` (for `npx` execution).
  • ⚠️Requires an active internet connection to `cdn.jsdelivr.net` for initial holiday data fetching.
Verified SafeView Analysis
The server fetches holiday data from `cdn.jsdelivr.net/gh/ruyut/TaiwanCalendar`. While `cdn.jsdelivr.net` is a reputable CDN, it's an external dependency. The server implements robust error handling, circuit breaking, request throttling, and input/data validation (e.g., `validateHolidayData`, `parseDate`) to mitigate risks from external API failures or malformed input. No `eval` or direct `fs` writes are observed. `fs.readFileSync` is used only for reading `package.json` at startup. No hardcoded secrets are found.
Updated: 2025-12-04GitHub→
0
0
Low Cost
arnaldo-delisio icon

mcp-oauth-password

by arnaldo-delisio

Sec8

Provides a self-hosted, password-based OAuth 2.1 authentication server for Model Context Protocol (MCP) applications.

Setup Requirements

  • ⚠️Requires a PostgreSQL database connection string, which will be used to automatically create necessary tables (`authorization_codes`, `oauth_clients`, `session`, `auth_logs`).
  • ⚠️Requires several pre-generated credentials for configuration, including a bcrypt hash of the login password, an OAuth client ID and secret, a session secret, and an API key.
  • ⚠️If using the default login page, the host application must configure Express to use EJS as its view engine and specify the path to the login view.
Verified SafeView Analysis
The server implements OAuth 2.1 with Proof Key for Code Exchange (PKCE), bcrypt password hashing (10 rounds), and secure session cookies (httpOnly, secure, sameSite=Lax). Session and authorization codes are stored persistently in PostgreSQL. Redirect URI validation and automatic rate limiting on login, token, and authorize endpoints help mitigate common attacks. Audit logging tracks authentication events for monitoring. The 'secure' cookie flag is correctly enforced based on the NODE_ENV. For its intended use in personal/self-hosted environments, these features provide strong security. However, as noted in the README, features like token expiration with refresh tokens and multi-user support (beyond a single configured password) are still on the roadmap for full enterprise-grade production readiness (v1.0.0). The example provides default credentials for demonstration, but the core library design encourages using environment variables for sensitive data.
Updated: 2025-12-13GitHub→
0
0
High Cost
mfatihp icon
Sec1

Manage the lifecycle of custom Python Micro-Computational Program (MCP) servers using Docker and interact with them via an AI-powered chat interface.

Setup Requirements

  • ⚠️Requires Docker and Docker Compose for deployment.
  • ⚠️Requires PostgreSQL and Redis databases.
  • ⚠️HuggingFace API Key (HF_API_KEY) is necessary for the LLM service.
  • ⚠️Requires downloading large LLM models from HuggingFace, which can consume significant disk space and bandwidth.
Review RequiredView Analysis
The application allows arbitrary Python code and Dockerfile commands to be executed via user input in the `func_body`, `server_name`, and `pkgs` fields when creating a new server. This leads to severe remote code execution (RCE) vulnerabilities. Additionally, the FastAPI services (`mcp_manager_core`, `llm_chat_service`) use `CORSMiddleware(allow_origins=["*"])`, making them vulnerable to cross-site request forgery (CSRF) and other attacks if deployed in a public-facing manner. Direct Docker daemon interaction from `DockerHandler` based on user-supplied container IDs poses a high risk if the application itself is compromised.
Updated: 2025-12-12GitHub→
0
0
Medium Cost
jegelstaff icon

formulize-mcp

by jegelstaff

Sec9

Enables AI assistants to interact with and manage data within a remote Formulize open-source data management platform.

Setup Requirements

  • ⚠️Requires Node.js to be installed on the system.
  • ⚠️A Formulize instance must be running and accessible via a URL.
  • ⚠️An API key from your Formulize system is required and must be configured as an environment variable.
Verified SafeView Analysis
The server correctly uses environment variables for sensitive API keys (FORMULIZE_API_KEY) and does not hardcode them. It acts as a proxy, forwarding requests to a remote Formulize instance using standard HTTP fetch. There is no evident use of 'eval' or unsafe direct command execution within the proxy's core logic. The security of the overall system largely depends on the remote Formulize server's configuration and the careful management of API keys by the user. The 'query_the_database_directly' tool, if exposed by Formulize, would be a remote security concern for the Formulize instance itself, rather than a direct vulnerability in this proxy server's implementation.
Updated: 2026-01-12GitHub→
0
0
High Cost
eslaim icon
Sec9

The MCP server generates various AI-powered diagrams (architecture, flowcharts, user journey/story maps, empathy maps, pyramid diagrams), infographics (Feynman learning method, posters), and UI/UX prototypes (general HTML, Apple Mobile, WeChat MiniApp) in DrawIO XML, HTML, SVG, or JSON formats based on user descriptions.

Setup Requirements

  • ⚠️Requires an API key for ZhipuAI, OpenAI, or Gemini (Paid Service) to function.
  • ⚠️Python 3.10 or newer is required as per `pyproject.toml`.
  • ⚠️Installation of Python packages `mcp`, `openai`, `zhipuai`, and `python-dotenv` is necessary.
Verified SafeView Analysis
API keys for AI providers are loaded from environment variables (.env file), which is a secure practice. The server includes functions (`svg_clear`, `xml_drawio_clear`, `json_clear`, `html_clear`) to sanitize AI-generated output, mitigating potential injection risks if output were rendered directly. No use of `eval` or obvious malicious patterns was found. The primary security consideration is the secure handling of AI API keys by the user.
Updated: 2026-01-19GitHub→
0
0
Low Cost
EPS-AI-SOLUTIONS icon

GeminiHydra

by EPS-AI-SOLUTIONS

Sec8

Lightweight MCP server for integration with Ollama and Gemini CLI, providing AI text generation, multi-agent task execution, task queuing, caching, and prompt optimization.

Setup Requirements

  • ⚠️Requires a local Ollama server instance running and accessible at OLLAMA_HOST.
  • ⚠️Requires the Gemini CLI tool to be installed and configured with GOOGLE_API_KEY or GEMINI_API_KEY for cloud AI integration.
  • ⚠️Project setup uses pnpm for dependency management (`pnpm install`).
Verified SafeView Analysis
The server includes a `run_shell_command` tool, which inherently carries security risks if exposed to untrusted input. However, significant efforts have been made to mitigate these risks through a `CommandSanitizer`, `SecurityEnforcer`, `AuditLogger`, and the use of `DANGEROUS_PATTERNS` to block or warn about potentially malicious commands and path traversals. The `HYDRA_RISK_BLOCKING` environment variable allows administrators to control this exposure. Cache encryption is optional via `CACHE_ENCRYPTION_KEY`, with a warning issued if not configured. No obvious hardcoded secrets were found; API keys are expected via environment variables or standard config files.
Updated: 2026-01-19GitHub→
0
0
Low Cost
dchu3 icon
Sec9

The MCP server wraps the Base Blockscout API to provide agent-friendly tools for querying account, transaction, contract, token, log, and DEX router activity on Base Mainnet and Base Sepolia.

Setup Requirements

  • ⚠️Requires Node.js 20+ to run.
  • ⚠️Requires manual creation and configuration of a '.env' file based on '.env.example'.
  • ⚠️Blockscout API access is necessary, and heavy usage might require an API key to avoid rate limits.
Verified SafeView Analysis
The server appears well-designed for security, using environment variables for API keys and configurable values (like router addresses), adhering to read-only operations, and implementing rate limiting, caching, and retries for external API interactions. There is no usage of 'eval' or other inherently dangerous patterns. Router addresses are hardcoded as defaults but are explicitly overrideable via a JSON file and CLI, mitigating potential single-point-of-failure concerns.
Updated: 2025-11-22GitHub→
0
0
Medium Cost
workademy icon
Sec3

Provides comprehensive integration with the Workademy LMS platform, enabling LLMs to manage courses, users, enrollments, learning paths, and generate reports.

Setup Requirements

  • ⚠️Requires Node.js 18 or higher to run.
  • ⚠️Requires a Workademy account with API access and an API key.
  • ⚠️Authentication involves a hardcoded system credential, posing a significant security risk.
Review RequiredView Analysis
CRITICAL: The server's authentication mechanism for obtaining an access token uses a hardcoded Basic Authentication credential ('Basic c3lzdGVtOkViNFRRaXpEdFlpYndJTHI=' which decodes to 'system:Eb4TQizDtYibwILr'). This static, hardcoded system credential is a severe security vulnerability, as it is exposed in the source code and could be exploited to compromise the token issuance process or gain unauthorized access if not properly secured on the Workademy API side. Additionally, the server interacts with the local file system (using `fs/promises` and `path`) to save and analyze CSV reports in a Claude-specific temporary directory, which introduces a potential vector for file system manipulation if not handled robustly.
Updated: 2025-12-10GitHub→
0
0
Medium Cost
ryan-rbw icon
Sec9

Provides GitLab integration tools to AI assistants like Claude Desktop and ChatGPT, acting as a secure bridge for code and project management operations.

Setup Requirements

  • ⚠️Requires Python 3.12+ or Docker for deployment.
  • ⚠️Requires access to a GitLab instance and the ability to register an OAuth application (admin rights recommended). This involves several manual steps to configure Client ID, Secret, Redirect URI, and Scopes in GitLab.
  • ⚠️Persistent user sessions with encrypted token storage require generating and securely managing a Fernet encryption key (`KEPLER_MCP_TOKEN_ENCRYPTION_KEY`).
Verified SafeView Analysis
The server implements strong security practices including OAuth 2.0 with PKCE for user authentication, Fernet encryption for session tokens at rest, and explicit redaction of sensitive data in logs. It uses Pydantic's SecretStr for secret configuration fields. The server binds to '0.0.0.0' by default, which is noted as intentional for Docker container networking, but administrators must ensure it's behind a reverse proxy or firewall in production to mitigate direct exposure. There are no obvious malicious patterns, 'eval' usage (other than standard library imports, not arbitrary execution) or hardcoded secrets in the provided code.
Updated: 2025-12-08GitHub→
0
0
Low Cost
chienchuanw icon

gma2-mcp

by chienchuanw

Sec3

Provides a programmatic interface via Telnet to control grandMA2 lighting consoles using the Model Context Protocol (MCP).

Setup Requirements

  • ⚠️Requires grandMA2 lighting console with Telnet access enabled.
  • ⚠️Requires Python 3.12+.
  • ⚠️Login credentials (GMA_HOST, GMA_USER, GMA_PASSWORD) must be configured in a .env file or environment variables; otherwise, insecure defaults are used.
Review RequiredView Analysis
The server relies on Telnet, an unencrypted protocol, meaning all communication including login credentials and commands are transmitted in plain text, making it vulnerable to eavesdropping and credential theft. Default login credentials ('administrator', 'admin') are hardcoded, which, if not overridden in the `.env` file, pose a significant security risk. Unauthorized access could lead to disruption of lighting control systems.
Updated: 2025-12-26GitHub→
0
0
Medium Cost
keyurgolani icon

TasksMcp

by keyurgolani

Sec8

Enterprise-grade task management and orchestration for AI agents, featuring dependency management and multi-interface support.

Setup Requirements

  • ⚠️Requires Node.js runtime environment.
  • ⚠️Local development requires 'npm install' and 'npm run build'.
  • ⚠️Relies heavily on environment variables for configuration, necessitating careful setup (e.g., data storage paths, database credentials).
  • ⚠️Default data storage is filesystem-based, requiring a configurable DATA_DIRECTORY.
Verified SafeView Analysis
The server uses robust Zod for input validation and comprehensive error handling with retry logic and circuit breakers. Input preprocessing is applied for agent-friendly type coercion before strict validation. File system operations are wrapped in file locks and retry logic. No direct use of 'eval' or obvious command injection vulnerabilities were found. Configuration is managed via environment variables and dedicated config files, avoiding hardcoded secrets. Rate limiting is configured but the middleware implementation wasn't fully shown in the provided snippets. Overall, it follows good security practices for its context.
Updated: 2026-01-19GitHub→
0
0
High Cost
a7medsa22 icon

Ai-Knowledge-Hub

by a7medsa22

Sec8

AI-powered knowledge management and research platform featuring document management, intelligent summarization, Q&A, and MCP integration.

Setup Requirements

  • ⚠️Requires Docker and Docker Compose for PostgreSQL.
  • ⚠️Requires local Ollama server running and a model pulled (e.g., 'llama3.1:8b') for local AI, or an OpenAI/Anthropic API key for cloud AI.
  • ⚠️Requires Node.js 18+ and npm.
Verified SafeView Analysis
The application uses NestJS with security best practices like Helmet for HTTP headers, global validation pipes, JWT-based authentication with ownership checks for resources, and throttling for rate limiting. Sensitive configurations (API keys, JWT secrets, DB URLs) are correctly loaded from environment variables. A custom HTTP exception filter provides consistent error handling. File uploads use unique filenames, and the `serveFile` endpoint relies on Express's `res.sendFile` which typically prevents path traversal. However, production deployments should harden CORS policies beyond `localhost:3000` and confirm robust path traversal prevention in `serveFile` for filenames provided by users. No 'eval' or obvious obfuscation detected.
Updated: 2026-01-12GitHub→
PreviousPage 507 of 760Next