Stop Searching. Start Trusting.

The curated directory of MCP servers, vetted for security, efficiency, and quality.

Browse Directory Why 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)

Low Cost

mcp-server-authless

by Origonlabs

Sec6

Deploys a remote Model Context Protocol (MCP) server on Cloudflare Workers without authentication, allowing AI clients to access custom tools.

Setup Requirements

⚠️Requires a Cloudflare account for deployment to Cloudflare Workers.
⚠️The server is intentionally 'authless', which requires careful security consideration if deploying beyond demonstration purposes.

Verified SafeView Analysis

The server is explicitly designed to be 'authless', meaning any client with the URL can connect. While suitable for demonstration, this poses a network risk in production environments if sensitive tools are exposed or if the tools themselves have security vulnerabilities. No obvious 'eval' or obfuscation is mentioned within the provided README.

Updated: 2025-11-17GitHub→

Medium Cost

claude-mcp-servers

by harshv2013

Sec9

Provides Model Context Protocol (MCP) servers for Claude Desktop, enabling secure file system access and advanced mathematical calculations.

Setup Requirements

⚠️Requires macOS and Claude Desktop application.
⚠️Requires Python 3.10+.
⚠️Manual configuration of Claude Desktop's `claude_desktop_config.json` with absolute paths to the server scripts is required and can be error-prone.
⚠️Currency exchange rates in the calculator are hardcoded (as of Jan 2025 approximations) and not real-time.

Verified SafeView Analysis

The File System server implements robust path validation checks (e.g., `path.resolve().startswith(ALLOWED_DIR.resolve())`) for all file operations (read, write, search, stats). This is crucial and effectively prevents directory traversal attacks, limiting file access and modification to the `test_files` directory (or a user-configured directory). The `write_file` tool is exposed, allowing an agent to create/modify files within the allowed directory, which is an intended but powerful capability. The Calculator server is purely computational, using standard Python `math` functions and explicit arithmetic operations without `eval` or dynamic code execution, making it inherently safe. There are no obvious hardcoded secrets or network risks beyond standard MCP (stdin/stdout) communication. The `factorial` tool has a maximum input limit (n<=20) to prevent resource exhaustion.

Updated: 2026-01-18GitHub→

Medium Cost

MCP-F1data

by Maxbleu

Sec1

Provides a Model Context Protocol (MCP) server to allow LLMs like Claude to interact with Formula 1 data through a set of Python tools.

Setup Requirements

⚠️Requires Claude Desktop application to be installed and configured with the MCP server entry in its `claude_desktop_config.json` file.
⚠️Requires Python 3.12 or newer to run the server.
⚠️Relies on several environment variables (`JWT_TOKEN`, `APIF1DB_PRIVATE_NETWORK_BASE_PATH`, `PUBLIC_KEY`, `ALGORITHM`) for API authentication and endpoint configuration, which must be correctly set.

Review RequiredView Analysis

The `ExecutionTools.execute_code` function uses `exec(code, env, local_env)` to execute arbitrary Python code. If the LLM is prompted by a malicious actor to generate harmful code, this could lead to critical Remote Code Execution (RCE) vulnerabilities on the host system. While environment variables are used for sensitive API keys (e.g., `JWT_TOKEN`), the direct execution of arbitrary code from potentially untrusted LLM outputs presents a severe risk.

Updated: 2025-12-20GitHub→

Low Cost

mcp-code-analyzer

by Pratham-Prog861

Sec9

Analyzes JavaScript/TypeScript code quality in real-time, providing linting suggestions via both a Model Context Protocol (MCP) server and a standalone HTTP API.

Setup Requirements

⚠️Requires Node.js version 18 or higher.
⚠️Initial setup requires 'npm install' to fetch dependencies.
⚠️For MCP integration with Claude Desktop, the absolute path to 'index.js' needs to be configured manually.

Verified SafeView Analysis

The server performs static code analysis using ESLint on user-provided code. It does not execute the input code, significantly reducing dynamic execution risks (e.g., no 'eval' or direct arbitrary code execution). No hardcoded secrets or obvious malicious patterns are present. Input sanitization is inherently handled by ESLint's static analysis process. The risk is very low.

Updated: 2025-12-02GitHub→

Medium Cost

repka-lifeforce

by repkam09

Sec3

A modular REST API server providing an AI conversational assistant, server utilities, weather, music playback information, and media management.

Setup Requirements

⚠️Requires a Temporal cluster for workflow management.
⚠️Requires a Supabase instance for user authentication and database operations.
⚠️Requires multiple external API keys for services like OpenAI, Brave Search, OpenWeatherMap, and Last.fm (many are paid services).
⚠️Requires Docker and Docker Compose for easy setup and development.

Review RequiredView Analysis

1. Critical Directory Traversal Vulnerability: The `backend_helper/repcast.php` script, which is actively deployed by the project's helper scripts, directly concatenates user-controlled base64-decoded input (`$urlparam`) into the directory path without sanitization. This allows an attacker to list and potentially read arbitrary files outside the intended `repcast` directory (e.g., `?dir=Lw==` would decode to `/`). 2. Static Authentication Token: The system relies on a single, static `LIFEFORCE_AUTH_TOKEN` for general API authorization. If this token is compromised, an attacker gains full access to all endpoints protected by this mechanism, with no expiry or user-specific revocation capabilities. 3. Potential Command Injection in RepCast Torrent Add: While magnet links are base64-decoded, if the `transmission` library (used for adding torrents) doesn't adequately sanitize or escape shell commands embedded within a malformed magnet link, this could lead to command injection on the server running Transmission. This is a hypothetical risk depending on the `transmission` library's internal robustness. 4. Sensitive Data in Logs: Logging webhook request bodies and query parameters directly (`/api/webhook/log`) could expose sensitive information (e.g., passwords, API keys) if clients send such data to these endpoints. 5. Misconfiguration Risk: Plugins like Home Assistant and Weather rely on API keys/URLs from environment variables. A misconfigured or malicious URL could lead to Server-Side Request Forgery (SSRF) if not properly vetted by an administrator.

Updated: 2026-01-07GitHub→

Medium Cost

simlab-ug-mcp-server

by miho

Sec6

Provides an MCP server and GUI for managing, configuring, and executing UG4 Lua simulation scripts by interacting with an external UG gRPC server.

Setup Requirements

⚠️Requires an external UG gRPC server to be running (default localhost:50051) for script analysis and execution.
⚠️Requires the UG4 `ugshell` executable (UG4 simulation software) to be installed and configured in the application.
⚠️The `ughub` launcher in the macOS DMG requires Python 3.x to be installed.
⚠️On macOS, users are advised to run a 'Fix Security.command' (using `xattr -cr`) to bypass Apple's Gatekeeper security warnings for unsigned applications.

Verified SafeView Analysis

The application runs a Model Context Protocol (MCP) server that can be exposed via HTTP (default port 7072) or STDIO. This server allows external clients (like AI agents) to perform actions such as searching scripts, getting script schemas, loading scripts, setting parameters, and executing scripts. While argument passing to the underlying 'ugshell' process is done via `ProcessBuilder` (which mitigates direct shell command injection via parameter values), the server itself provides capabilities for arbitrary script execution. If the HTTP server is exposed to an untrusted network without additional authentication or authorization, it presents a significant security risk, as it grants full control over the execution environment. The `create-dmg.sh` script, intended for macOS distribution, includes a 'Fix Security.command' that uses `xattr -cr` to remove macOS quarantine flags, advising users to disable a system security feature.

Updated: 2025-12-14GitHub→

Low Cost

LongportMCPDocker

by WisdomShun

Sec9

Deploying and managing a Longport Model Context Protocol (MCP) server using Docker for financial API services.

Setup Requirements

⚠️Docker Engine (20.10.0+) and Docker Compose (1.29.0+) are required.
⚠️Longport API credentials (APP_KEY, APP_SECRET, ACCESS_TOKEN) are mandatory and must be obtained from Longport.
⚠️Users need to manually create a `.env` file in the project root to configure credentials and server settings.

Verified SafeView Analysis

The project emphasizes secure practices like environment variable-based credential management, a default read-only mode, and recommends firewall configuration. The primary security risks are user-related, such as accidentally committing `.env` files or exposing the service publicly without proper access restrictions, which the documentation explicitly warns against.

Updated: 2025-11-19GitHub→

Medium Cost

mcp-server-doubao

by oychao1988

Sec6

An MCP server that provides comprehensive image and video generation capabilities using Doubao AI models (Seedream for images, Seedance for videos), designed for integration with clients like Claude Desktop.

Setup Requirements

⚠️Requires an `ARK_API_KEY` obtained from the Volcengine Ark console (potentially a paid service).
⚠️Primarily designed for integration with Claude Desktop, requiring specific `claude_desktop_config.json` setup.
⚠️Requires Node.js version 18.0.0 or higher.

Verified SafeView Analysis

The `download_image` tool's handler uses `path.resolve` and `fs.writeFile` with a user-provided `filePath`. This creates a potential path traversal and arbitrary file write vulnerability if an attacker can control the `filePath` parameter, allowing files to be written outside intended directories (e.g., to sensitive system locations) on the server's host machine. The server relies on an external API key (ARK_API_KEY) which is correctly loaded from environment variables, preventing hardcoded secrets.

Updated: 2026-01-17GitHub→

Low Cost

mcp

by xuemingqi

Sec3

This server acts as a Model Context Protocol (MCP) tool provider, exposing various functionalities (like user management and mail services) as AI-callable tools for Spring AI applications.

Setup Requirements

⚠️Requires a MySQL database instance to be accessible at the configured URL, username, and password.
⚠️Requires a Redis server instance to be accessible at the configured address and password.
⚠️Requires `x-framework` libraries to be built and available as dependencies (suggesting a multi-module Maven/Gradle project).
⚠️The default configurations in `application.yml` for database and Redis (`username: username`, `password: ''`) are insecure and must be changed for any non-local/test environment.

Review RequiredView Analysis

Critical security risks identified: 1. **Hardcoded Empty Passwords:** `application.yml` contains hardcoded empty passwords for MySQL (`password: ''`) and Redis (`password: ''`). This is highly insecure and makes the server vulnerable to unauthorized access. 2. **Hardcoded API Keys:** The client's `application.yml` (though not the primary focus, it's part of the repo) contains a hardcoded DeepSeek/OpenAI API key (`api-key: sk-413c6606010c4852939181278ed7e4a2`), which is a critical secret exposure. 3. **Custom Authentication via Query Params:** The `McpFilter` implements custom authentication using `key` or `sessionId` passed as query parameters. Relying on query parameters for sensitive authentication tokens is generally less secure than using HTTP headers, as query parameters can be logged more easily and persist in browser history/proxy logs. 4. **Extensive Logging:** The `McpFilter` logs full request and response bodies, which could inadvertently expose sensitive data if not handled with caution in production environments. 5. **Test Secrets:** The `ClientSse.java` test file contains a hardcoded key (`sk-e7030e17d1d64881a44a53b359af1644`), which is poor practice even in test code as it could be mistakenly deployed or reveal patterns.

Updated: 2025-11-19GitHub→

Low Cost

test_remote_mcp_server

by aanal25patel

Sec8

This server functions as an expense tracker, allowing users to add, list, and summarize financial expenditures via an API.

Setup Requirements

⚠️Requires Python 3.12 or newer.
⚠️Requires file system write access in the temporary directory for the SQLite database.

Verified SafeView Analysis

The server uses parameterized queries for all database operations, effectively preventing SQL injection. It does not contain 'eval', hardcoded secrets, or obvious obfuscation. File system write access is required for the SQLite database in the temporary directory. Listening on '0.0.0.0' makes it accessible on all network interfaces, which is a deployment consideration rather than a code vulnerability.

Updated: 2025-11-27GitHub→

High Cost

temporal-mcp

by vreme-ai

Sec8

Provides an AI assistant with comprehensive temporal intelligence, including timezone conversions, multi-cultural calendars, holiday data, business time calculations, and astronomical events.

Setup Requirements

⚠️Requires an active connection to the external Vreme Time API (api.vreme.ai) for its core functionality, which may incur costs or require registration/API keys not detailed in the provided context.
⚠️Requires Node.js runtime version 18.0.0 or higher.
⚠️It is designed to be run as an MCP server, meaning an MCP-compatible AI client (e.g., Claude Desktop, VS Code, Continue, Cline) is necessary for its intended use.

Verified SafeView Analysis

The server primarily acts as a proxy to an external Vreme Time API (defaulting to https://api.vreme.ai). While API calls are made over HTTPS, the security and reliability of this external service are critical dependencies outside the scope of this source code analysis. The server uses `StdioServerTransport` for communication with MCP clients, which typically involves standard I/O and does not inherently expose network ports. Input validation for tools is implemented using Zod schemas. Local activity context is stored in a file (`~/.vreme/temporal-context.json`), which could be sensitive depending on user interaction patterns, but no direct filesystem vulnerabilities or hardcoded secrets were identified. No `eval` or obvious obfuscation patterns were detected.

Updated: 2025-12-30GitHub→

Medium Cost

cortex-mcp-server

by Tuckdin

Sec8

The Cortex MCP Server provides a semantic search interface and content ingestion capabilities for a knowledge base focused on ICT trading and social intelligence.

Setup Requirements

⚠️Requires an OpenAI API Key (Paid service for embeddings)
⚠️Requires a Supabase project URL and API Key for data storage
⚠️Python environment with specific dependencies (fastmcp, openai, supabase) must be set up

Verified SafeView Analysis

The application uses environment variables for sensitive API keys (OpenAI, Supabase) and initializes clients lazily, which are good practices. There's no evident use of 'eval' or direct arbitrary code execution. Database interactions use the Supabase client library, which is generally expected to handle parameterization and prevent basic SQL injection for queries and inserts. The `ilike` pattern in `search_text` passes user input directly; while Supabase client usually handles this, it's a point where a very sophisticated payload *could* potentially cause issues if not fully escaped by the library (though unlikely for typical `ilike` usage). Overall, appears reasonably secure for a Python application using modern client libraries.

Updated: 2025-12-04GitHub→

PreviousPage 377 of 760Next