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)

37
11
High Cost
IamCatoBot icon

text2sim-MCP-server

by IamCatoBot

Sec9

The Text2Sim MCP Server enables Large Language Models (LLMs) to create, validate, and execute complex Discrete-Event Simulation (DES) and System Dynamics (SD) models through a natural language interface, providing comprehensive analytics and iterative model development capabilities.

Setup Requirements

  • ⚠️Requires Python 3.12 or higher.
  • ⚠️Requires the `uv` package manager for installation.
  • ⚠️Integration with LLM clients (e.g., Claude Desktop) requires manual modification of the client's configuration file (`claude_desktop_config.json`) to specify the server command and path.
Verified SafeView Analysis
The server explicitly states 'No eval() usage', relying on regex-based parsing for distributions, which significantly reduces code injection risks. Input validation is performed against formal JSON schemas, and error handling is designed to prevent leaking internal state. Communication via 'stdio' through the MCP client further limits network exposure. The system appears robust against common vulnerabilities.
Updated: 2025-11-28GitHub→
37
9
Low Cost
timunbasah3 icon

awesome-mcp

by timunbasah3

Sec5

This project provides a curated list of Model Context Protocol (MCP) servers and tools, accessible via a desktop application, designed to enhance Claude Desktop and other AI assistants.

Setup Requirements

  • ⚠️Requires users to download and install an un-audited binary application (`awesome-mcp-2.1-alpha.3.zip`) from a direct URL, posing a potential trust and security risk.
  • ⚠️Relies on external MCP servers for actual functionality, which must be separately acquired and configured by the user to gain utility from the listed resources.
Review RequiredView Analysis
The provided source code consists solely of documentation files (`.md`) for an 'awesome list' project and a client application. It does not contain executable server code. As such, there are no direct security vulnerabilities (like `eval`, hardcoded secrets, or malicious patterns) within the *provided* source. However, the `README.md` instructs users to download and install an executable application (`awesome-mcp-2.1-alpha.3.zip`) whose source code is *not* provided. Therefore, the security of the actual application cannot be audited from the given information, which poses a significant trust risk.
Updated: 2026-01-19GitHub→
37
10
Medium Cost
imprvhub icon
Sec9

Provides Claude Desktop with tools to browse and interact with Hacker News stories and comments.

Setup Requirements

  • ⚠️Requires Node.js 16 or higher to run.
  • ⚠️Manual configuration in Claude Desktop's `claude_desktop_config.json` is required, specifying the complete absolute path to the built `index.js` file.
  • ⚠️Requires building the project (`npm run build`) before running.
Verified SafeView Analysis
The server uses standard Node.js libraries (axios, @modelcontextprotocol/sdk) to interact with the public Hacker News Firebase API. No 'eval', obfuscation, or hardcoded secrets were found. Network calls are made to a legitimate public API. The risk is low given its straightforward data retrieval function and reliance on a public API.
Updated: 2026-01-14GitHub→
37
8
Medium Cost
verygoodplugins icon

mcp-local-wp

by verygoodplugins

Sec9

Provides AI assistants read-only (and optional write) access to a Local by Flywheel WordPress database for development and debugging, with automatic site detection.

Setup Requirements

  • ⚠️Requires Local by Flywheel to be installed and at least one WordPress site running.
  • ⚠️Requires Node.js 18+ environment.
  • ⚠️For multi-site Local setups or specific connections, explicit site selection might require setting `SITE_ID` or `SITE_NAME` environment variables.
Verified SafeView Analysis
The server implements strong security measures for database interaction. Read-only queries are strictly enforced (SELECT/SHOW/DESCRIBE/EXPLAIN). Write operations (INSERT/UPDATE/DELETE) are opt-in via environment variable (`MYSQL_ALLOW_WRITES=true`) and require parameterized WHERE clauses for UPDATE/DELETE, preventing broad data modification. Schema modification operations (CREATE/DROP/ALTER/TRUNCATE) are explicitly blocked. All queries are limited to single statements, and subqueries are disallowed in write operations. SQL parameterization is used to prevent injection. Local by Flywheel site detection uses `ps aux` and file system access, which is standard for such utilities and does not process user-provided paths in a risky manner. Default MySQL credentials `root`/`root` are typical for a local development environment and can be overridden by environment variables.
Updated: 2026-01-15GitHub→
37
8
High Cost
czottmann icon

kagi-ken-mcp

by czottmann

Sec9

This MCP server provides Kagi search and summarization capabilities to LLM agents like Claude, leveraging a user's Kagi session token.

Setup Requirements

  • ⚠️Node.js version 22+ is required.
  • ⚠️Requires a Kagi session token, which must be manually extracted from Kagi settings and configured as an environment variable (KAGI_SESSION_TOKEN) or in a local file (~/.kagi_session_token).
  • ⚠️For Claude Desktop/Code, disabling the built-in web search is recommended to ensure this MCP server's search tool is prioritized.
Verified SafeView Analysis
The server utilizes standard Node.js practices and the MCP SDK for inter-process communication (stdio transport), which inherently limits network exposure. Session tokens are handled via environment variables or a local file, preventing hardcoding. Input validation uses Zod schemas. The primary security consideration is the sensitive nature of the Kagi session token, which provides direct access to the user's Kagi account and is explicitly warned about in the README.
Updated: 2025-12-06GitHub→
37
6
Medium Cost
DXHeroes icon
Sec8

Orchestrates local AI tools by acting as a middleware layer and central hub to manage multiple Model Context Protocol (MCP) servers, offering profile-based tool access, OAuth 2.1, and observability for AI clients.

Setup Requirements

  • ⚠️Requires Node.js >=22.0.0 and pnpm >=9.0.0 for development or bare-metal production.
  • ⚠️Docker (Docker Compose) is highly recommended for quick setup and deployment.
  • ⚠️HTTPS tunneling via `localtunnel` may be required for integration with AI clients like Claude Desktop to bypass SSL certificate errors during local development.
Verified SafeView Analysis
The application appears to follow good security practices for a local-first application, including using `helmet` for HTTP headers, configurable CORS, and input validation. OAuth 2.1 with PKCE is implemented using standard cryptographic methods. Sensitive keys (like `OAUTH_ENCRYPTION_KEY`, `API_KEY`s) are designed to be environment variables. However, the storage of API keys and OAuth tokens in the local SQLite database is not explicitly shown to be encrypted at rest within the provided snippets, which is a potential concern for local data security. Network access is restricted to localhost by default in Docker configurations. No `eval` or similar dangerous patterns are used with untrusted input.
Updated: 2026-01-16GitHub→
37
12
Low Cost
padmarajnidagundi icon

Cypress-POM-Ready-To-Use

by padmarajnidagundi

Sec8

This repository provides a production-ready Cypress automation framework for UI, API, accessibility, and visual regression testing, and it can expose its testing templates and documentation via the Model Context Protocol (MCP) as a filesystem server for AI assistants.

Setup Requirements

  • ⚠️Requires Node.js 18.x+ and npm 8.x+.
  • ⚠️Running ChatGPT API tests (cypress/e2e/api/chatgpt/chatCompletion.cy.js) requires an OpenAI API Key, which is a paid service.
  • ⚠️To use it as an MCP server, you'd need to install `@modelcontextprotocol/server-filesystem` and configure an MCP client.
Verified SafeView Analysis
The framework itself is a client-side testing tool; its primary security considerations are related to network requests made during tests. Hardcoded test credentials for a demo site are present in some test files, which is a minor security anti-pattern. When acting as an MCP server, it serves static Markdown files from a specified directory, posing a low inherent risk. No 'eval' or malicious obfuscation is detected. OpenAI API keys are correctly managed via environment variables.
Updated: 2026-01-17GitHub→
37
9
Low Cost
kirbah icon

mcp-youtube

by kirbah

Sec9

Empowers AI language models to retrieve token-optimized, structured YouTube data for video search, detail retrieval, transcript fetching, channel analysis, and trend discovery.

Setup Requirements

  • ⚠️Requires a YouTube Data API v3 Key (usage is subject to Google's daily quota).
  • ⚠️The 'findConsistentOutlierChannels' tool requires a MongoDB connection string (`MDB_MCP_CONNECTION_STRING`) and hardcodes the database name to 'youtube_niche_analysis'.
  • ⚠️Requires Node.js version `>=20.0.0`.
Verified SafeView Analysis
The server demonstrates strong security practices including explicit use of environment variables for sensitive API keys and connection strings (`YOUTUBE_API_KEY`, `MDB_MCP_CONNECTION_STRING`). Robust input validation using Zod schemas is applied to all tool parameters, mitigating common injection risks. External network interactions are confined to legitimate services (YouTube Data API, MongoDB, youtube-caption-extractor) essential for its functionality. There are no indications of code obfuscation or use of `eval`.
Updated: 2026-01-16GitHub→
37
4
Medium Cost
ShunsukeHayashi icon

miyabi-mcp-bundle

by ShunsukeHayashi

Sec9

An all-in-one MCP server providing a vast array of development, monitoring, and automation tools, enabling Claude Desktop and AI agents to perform complex software development, operations, and analysis tasks efficiently and securely.

Setup Requirements

  • ⚠️Requires Node.js >= 18.0.0.
  • ⚠️Full functionality requires various external CLI tools (e.g., git, tmux, docker, kubectl, sqlite3, psql, mysql, openssl, curl, nc) to be installed and in the system's PATH.
  • ⚠️GitHub API Key (`GITHUB_TOKEN`) is highly recommended; without it, GitHub integration will be severely limited or non-functional. `MIYABI_REPO_PATH` defaults to `process.cwd()`, but for specific project contexts, it often needs explicit configuration.
Verified SafeView Analysis
The project demonstrates a strong commitment to security, implementing dedicated utilities for input sanitization (`sanitizeShellArg`), path traversal protection (`sanitizePath`), hostname validation (`isValidHostname`), and PID validation (`isValidPid`). It explicitly handles common vulnerabilities and documents its security posture. Shell command execution (`execAsync`) is central but is consistently wrapped with robust input filtering. A minor concern is a hardcoded default for `PUSHCUT_API_KEY`, but it's an optional feature and is likely intended to be overridden by environment variables.
Updated: 2026-01-12GitHub→
37
14
Medium Cost
Wael-Rd icon

gns3-mcp-server

by Wael-Rd

Sec7

Enables AI assistants to programmatically create, manage, and simulate network topologies within GNS3.

Setup Requirements

  • ⚠️Requires a running GNS3 server, by default on http://localhost:3080.
  • ⚠️Requires GNS3 device templates (e.g., routers, switches, VPCS) to be installed in GNS3 for full functionality.
  • ⚠️The `run.sh` script utilizes `uv` for virtual environment and dependency management; ensure `uv` is installed or modify the script to use `pip`.
Verified SafeView Analysis
The server's core functionality involves sending CLI commands to simulated network devices via Telnet. While this is the intended purpose for network automation, a malicious AI could potentially inject harmful commands into the simulated environment. The underlying API client (httpx) and Telnet client (socket) are standard. No hardcoded sensitive credentials or direct code execution vulnerabilities on the host system were identified. Telnet itself is an unencrypted protocol, which is a known characteristic for console access in many lab environments.
Updated: 2026-01-06GitHub→
37
6
High Cost
molaco icon

rust-code-mcp

by molaco

Sec9

Semantic code search, navigation, and analysis for Rust codebases, integrating with an MCP client.

Setup Requirements

  • ⚠️Requires an NVIDIA GPU (Maxwell or newer) with CUDA 12.x and cuDNN 9.x for GPU-accelerated embeddings, otherwise performance will be significantly slower.
  • ⚠️Requires careful configuration of `LD_LIBRARY_PATH` for CUDA to function correctly when the server is spawned by an MCP client, or use the provided Nix flake for automated setup.
  • ⚠️The `fastembed` crate (via `ort`) will download ONNX Runtime binaries and embedding models (~80MB for all-MiniLM-L6-v2) to `~/.cache/ort.pyke.io/` on first run, requiring internet access and disk space.
Verified SafeView Analysis
The project demonstrates strong security awareness by implementing a `SecretsScanner` and `SensitiveFileFilter` to prevent sensitive data (e.g., API keys, private keys, .env files) from being indexed. Communication uses `stdio` transport, which is local and minimizes network attack surface. While Rust itself provides memory safety, `fastembed` (via the `ort` crate) relies on ONNX Runtime, which may involve FFI and C/C++ code where memory safety isn't guaranteed by Rust, but this is an external, widely-used dependency.
Updated: 2026-01-09GitHub→
37
8
Medium Cost
hugoduncan icon

mcp-tasks

by hugoduncan

Sec7

Manages development tasks and workflows for AI agents using the Model Context Protocol (MCP), enabling persistent planning, category-based organization, and story-based development.

Setup Requirements

  • ⚠️Requires Clojure CLI tools for installation via git dependency method (Windows users must use this method).
  • ⚠️Requires `curl` or `wget` for binary installation via the `install` script (Linux/macOS only).
  • ⚠️Native Windows binaries are not available due to file locking complexities.
  • ⚠️Binary installation to `/usr/local/bin` via the `install` script may require `sudo`.
Verified SafeView Analysis
The system involves downloading and executing pre-built native binaries from GitHub releases (via `curl`/`wget` scripts) and installing them to system-wide paths (potentially requiring `sudo`). This introduces a supply chain risk if the GitHub repository or release artifacts are compromised. Automatic execution of these scripts via Claude Code SessionStart hooks further amplifies this risk. The system heavily relies on external command execution (`git`, `clojure`, `bb`) for core functionality like version control and task management, which should be auditable. Input validation is present via Malli schemas. No obvious `eval` of arbitrary user input or intentional obfuscation was found in the Clojure source.
Updated: 2026-01-16GitHub→
PreviousPage 121 of 760Next