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)

30
1
Low Cost
henkisdabro icon
Sec9

Optimizes Claude Code context windows by interactively enabling/disabling MCP servers and managing plugins through a TUI or CLI.

Setup Requirements

  • ⚠️Requires Node.js 20 or later.
  • ⚠️Changes made while Claude Code is running will only take effect on the next session restart (exit Claude Code before running 'mcp' for immediate effect).
  • ⚠️For VSCode's integrated terminal on macOS, set `"terminal.integrated.macOptionIsMeta": true` for single-press Option key shortcuts.
Verified SafeView Analysis
The project demonstrates robust security practices for its domain, including atomic writes, automatic backups, and file locking to prevent configuration corruption during file system operations. External command execution (`claude mcp list`, `claude` binary launch) is central to its functionality, with command arguments passed through by the user. Input validation for adding new servers (`!/^[a-zA-Z0-9_-]+$/.test(name)`) mitigates potential command injection risks for server names. Plugin installation fetches from local marketplace directories, not arbitrary network URLs. No hardcoded secrets or 'eval' usage are present. The primary security considerations are the integrity of the Claude Code CLI and the user's system environment.
Updated: 2026-01-09GitHub→
30
1
High Cost
dgaida icon

PyADM1ODE

by dgaida

Sec6

Framework for modeling, simulating, and optimizing agricultural biogas plants based on the Anaerobic Digestion Model No. 1 (ADM1).

Setup Requirements

  • ⚠️Requires Mono runtime (on Linux/macOS) or .NET Framework (on Windows) for C# DLL interaction.
  • ⚠️Requires the `pythonnet` library for Python-C# interoperability, which may have specific installation requirements (e.g., `vs2015_runtime` on Windows).
  • ⚠️Initial ADM1 state for digesters must typically be provided via a CSV file (e.g., `data/initial_states/digester_initial8.csv`).
Review RequiredView Analysis
The project relies on `pythonnet` to interact with C# DLLs (`substrates.dll`, `biogas.dll`, `plant.dll`, `physchem.dll`). While these DLLs are included in the repository's `dlls/` directory (mitigating risk from arbitrary external downloads), they are opaque binary components that cannot be easily audited within the Python ecosystem. This introduces a significant trust dependency on the pre-compiled C# code. If these DLLs were compromised or maliciously altered, they could execute arbitrary code on the host system. The broader project context also mentions an 'MCP server for LLM integration', which, if implemented without stringent input validation and sandboxing, could present further remote code execution vulnerabilities.
Updated: 2026-01-11GitHub→
30
1
Low Cost
my-mcp-hub icon

node-mcp-server

by my-mcp-hub

Sec8

A template for building Model Context Protocol (MCP) compatible servers with support for multiple transport protocols like HTTP, SSE, and standard I/O.

Verified SafeView Analysis
The server uses Fastify, a robust web framework. Input validation for tools is implemented using Zod, which is a good practice for type safety and preventing unexpected data. Session IDs are generated using nanoid. By default, CORS is configured to allow all origins, which is typical for a template but should be restricted in a production environment to prevent cross-origin attacks. No direct 'eval' or obvious command injection vulnerabilities were found without proper sanitization.
Updated: 2026-01-15GitHub→
30
1
Low Cost
zerob13 icon

slidev-mcp

by zerob13

Sec1

An AI-powered server designed to generate and manage Slidev presentation slides and projects.

Setup Requirements

  • ⚠️Requires Node.js runtime environment.
  • ⚠️Utilizes pnpm for package management; other package managers might not work seamlessly.
  • ⚠️The core 'AI content generation' features advertised in the README (e.g., generating presentation content, slide content) are implemented with deterministic templating logic in the provided source code, not actual calls to an external AI/LLM model. Users expecting true AI-driven prose generation would need to integrate their own LLM API.
  • ⚠️Requires the `npx` command to be available for template initialization, which typically comes with npm.
Review RequiredView Analysis
CRITICAL: The `create-slidev-project` tool is highly vulnerable to command injection and path traversal. The `projectPath` argument, which comes directly from user input, is used unsanitized in `node:child_process.exec` (via `npx degit ... "${projectPath}"`) and `node:fs` operations. An attacker could inject arbitrary shell commands (e.g., `$(rm -rf /)` or remote code execution payloads) by manipulating `projectPath`. Additionally, path traversal with `../../` could lead to arbitrary file overwrites or creation outside the intended project directory.
Updated: 2026-01-15GitHub→
30
1
Low Cost
Jing-yilin icon

linkedin-mcp-server

by Jing-yilin

Sec3

Provides a Model Context Protocol (MCP) server for accessing LinkedIn data via the HarvestAPI service.

Setup Requirements

  • ⚠️Requires a HarvestAPI API key (HARVESTAPI_API_KEY or LINKEDIN_API_KEY environment variable is mandatory, HarvestAPI is a paid service).
  • ⚠️Requires Node.js version 18.0.0 or higher.
  • ⚠️Requires a TypeScript build step (`npm run build`) before execution.
Review RequiredView Analysis
The server has a critical path traversal vulnerability. The `save_dir` parameter, available in most tools, takes an unsanitized string which is then used in `fs.writeFileSync(path.join(dir, filename))`. An attacker or malicious LLM prompt could provide a `save_dir` like `../../../../../tmp` to write files to arbitrary locations on the host system, potentially leading to data corruption, information disclosure, or even remote code execution if combined with writing an executable file to a known execution path.
Updated: 2026-01-10GitHub→
30
1
Medium Cost
schornio icon
Sec3

This server provides a collection of example Model Context Protocol (MCP) servers, demonstrating integration with various external data sources and smart home devices (Philips HUE, Austrian public data like Linz Innovationshaupplatz, klimaaktiv funding, Firmenbuch, and legal texts).

Setup Requirements

  • ⚠️Requires Node.js and npm/npx to run.
  • ⚠️The 'Firmenbuch' example requires a `FIRMENBUCH_API_KEY` which must be obtained from 'justizonline.gv.at' (might require registration).
  • ⚠️The 'Philips HUE' example requires `PHILIPS_HUE_BRIDGE_ADDRESS`, `PHILIPS_HUE_API_KEY`, and `PHILIPS_HUE_LIGHT_IDS`. An initialization script (`npm run philips-hue:init`) is provided to help acquire these, but it requires physical interaction with the Philips HUE Bridge (pressing a button).
  • ⚠️The Philips HUE example has a critical security vulnerability due to disabling TLS certificate validation (`rejectUnauthorized: false`), making it unsafe for use in untrusted network environments.
Review RequiredView Analysis
The Philips HUE example (`examples/philips-hue/fetchHUE.ts`) explicitly sets `rejectUnauthorized: false` for its `undici` agent. This critically disables SSL/TLS certificate validation for connections to the Philips HUE bridge. While possibly intended for local networks or specific development setups where self-signed certificates might be used, this practice opens the connection to Man-in-the-Middle (MITM) attacks. An attacker on the local network could easily intercept or alter communication with the Hue Bridge. This is a severe security flaw for any network communication. Additionally, the server depends on API keys (Firmenbuch, Philips HUE) passed via environment variables, which is a good practice, but the overall lack of robust input sanitization beyond `zod` schemas (which validate structure but not necessarily malicious content for external systems) could be a concern if the external APIs are untrusted.
Updated: 2025-12-10GitHub→
30
1
Medium Cost
brainbloodbarrier icon

3dslicer-claude-bridge

by brainbloodbarrier

Sec6

Provides Claude Code with programmatic access to 3D Slicer for AI-assisted medical image analysis, surgical planning, and radiomics research.

Setup Requirements

  • ⚠️Requires 3D Slicer 5.0+ with the WebServer extension installed and running on localhost:2016.
  • ⚠️For full functionality, may require additional 3D Slicer extensions (e.g., HD-BET, SwissSkullStripper).
  • ⚠️Intended for localhost-only use; not suitable for production, clinical data, or remote access due to lack of authentication/encryption and arbitrary code execution capabilities.
  • ⚠️Installation requires `uv` package manager and specific configuration in `~/.claude/mcp.json`.
Verified SafeView Analysis
The server includes an `execute_python` tool that allows execution of arbitrary Python code in 3D Slicer's environment. This is a critical security risk if misused or deployed in an untrusted environment. However, the project explicitly states it is an 'educational/research tool for localhost use only' and 'not suitable for clinical data or production environments'. Input validation is robustly implemented for other tools to prevent common injection attacks. Audit logging for `execute_python` calls is present but for traceability, not enforcement. No hardcoded secrets were found.
Updated: 2026-01-10GitHub→
30
1
High Cost
joe-watkins icon

axecore-mcp-server

by joe-watkins

Sec8

Performs automated accessibility testing on URLs or raw HTML content using axe-core and IBM Equal Access engines, supporting multi-screen analysis and configurable WCAG levels.

Setup Requirements

  • ⚠️Requires Node.js (version 18 or higher is recommended by dependencies).
  • ⚠️Relies on Playwright to automatically download and manage Chromium browser binaries during installation and runtime.
Verified SafeView Analysis
The server uses Playwright to launch a headless browser for testing arbitrary URLs or HTML content. While Playwright provides process isolation, interacting with unverified external web content carries inherent risks of browser-level exploits or resource exhaustion (mitigated by navigation timeouts). The server's own code does not show signs of hardcoded secrets, `eval()` of untrusted input, or direct command injection vulnerabilities. Configuration is managed securely via environment variables.
Updated: 2025-12-07GitHub→
30
1
Low Cost
nentgroup icon

viaplay-mcp-test

by nentgroup

Sec8

This MCP server enables AI assistants to search the Viaplay catalog for movies and series and retrieve device key information.

Setup Requirements

  • ⚠️Node.js version 22.14.0 or higher is required.
  • ⚠️The 'run_command' provided in 'mcp.json' uses an absolute path ('/Users/raphport/Documents/GitHub/viaplay-mcp/dist/index.js') which must be updated by the user to reflect their local repository location.
Verified SafeView Analysis
The server code is small and clear, using Zod for parameter validation and making HTTP requests to a specific, known third-party API. No 'eval' or obfuscation found. No hardcoded sensitive secrets are present. The only network risk involves standard API calls to Viaplay's public content API.
Updated: 2026-01-19GitHub→
30
1
Low Cost
imnotowann icon

Windsurf-Tool

by imnotowann

Sec4

Manages Windsurf accounts, including batch registration, automated switching, and account pool management.

Setup Requirements

  • ⚠️Requires Cloudflare Email Routing to be configured for custom domain email reception.
  • ⚠️IMAP email configuration requires specific server details and often app-specific passwords/authorization codes for common providers, which users need to generate outside the application.
  • ⚠️On Windows, `robotjs` (for keyboard automation) requires Visual Studio Build Tools and Python for compilation, which can be a significant setup hurdle.
  • ⚠️On macOS, the application is unsigned and requires a security bypass (right-click 'Open' or a terminal command) on first run.
Review RequiredView Analysis
The `EmailReceiver` module uses `tlsOptions: { rejectUnauthorized: false }` when connecting to IMAP servers, which disables SSL/TLS certificate validation. This is a critical security vulnerability that makes IMAP connections susceptible to Man-in-the-Middle (MITM) attacks, allowing an attacker to intercept and read sensitive email credentials and verification codes. Additionally, the application utilizes `child_process.exec` (including PowerShell commands on Windows and AppleScript on macOS) and `robotjs` for system-level automation (e.g., closing applications, deleting configuration files, simulating keyboard input). While intended for the application's stated purpose, this level of control inherently carries a high risk if the application itself were compromised or if malicious input were somehow introduced, potentially leading to unauthorized system manipulation or data loss. There are no obvious hardcoded secrets or direct obfuscation found.
Updated: 2025-12-15GitHub→
30
1
High Cost
ariunbolor icon

nsaf-mcp-server

by ariunbolor

Sec3

The NSAF Complete MCP Server implements a Neuro-Symbolic Autonomy Framework, exposing 19 tools for AI assistants to manage complex multi-objective tasks, evolve specialized AI agents, project future intentions, manage symbolic memory, synchronize human-AI cognitive states, integrate foundation models, and perform real-time system analytics, potentially with quantum enhancement.

Setup Requirements

  • ⚠️Requires OpenAI API Key (Paid) and potentially Google Gemini API Key for Foundation Models. These are configured via environment variables.
  • ⚠️Critical environment variables (e.g., `AGENT_BUILDER_SECURITY_JWT_SECRET_KEY`, `ADMIN_PASSWORD`) must be set to override insecure hardcoded defaults, especially for JWT secret and admin credentials.
  • ⚠️Marketplace and user data defaults to local JSON file storage (`data/marketplace/*.json`, `data/users.json`), which is not scalable or secure for production and requires proper database setup (e.g., PostgreSQL, Redis).
  • ⚠️Uses Qiskit for quantum symbolic computing and TensorFlow for SCMA, which may require specific setup or dependencies.
  • ⚠️The server relies on FastAPI and Uvicorn; while Python packages, they are core framework dependencies.
Review RequiredView Analysis
The server has critical security vulnerabilities: it uses hardcoded default values for `JWT_SECRET_KEY` ('supersecretkey') and `admin` credentials if corresponding environment variables (`AGENT_BUILDER_SECURITY_JWT_SECRET_KEY`, `ADMIN_USERNAME`, `ADMIN_PASSWORD`) are not set. The agent marketplace and user data are stored in local JSON files (`data/marketplace/*.json`, `data/users.json`), which is highly insecure and unsuitable for a multi-user or production environment. System maintenance skills include `subprocess` calls (e.g., for system info, software management) which, while currently mocked in snippets, pose a risk if not rigorously sanitized and executed with least privilege.
Updated: 2025-11-26GitHub→
30
1
Medium Cost
jussker icon
Sec8

The server provides access to Context7 API for searching and downloading library documentation and source code repositories, and managing them locally.

Setup Requirements

  • ⚠️Requires Python 3.10+.
  • ⚠️Relies on the external Context7 API (context7.com) which may have its own usage limits or costs.
  • ⚠️The project explicitly states 'as-is' with 'no maintenance commitment', which is a significant factor for production use.
  • ⚠️CLIENT_IP_ENCRYPTION_KEY should be set to a unique, secret value in production to ensure client IP obfuscation is effective beyond simple obscurity.
Verified SafeView Analysis
The default CLIENT_IP_ENCRYPTION_KEY is hardcoded and publicly available, meaning IP addresses 'encrypted' with this default key are not truly confidential. While configurable, users should be aware of this for production environments. The server executes `git clone` commands based on repository URLs extracted from documentation fetched from an external API (context7.com), which introduces a trust dependency on the external API not providing malicious URLs. File system operations are generally scoped to a specific `.kms/context7/km-base` directory.
Updated: 2026-01-19GitHub→
PreviousPage 228 of 760Next