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
High Cost
Amaculus icon
Sec9

Enables Claude to perform deep technical SEO analysis by querying crawl data, Google Search Console (GSC) metrics, and Google Analytics 4 (GA4) data from OnCrawl, facilitating crawl-over-crawl comparisons and identification of common SEO issues.

Setup Requirements

  • ⚠️Requires Python 3.11+.
  • ⚠️Requires an OnCrawl account with API access and a generated API token (with `projects:read` scope).
  • ⚠️The MCP server configuration in Claude Desktop/Code requires using an absolute file path for the `command` attribute (e.g., `C:\path\to\venv\Scripts\python.exe`).
  • ⚠️Claude Desktop/Code must be restarted after making configuration changes for the MCP server to be recognized.
Verified SafeView Analysis
The server securely handles API authentication via environment variables, avoiding hardcoded secrets. It utilizes `httpx` for reliable API communication and constructs OnCrawl Query Language (OQL) arguments as structured objects, minimizing the risk of injection vulnerabilities. There is no usage of `eval` or direct shell command execution with user-controlled input. Data parsing and manipulation are handled safely with Python's built-in `json` module. The server makes requests to a known external API (OnCrawl) and sets timeouts for requests.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
SDS-Manager icon

sds-mcp-server

by SDS-Manager

Sec6

This server provides a Model Context Protocol (MCP) interface to an SDS Manager backend, enabling an AI assistant to search, retrieve, upload, and manage Safety Data Sheets for regulatory compliance and organizational purposes.

Setup Requirements

  • ⚠️Requires a running Redis server for session management and temporary file handling.
  • ⚠️Requires a separate SDS Manager backend service to be running (defaults to http://localhost:8000/mcp).
  • ⚠️Requires an API key for the SDS Manager backend for authentication with its services.
Verified SafeView Analysis
The server directly processes user-uploaded Excel files via `pandas.read_excel`. This introduces a significant security risk, as specially crafted malicious Excel files could exploit vulnerabilities in the pandas library or underlying system. User API keys are stored in Redis in plain JSON, posing a risk if the Redis instance is compromised or not adequately secured. While file uploads for PDFs are proxied to the backend, the Excel file processing occurs directly on this server. There is no usage of `eval` or intentional obfuscation.
Updated: 2025-12-18GitHub→
0
0
Medium Cost
GalSened icon
Sec3

The WeSign MCP Server enables AI assistants to manage digital signature workflows, documents, templates, and user administration with the WeSign platform.

Setup Requirements

  • ⚠️Requires WeSign API credentials (email, password) and an API URL to be configured via environment variables.
  • ⚠️File operation tools (e.g., upload, download) expect absolute local file paths on the server's filesystem, which requires the AI assistant to manage server-side file access or provide Base64 content.
  • ⚠️For integration with remote AI platforms like ChatGPT, the server must be exposed publicly using tools like ngrok or cloud deployment.
Review RequiredView Analysis
The server has critical security vulnerabilities if exposed publicly. The `wesign_download_document` tool allows a user-controlled `savePath` parameter, enabling potential directory traversal and arbitrary file write if not rigorously sanitized by the AI. Similarly, `wesign_upload_document` and `wesign_create_document_collection` read local files via `filePath`, posing an information disclosure risk if an attacker can control this path. The `docker-compose.yml` and configuration guides contain real-looking example credentials ('nirk@comsign.co.il', 'Comsign1!'), which is a bad practice as users might deploy them directly. Debug logging in `wesign-client.ts` includes full request/response data, which could expose sensitive information (e.g., passwords in login requests) in logs during production if not properly redacted.
Updated: 2025-11-23GitHub→
0
0
Medium Cost
hightemp icon
Sec3

Enables AI agents to perform desktop automation by controlling the mouse, keyboard, screen, windows, and processes on a local computer system.

Setup Requirements

  • ⚠️Building from source requires Go 1.21+, a GCC compiler, and X11 development libraries (on Linux).
  • ⚠️Requires the `DISPLAY` environment variable to be set for all GUI operations on Linux, without which most tools will fail.
  • ⚠️The `npx` quick start command (npx -y go-computer-use-mcp-server -t stdio) requires Node.js 18+ and executes pre-compiled binaries downloaded from npm, requiring trust in the package publisher.
  • ⚠️The `screen_capture` tool can return very large base64 encoded PNG images (tens to hundreds of thousands of tokens), significantly increasing token costs for LLM clients if frequently used.
Review RequiredView Analysis
The `process_run` tool executes arbitrary shell commands provided as a string, posing a critical command injection vulnerability if the input is not fully trusted and sanitized by the client. All tools granting mouse, keyboard, screen, and window control are high-privilege operations. Deploying this server, particularly using `npx` (which downloads and executes pre-compiled binaries), demands complete trust in the source and robust client-side input validation. Binding the SSE transport to `0.0.0.0` or exposing it to untrusted networks creates a severe remote control risk.
Updated: 2026-01-17GitHub→
0
0
Medium Cost
hballington12 icon

mcp-oignon

by hballington12

Sec9

Facilitates exploration of academic literature and building citation networks using the OpenAlex API, primarily for AI agents to conduct research tasks and literature reviews.

Setup Requirements

  • ⚠️Requires an OpenAlex API email for optimal performance (increasing rate limits).
  • ⚠️Requires specific integration steps to add to an MCP-compatible client's configuration (e.g., Claude Desktop, Gemini CLI).
Verified SafeView Analysis
The server appropriately uses environment variables for API configuration (`OPENALEX_EMAIL`), avoiding hardcoded secrets. It defaults to safer `stdio` or `localhost` for HTTP transport, reducing external network attack surface. No direct use of dangerous functions like `eval()` or `subprocess.run(shell=True)` was observed. The use of `json.loads` is within the expected operational flow of an MCP server processing tool outputs.
Updated: 2026-01-18GitHub→
0
0
Medium Cost
taufiqur0991 icon

MCP-Server-CSharp

by taufiqur0991

Sec4

Provides a server application built with C# for general-purpose backend services.

Setup Requirements

  • ⚠️Requires .NET SDK (e.g., .NET 6 or 8) to build and run.
Review RequiredView Analysis
CRITICAL: No C# source code was provided for analysis. The 'SOURCE CODE' section only contained the readme.md content. Therefore, a comprehensive security audit for 'eval', obfuscation, hardcoded secrets, or malicious patterns could not be performed. The score reflects this inability to audit rather than specific findings.
Updated: 2025-12-02GitHub→
0
0
Low Cost
Samuel88 icon

mcp-server-test

by Samuel88

Sec8

This server provides a Model Context Protocol (MCP) endpoint to expose an addition tool and a greeting resource via HTTP.

Setup Requirements

  • ⚠️Node.js 18+ required
  • ⚠️npm or yarn required for dependency installation
Verified SafeView Analysis
The server uses Zod for schema validation which improves input safety. However, the CORS configuration (`origin: '*'`) allows requests from any domain, which might be overly permissive for production environments. The 'greeting' resource directly interpolates user-provided 'name' into its output, which, if rendered directly by a client-side application without sanitization, could lead to Cross-Site Scripting (XSS) vulnerabilities. No hardcoded secrets or 'eval' usage found.
Updated: 2025-11-25GitHub→
0
0
Low Cost

ask-anything-mcp

by villagemetrics

Sec7

An MCP server that bridges AI agents with Village Metrics behavioral tracking data and analytics through authenticated API calls.

Setup Requirements

  • ⚠️Requires a Village Metrics account with associated behavioral tracking data.
  • ⚠️Requires obtaining and securely configuring specific API tokens (VM_MCP_TOKEN or VM_AUTH_TOKEN) from the Village Metrics app.
  • ⚠️MCP server mode requires a compatible Model Context Protocol client (e.g., Claude Desktop).
Verified SafeView Analysis
The server makes authenticated API calls to Village Metrics, handling personal behavioral data. Security depends heavily on the secure handling and protection of `VM_MCP_TOKEN` and `VM_AUTH_TOKEN` (provided via .env.secrets.local), as compromise of these tokens could lead to unauthorized data access. The project itself does not show signs of malicious code like 'eval' or obfuscation.
Updated: 2025-11-17GitHub→
0
0
Medium Cost
Sec5

This system serves as a home automation and management platform, likely leveraging Ansible for deployment and control of devices, potentially including OpenWRT routers.

Setup Requirements

  • ⚠️Requires Ansible to be installed for deployment and management.
  • ⚠️Assumes or requires OpenWRT-compatible devices for full functionality.
  • ⚠️Configuration likely relies on environment variables as indicated by '.env.sample'.
  • ⚠️The absence of a functional 'README.md' (404 Not Found) is a critical friction point for understanding setup and usage.
Review RequiredView Analysis
Without code access, a full security audit is impossible. However, as a home automation and system administration tool managing network devices, it inherently involves sensitive configurations and network interactions. Misconfigurations could pose risks to the home network. The presence of prompt files suggests potential AI integration, which could have data privacy implications depending on implementation.
Updated: 2025-11-18GitHub→
0
0
Low Cost
ServiceNow icon

saai-skill-feedback

by ServiceNow

Sec8

Submit feedback about Claude Model Context Protocol (MCP) skills directly from conversations, creating ServiceNow SBOs for tracking.

Setup Requirements

  • ⚠️Requires Node.js 18+ and Python 3.8+ installed locally.
  • ⚠️Requires a ServiceNow account on `surf.service-now.com` with permissions to create SBOs in the `x_snc_security_d_0_dsrtable` table.
  • ⚠️Requires interactive browser-based authentication (Okta, MFA) during installation and potential re-authentication for session refresh, leveraging `selenium` and `webdriver-manager`. Safari automation requires `sudo safaridriver --enable`.
Verified SafeView Analysis
The server uses browser automation (Selenium) for initial ServiceNow authentication, caching session cookies and an X-UserToken locally in `~/.servicenow_surf_session.json`. While this is a common practice for internal tools, the security relies on the integrity of the local file and browser environment. Credentials can also be provided via environment variables. All network communication to ServiceNow is over HTTPS. `child_process.spawn` is used to execute Python scripts, but arguments are internally controlled and not directly user-provided, mitigating injection risks. No hardcoded sensitive secrets were found.
Updated: 2026-01-16GitHub→
0
0
Medium Cost
aoki-collabo icon

simple-hono-mcp-server

by aoki-collabo

Sec8

This server provides a simple Model Context Protocol (MCP) endpoint that offers a 'factorize' tool for positive integer factorization, primarily serving as a demonstration and educational example for deploying MCP servers on Cloudflare Workers using the Hono framework.

Setup Requirements

  • ⚠️Requires Node.js v18 or higher.
  • ⚠️A Cloudflare account is needed for deployment to Cloudflare Workers.
Verified SafeView Analysis
The server explicitly lacks authentication, a documented design choice for simplicity in a demo. This means any client can call the exposed tools, making it unsafe for production environments without adding robust authentication. However, input validation for the 'factorize' tool is implemented using zod, checking for integer type, positive value, and a maximum of 15 digits, which mitigates computational DoS attacks for the tool's logic.
Updated: 2026-01-17GitHub→
0
0
Medium Cost
1bluebird777 icon

manus-mcp-server

by 1bluebird777

Sec1

MCP server facilitating real-time development tasks for ElevenLabs' Leiah AI agent on the BluebirdX project, including booking and code interaction.

Setup Requirements

  • ⚠️Requires a specific directory structure on the host machine with a 'bluebird-x' project repository located at '/home/ubuntu/bluebird-x' for development tools to function correctly.
  • ⚠️Relies on an external 'BluebirdX API' (URL configurable via BLUEBIRD_API_URL) for booking and address validation, which must be running and accessible.
Review RequiredView Analysis
CRITICAL VULNERABILITIES: The `get_code_context` tool uses `execSync` with `grep -r "${query}"`. The `query` argument comes directly from the AI agent's input, making the server highly vulnerable to shell injection attacks. An attacker controlling the AI agent's prompts could execute arbitrary commands on the host system. Additionally, the `INTEGRATION_GUIDE.md` explicitly states 'No authentication' and 'No rate limiting' are implemented in the current setup, making the server openly accessible and susceptible to abuse. The `create_task` tool writes user-provided content (`title`, `description`) to files, which could potentially lead to path traversal or denial-of-service via large files if inputs are not properly sanitized. The `BLUEBIRD_API_URL` being configurable via an environment variable could expose the server to Server-Side Request Forgery (SSRF) if the variable is compromised. This server is not safe to run in its current state without significant security enhancements.
Updated: 2025-12-14GitHub→
PreviousPage 702 of 760Next