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(8554)

0
0
Low Cost
LDTorres icon
Sec8

Provides real-time dollar exchange rates in Argentina via a Model Context Protocol (MCP) server.

Setup Requirements

  • ⚠️Requires pnpm package manager to install dependencies and run scripts.
Verified SafeView Analysis
The server fetches data from an external API (dolarapi.com), which introduces a dependency on an external service. However, there are no apparent code vulnerabilities such as 'eval' usage, obfuscation, hardcoded secrets, or direct malicious patterns in the provided source code. The external API call uses standard fetch, and the server communicates via stdio, not exposing a typical network interface directly.
Updated: 2025-11-25GitHub→
0
0
Medium Cost
9506hqwy icon
Sec9

Provides a Model Context Protocol (MCP) server that exposes SonarQube API functionalities, allowing external tools, such as AI agents, to interact with and manage SonarQube instances.

Setup Requirements

  • ⚠️Requires a running SonarQube server to connect to.
  • ⚠️Requires valid SonarQube API credentials (token or username/password) with appropriate permissions for the desired operations.
  • ⚠️Building from source requires Go (version not specified, but typically recent stable), while running pre-built images requires Docker.
Verified SafeView Analysis
The server acts as a proxy for SonarQube APIs. It is implemented in Go, following standard coding practices. Credentials (URL, username, password, token) are handled at runtime via command-line flags or environment variables and are not hardcoded. It supports both basic and bearer token authentication. A 'readonly' flag is available (defaulting to true) to restrict operations to HTTP GET methods only, enhancing security by preventing write operations. The server itself does not introduce complex parsing or arbitrary code execution risks. The primary security considerations depend on the trustworthiness of the SonarQube instance it connects to and the secure management of the credentials provided to this server.
Updated: 2025-12-08GitHub→
0
0
Low Cost
Ifrazahoor icon

GeminiMcpServer

by Ifrazahoor

Sec1

The provided source code is a GitHub profile markdown file, not an MCP server. Cannot determine the server's use case.

Setup Requirements

  • ⚠️Actual server source code for 'GeminiMcpServer' is missing and only a GitHub profile markdown file was provided.
Review RequiredView Analysis
The provided 'SOURCE CODE' only contains a GitHub profile markdown file (`ifrazahoor.md`) and no actual server code for 'GeminiMcpServer'. Therefore, a security audit of the server itself is not possible. The markdown file itself contains no executable code or inherent security risks, but the server's actual security posture is completely unknown.
Updated: 2025-12-05GitHub→
0
0
High Cost
BigBang142 icon

Tor-Search-MCP

by BigBang142

Sec8

Browse the web and search anonymously using the Tor network, fetching full page content from search results or specific URLs while maintaining privacy.

Setup Requirements

  • ⚠️Requires Python 3.11+.
  • ⚠️Requires Tor Browser to be installed and its profile initialized (the installer attempts to automate this, but a manual launch of Tor Browser might be necessary once).
  • ⚠️On Linux, for headless execution (without a graphical display), `pyvirtualdisplay` and `xvfb` must be installed (e.g., `pip install pyvirtualdisplay && sudo apt-get install xvfb`).
Verified SafeView Analysis
The server and installer use `subprocess.run` to manage the Python virtual environment, install dependencies, and interact with external browser automation tools (Tor Browser, geckodriver). These binaries are downloaded from official and trusted sources. No 'eval', hardcoded secrets, or obvious malicious patterns were found in the provided source code. The security largely depends on the integrity of the downloaded Tor Browser and geckodriver binaries and the underlying operating system.
Updated: 2026-01-19GitHub→
0
0
Low Cost
iamthite icon
Sec9

Provides basic arithmetic operations and random number generation via a simple API.

Setup Requirements

  • ⚠️Requires Python 3.14 or higher
Verified SafeView Analysis
The server's code is minimal and performs only basic, contained operations (addition, random number generation, self-info). There are no external dependencies beyond standard library functions, no file system access, no 'eval' or other dynamic code execution, and no hardcoded secrets. The operations are inherently safe. Running on 0.0.0.0 makes it accessible from all interfaces, which is a standard deployment configuration, but requires proper network isolation in a production environment; however, this is an infrastructure concern, not a code vulnerability.
Updated: 2025-12-14GitHub→
0
0
Medium Cost
robertalv icon

loops-mcp-server

by robertalv

Sec9

Integrate Loops.so email marketing API into MCP-compatible clients like Claude Desktop, Cursor, or VS Code to manage contacts, send events, and transactional emails.

Setup Requirements

  • ⚠️Requires a Loops.so API Key (obtained from your Loops.so account settings)
  • ⚠️Requires Node.js version 18.0.0 or higher
  • ⚠️Requires an MCP-compatible client (e.g., Claude Desktop, Cursor, VS Code with MCP extension) for interaction
Verified SafeView Analysis
The server correctly retrieves the LOOPS_API_KEY from environment variables, preventing hardcoding. It uses standard fetch for API calls and handles errors gracefully. It operates over stdio, mitigating typical network attack vectors for the server itself. No 'eval' or other inherently dangerous functions are used. The primary security consideration for users is ensuring their LOOPS_API_KEY is stored securely in their environment.
Updated: 2025-11-26GitHub→
0
0
Medium Cost
danielsaban icon
Sec7

Manages Italian city data through CRUD operations, exposing these capabilities as tools for AI assistants via an MCP server.

Setup Requirements

  • ⚠️Requires Docker & Docker Compose for full setup (Elasticsearch and CRUD API).
  • ⚠️Requires Node.js 20+.
  • ⚠️The MCP server depends on the CRUD API server being actively running.
Verified SafeView Analysis
The Elasticsearch instance, as configured in `docker-compose.yml`, has security disabled (`xpack.security.enabled=false`), which is highly insecure for production environments. Additionally, the CRUD API uses `cors()` without specific origin restrictions, posing a risk if exposed publicly. Input validation is present for city names. For local development and use with Claude Desktop, these are generally acceptable, but require hardening for any public deployment.
Updated: 2025-12-14GitHub→
0
0
Low Cost
AmrKhater0011 icon

devops_server

by AmrKhater0011

Sec6

An end-to-end example project showcasing automated software deployment of a full-stack server application.

Setup Requirements

  • ⚠️Requires a PostgreSQL database instance.
  • ⚠️Requires a NATS server instance for messaging.
  • ⚠️Requires a Discord webhook URL for notifications.
  • ⚠️Requires Google Cloud credentials and a bucket for database backups.
Review RequiredView Analysis
The server uses parameterized queries for database interactions, preventing common SQL injection. However, it relies heavily on environment variables for sensitive data (DB credentials, Discord webhook, GCP credentials) which must be securely managed externally. Potential for Server-Side Request Forgery (SSRF) exists if 'IMAGE_SOURCE_URL' in server.js can be manipulated by an attacker, as it fetches an image from this URL without apparent validation. User-provided content for todos is sent to NATS and then to Discord via a webhook without explicit sanitization, posing a risk for content injection or abuse of Discord's markdown/commands.
Updated: 2026-01-19GitHub→
0
0
High Cost
zhiqiangwang4 icon

MCPTox-Benchmark

by zhiqiangwang4

Sec1

This server provides a collection of intentionally vulnerable and manipulated tool definitions designed for benchmarking and testing the security robustness of AI agents or systems interacting with diverse external services.

Setup Requirements

  • ⚠️Extreme Security Risk: Running this server will intentionally execute malicious operations, leading to severe data loss, privacy breaches, and infrastructure damage on the system it operates on or interacts with. This is not a benign benchmark.
  • ⚠️Requires Access to Sensitive System Resources: Many tools attempt to read/write critical system files (/etc/passwd, ~/.ssh/id_rsa) or perform network exfiltration, requiring elevated permissions and access to external services (file system, network, browser, various APIs like GitHub, Slack, etc.).
  • ⚠️Complex Malicious Chain Dependencies: The 'Template-1' and 'Template-2' paradigms enforce specific pre-conditions that must be met (often involving another malicious action) before the primary tool can even be called, making interaction and analysis complex.
Review RequiredView Analysis
The server's core functionality is to define and execute malicious operations across various domains. Risks include extensive credential leakage (e.g., overwriting SSH keys, reading /etc/passwd), severe infrastructure damage (e.g., deleting critical files, database resets), pervasive information manipulation and hijacking (e.g., redirecting search queries, altering content, forcing incorrect data), rampant code injection (e.g., injecting keyloggers, malware downloads, SQL injection), and service disruption (e.g., forcing failures, resource exhaustion). Pre-conditions for many tools involve destructive or privacy-violating actions, often exfiltrating sensitive data to attacker-controlled domains (e.g., 'attacker.com', 'evil.com').
Updated: 2025-12-03GitHub→
0
0
Low Cost
nbjoin icon
Sec2

Provides AI-powered tools and knowledge base services for 3D printing assistance, including G-code analysis, troubleshooting, and settings optimization for FlashForge printers.

Setup Requirements

  • ⚠️Implicit dependency on 'better-sqlite3' for the 'knowledge-base' server, which is a native Node.js module and often requires system-level build tools (e.g., Python, C++ compiler) to be installed for 'npm install' to succeed.
  • ⚠️Requires integration into the Model Context Protocol (MCP) ecosystem (e.g., via VS Code extension) as these are not standalone web services.
Review RequiredView Analysis
The `gcode-analyzer` MCP server (`src/mcp-servers/gcode-analyzer/server.js`) directly uses user-provided file paths in `fs.readFileSync` without validation, enabling arbitrary file reads on the host system. This is a critical security vulnerability. Additionally, the CLI interface for `src/tools/model-analyzer.js` has a similar vulnerability if exposed directly.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
isakskogstad icon

svt-texttv-mcp

by isakskogstad

Sec9

Access Swedish teletext content (news, sports, weather, TV schedules) from SVT Text-TV via the Model Context Protocol.

Setup Requirements

  • ⚠️Requires Node.js 18.0.0 or higher.
Verified SafeView Analysis
The server primarily provides read-only access to public Text-TV data. Input is strictly validated using Zod schemas, mitigating common injection risks. No direct usage of 'eval' or other dangerous dynamic code execution patterns was found. There are no hardcoded secrets beyond a public application ID. The HTTP server uses permissive CORS ('Access-Control-Allow-Origin: *'), which is common for public APIs and not a vulnerability for this read-only service. The main external dependency is an unofficial API (texttv.nu), so its reliability and security are external factors, but the server handles its usage robustly.
Updated: 2025-12-02GitHub→
0
0
Low Cost
yukihito-jokyu icon

mysql-mcp-server

by yukihito-jokyu

Sec9

A Model Context Protocol (MCP) server providing read-only access to MySQL database schema information and sample data for LLM agents or backend development.

Setup Requirements

  • ⚠️Requires a running MySQL database.
  • ⚠️The default MySQL port in the CLI options is `8080`, which is uncommon for MySQL (typically `3306`). Users must explicitly set `--port 3306` or use a correct port for their MySQL instance.
Verified SafeView Analysis
The server is explicitly designed for read-only operations, preventing any data modification (INSERT, UPDATE, DELETE). It uses parameterized queries (e.g., `DESCRIBE ??`, `SELECT * FROM ?? LIMIT 5`) in `src/lib/database.ts` to prevent SQL injection for table names. Database credentials are passed via CLI arguments, which is less secure than environment variables for highly sensitive production environments but is a common pattern for local MCP client configurations.
Updated: 2025-11-21GitHub→
PreviousPage 552 of 713Next