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
Medium Cost
jeanlopezxyz icon

mcp-prometheus

by jeanlopezxyz

Sec9

MCP Server for Prometheus monitoring, enabling AI assistants to query metrics, analyze trends, and monitor infrastructure health.

Setup Requirements

  • ⚠️Requires Java 21+
  • ⚠️Requires a running Prometheus instance accessible from the server
Verified SafeView Analysis
The server uses standard Quarkus/MicroProfile REST client for Prometheus API interactions, handling PromQL queries as parameters. It securely retrieves Kubernetes ServiceAccount tokens for authentication within a cluster if available. The npm CLI downloads the JAR from GitHub releases via HTTPS. No obvious 'eval' or malicious patterns were found. The primary security risk would be the PromQL queries themselves if they are resource-intensive for the Prometheus server, but the MCP server acts as a secure proxy.
Updated: 2025-12-10GitHub→
0
0
Medium Cost
gebl icon
Sec9

Seamless integration of AI assistants with Microsoft OneNote for knowledge management and content organization via the Model Context Protocol (MCP).

Setup Requirements

  • ⚠️Requires Microsoft Azure App Registration with 'Notes.ReadWrite' delegated API permissions and a configured redirect URI.
  • ⚠️Requires Go 1.21+ for local development or Docker Engine for containerized deployment.
  • ⚠️OAuth 2.0 PKCE authentication flow requires a one-time browser interaction for initial setup or re-authentication.
Verified SafeView Analysis
The project transparently highlights security risks related to AI agents autonomously modifying data and Microsoft Graph API limitations. It implements a 'Notebook-Scoped Authorization' system as an AI safety guardrail with a 'Default-Deny Security Model', preventing cross-notebook access and enforcing permissions. Authentication uses secure OAuth 2.0 PKCE. Sensitive configuration data was purged from Git history, and best practices for secret management are documented. The code does not appear to contain 'eval', obfuscation, or other malicious patterns, focusing on robust and secure integration with OneNote.
Updated: 2025-12-22GitHub→
0
0
High Cost
Aldiharley icon

secpluger

by Aldiharley

Sec6

Automates multi-step penetration testing workflows, including reconnaissance, vulnerability scanning, exploitation, and reporting, with AI orchestration and evidence collection.

Setup Requirements

  • ⚠️Requires installation of numerous external security tools (e.g., Nmap, Gobuster, SQLMap, Nuclei, Nikto, tshark, mitmproxy, hydra, rustscan, playwright).
  • ⚠️Many tools require root/sudo privileges or specific user permissions (e.g., tshark/Wireshark requires adding user to 'wireshark' group and setting dumpcap permissions).
  • ⚠️BurpSuite integration requires BurpSuite Professional and 'burp-rest-api' running separately.
  • ⚠️Screenshot capture requires Playwright to be installed and browser binaries downloaded ('playwright install chromium').
  • ⚠️Optimal functionality may require an NVD API key for comprehensive CVE lookups.
Review RequiredView Analysis
The server's core function involves executing external security tools and exploits, often using 'subprocess.run(shell=True)' with dynamically constructed commands. While designed for offensive security, this poses a risk of shell injection or arbitrary command execution on the host machine if workflow JSON files or user-provided inputs (e.g., target URLs, parameters) are manipulated by untrusted sources or contain unexpected metacharacters. Strong sandboxing/isolation of the server is highly recommended.
Updated: 2025-12-04GitHub→
0
0
Low Cost
Sec8

A frontend web application for training or demonstrating content, possibly video reels.

Setup Requirements

  • ⚠️Node.js (LTS recommended) is required
  • ⚠️Dependencies must be installed using a package manager (e.g., 'npm install' or 'yarn install')
Verified SafeView Analysis
This is a standard client-side web application project setup with Vite and TypeScript. The presence of ESLint suggests good coding practices. Without source code, it's difficult to identify specific vulnerabilities like XSS or unsafe third-party dependencies, but there are no obvious direct server-side risks from the file list alone.
Updated: 2025-11-18GitHub→
0
0
Medium Cost

mcp-server

by charlesdassonville

Sec5

Acts as a generic server application, its specific purpose cannot be determined without source code.

Review RequiredView Analysis
No source code was provided for analysis, therefore a thorough security audit is impossible. The score is a placeholder reflecting the inability to verify safety or identify risks. There is no evidence of 'eval' or other dangerous patterns because no code was available to review.
Updated: 2025-11-25GitHub→
0
0
Low Cost
deb-sahu icon
Sec8

A generic template for building Model Context Protocol (MCP) servers with a modular architecture for plug-and-play business logic.

Setup Requirements

  • ⚠️Requires Poetry for local development
  • ⚠️Requires Python 3.10+
  • ⚠️Example tools must be replaced with your custom business logic for actual use cases
Verified SafeView Analysis
The core infrastructure (Docker, Kubernetes readiness, non-root user, environment variable configuration) exhibits strong security practices. However, the `http_tools.py` example demonstrates making HTTP requests to arbitrary URLs (`fetch_api_data`). If this tool is exposed in the custom business logic without proper input validation or network controls, it could introduce Server-Side Request Forgery (SSRF) vulnerabilities. Developers should implement strict URL validation and whitelist/blacklist mechanisms when using or extending such HTTP capabilities.
Updated: 2025-11-26GitHub→
0
0
High Cost
Avidan87 icon

MCP-SERVER

by Avidan87

Sec9

Estimates food portion sizes from images using depth estimation for a KAI agent, focusing on Nigerian cuisine.

Setup Requirements

  • ⚠️Initial Docker build can take 15-20 minutes due to the Depth Anything V2 model download (~100MB).
  • ⚠️Warm inference on CPU (e.g., Railway serverless) can take 30-60 seconds per request, leading to long response times and high CPU-hour consumption.
Verified SafeView Analysis
The server uses standard practices for FastAPI and ML model loading. `subprocess.run` is used in the startup script but with well-defined, non-user-controlled arguments. CORS is set to `allow_origins=["*"]`, which is broad but common for internal microservices; for a publicly exposed API, this might be overly permissive depending on the specific threat model. No hardcoded secrets or 'eval' statements were found.
Updated: 2026-01-13GitHub→
0
0
High Cost
Lapeno01 icon

crypto-mcp

by Lapeno01

Sec9

A Model Context Protocol (MCP) server for tracking cryptocurrency prices and market data using the CoinMarketCap API.

Setup Requirements

  • ⚠️Requires a free CoinMarketCap API key (CMC_API_KEY).
  • ⚠️Python 3.11 is the specified environment version.
  • ⚠️Utilizes a Conda environment for setup, requiring Conda to be installed.
Verified SafeView Analysis
The server securely handles the CoinMarketCap API key by loading it from an environment variable (`.env` file) and explicitly checking for its presence and a placeholder value. All external API calls are wrapped in robust error handling. No 'eval' or other directly dangerous patterns are present. The primary security consideration is ensuring the `CMC_API_KEY` remains confidential, which is a standard requirement for API-driven applications.
Updated: 2025-11-18GitHub→
0
0
Low Cost
Tom687 icon
Sec1

An Electron desktop application demonstrating context bridge communication between renderer and main processes, allowing the execution of system commands from the renderer.

Setup Requirements

  • ⚠️Requires Electron to be installed or downloaded via npx.
Review RequiredView Analysis
CRITICAL RISK: The application exposes an 'executeCommand' function via the context bridge, allowing the renderer process (and thus potentially untrusted web content via an input field) to execute arbitrary system commands on the host machine using `child_process.exec`. This is a severe remote code execution vulnerability, allowing any user of the application to execute any command on their system. The `executeMCPCommand` function is also dangerous, as it executes commands with `mc-p` prefix, which could still lead to unintended system changes or exploits depending on what `mc-p` is.
Updated: 2025-11-29GitHub→
0
0
Low Cost
tjwio icon
Sec7

Deploys a remote Model Context Protocol (MCP) server on Cloudflare Workers, offering authentication-less calculator tools for AI agents and clients.

Setup Requirements

  • ⚠️Deploys without any authentication, making the exposed API publicly accessible.
  • ⚠️Requires a Cloudflare account for deployment and management.
  • ⚠️Local testing/development requires `wrangler` CLI and potentially `mcp-remote` for client connections.
Verified SafeView Analysis
The source code itself (src/index.ts) uses Zod for input validation on the calculator tools, making the arithmetic operations robust against common injection attacks within their defined scope. No direct 'eval' or other highly dangerous patterns are present. However, the server is explicitly designed to be 'authless', as stated in the README, meaning it lacks any authentication or authorization mechanisms. While this is intentional for the example, deploying such a server publicly for sensitive operations or without proper access controls would pose a significant security risk for a real-world application.
Updated: 2025-12-11GitHub→
0
0
High Cost
TobiWan1995 icon

fsm-mcp-python-client

by TobiWan1995

Sec8

Connects Large Language Models (LLMs) to state-aware MCP servers, managing LLM sessions and user interaction through an adapter-based architecture.

Setup Requirements

  • ⚠️Requires Python 3.13.2
  • ⚠️Requires a running Ollama server for LLM interaction (defaults to http://localhost:11434)
  • ⚠️Requires a running MCP server for capabilities and tool execution (defaults to http://127.0.0.1:8000/sse)
Verified SafeView Analysis
The client handles configuration via Pydantic models, CLI arguments, and internal defaults, with no hardcoded secrets for authentication. It interacts with an external MCP server and a local Ollama instance. Base64 encoded blobs from the MCP server are decoded for UI display but not executed, mitigating a common vulnerability. The primary security considerations involve the trustworthiness of the connected MCP server and the tools it exposes, as the client acts as an intermediary for tool execution.
Updated: 2025-12-10GitHub→
0
0
Low Cost
bioanywhere icon

news

by bioanywhere

Sec8

A client library for accessing the World News API, enabling developers to search for news articles, extract news links, retrieve geo-coordinates, convert news websites to RSS feeds, and get top news headlines.

Setup Requirements

  • ⚠️Requires an API key for the World News API (paid service).
  • ⚠️Python client requires Python 3.7+ and C++ client requires CMake 3.2+ and Qt.
  • ⚠️The C++ client's internal OAuth `ReplyServer` listens on TCP port 9999, which could lead to port conflicts on the local machine.
Verified SafeView Analysis
The project is primarily an auto-generated API client library in multiple languages. It handles API key and OAuth 2.0 authentication. The C++ client includes a local HTTP server (`ReplyServer`) for handling OAuth redirect callbacks, listening on port 9999. While designed for localhost interaction, this component, like any local server, introduces a minor attack surface (e.g., port conflicts, unintended exposure). The served HTML contains inline JavaScript to process redirect responses, which is a standard client-side OAuth pattern. No direct malicious patterns, code obfuscation, or hardcoded secrets were identified within the provided truncated source code across the various language implementations.
Updated: 2025-12-19GitHub→
PreviousPage 671 of 760Next