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
Sec6

A server component or proxy for Minecraft that integrates with Lanyard, likely for status updates or external monitoring related to the Minecraft server.

Setup Requirements

  • ⚠️Docker environment is highly recommended for deployment due to the presence of a Dockerfile; manual setup without Docker requires Python and dependency management.
  • ⚠️A Python environment must be set up, and dependencies listed in `requirements.txt` must be installed (`pip install -r requirements.txt`) if not using Docker.
  • ⚠️Configuration is likely required via `custom.yaml` for Lanyard API keys, server connection details, or other operational parameters.
Review RequiredView Analysis
Cannot inspect `lanyard_server.py` or `requirements.txt` for specific vulnerabilities like `eval` usage or risky dependencies. As a server application, it inherently exposes network services, requiring careful configuration and security practices. The presence of a `SECURITY.md` file is a positive indicator that security considerations have been made, but a full code review is essential before deployment.
Updated: 2025-11-18GitHub→
0
0
Low Cost
aiscibe-mcp-deployment icon

mcp-e70738e0-1d31cc16-jcd

by aiscibe-mcp-deployment

Sec7

An auto-generated Model Context Protocol (MCP) server that exposes configured APIs as tools for Claude and other AI models.

Setup Requirements

  • ⚠️Requires OpenAI API Key (Paid) if connecting to OpenAI services, as mentioned for Vercel deployment.
  • ⚠️Requires Python 3.9 for Vercel deployment (local development may vary but 3.9+ is recommended).
  • ⚠️Local development requires manually creating and editing a `.env` file from `.env.example`.
Verified SafeView Analysis
The `api/index.py` handler uses `Access-Control-Allow-Origin: *`, which is a permissive CORS setting. The `API_CONNECTIONS` object in `app/mcp_server.py` is defined in source code and, if modified, could potentially hardcode API keys/tokens directly instead of fetching them from environment variables, posing a secret management risk. The `call_api` function directly uses the `endpoint` argument for URL construction; while tools are intended to be manually registered, this pattern could lead to Server-Side Request Forgery (SSRF) if user input to tools is not rigorously validated. Logging is set to DEBUG which might expose sensitive information in a production environment. No direct use of `eval` or explicit command injection patterns were identified.
Updated: 2025-12-05GitHub→
0
0
Low Cost
samlevan icon
Sec9

Provides a safety system for AI assistants to update Bear notes by creating previews for user review and approval.

Setup Requirements

  • ⚠️Requires macOS (Bear app is macOS-only)
  • ⚠️Requires Bear app installed and running
  • ⚠️Requires Python 3.11+
  • ⚠️Requires manual configuration in Claude Desktop or a compatible MCP client to integrate
Verified SafeView Analysis
The server uses `subprocess.run` to interact with the Bear app via `x-callback-url`, with all content parameters properly URL-encoded using `urllib.parse.quote` to prevent injection. SQLite database interactions for reading notes use parameterized queries, preventing SQL injection. The local database file has secure permissions (600). The web interface for previews correctly escapes HTML content, mitigating XSS risks. No `eval` or similar dangerous patterns are used without clear justification. The overall design prioritizes user review and explicit approval before applying changes to Bear notes, significantly enhancing safety.
Updated: 2025-11-30GitHub→
0
0
Medium Cost
rickyhoneycutt icon

mcp-connector

by rickyhoneycutt

Sec5

A unified server for bridging multiple LLM platforms to a centralized tool execution layer using the Model Context Protocol (MCP).

Setup Requirements

  • ⚠️Requires Go 1.22+, Node.js 20+, Docker, PostgreSQL 15+, and Redis 7+ installed locally for development setup.
  • ⚠️Hardcoded PostgreSQL credentials (`mcp:mcp`) and unauthenticated Redis in the `docker-compose.yml` for development, which must be secured for production.
Verified SafeView Analysis
The `docker-compose.yml` file contains hardcoded database credentials (`mcp:mcp`) and does not configure authentication for Redis. While the `docs/architecture.md` outlines a robust security model (bcrypt-hashed API keys, scoped permissions, input validation, rate limiting), the provided Go backend's `main.go` is largely a scaffold with `TODO` comments, meaning these security features are not fully implemented or visible in the truncated source. This makes the current state of the repository as provided insecure for production deployment without significant configuration changes.
Updated: 2026-01-18GitHub→
0
0
Medium Cost
huangjien icon

devops-mcps

by huangjien

Sec9

A FastMCP-based server providing read-only DevOps tools and integrations for GitHub, Jenkins, Artifactory, and Azure, designed for data analysis and display.

Setup Requirements

  • ⚠️Requires accounts and API tokens/credentials for GitHub, Jenkins, Artifactory, and Azure. These are external services, which may incur costs and require specific setup.
  • ⚠️Requires Python 3.12 or newer.
  • ⚠️Requires outbound network access to GitHub, Jenkins, Artifactory, and Azure API endpoints.
  • ⚠️Artifactory authentication requires either 'ARTIFACTORY_IDENTITY_TOKEN' or both 'ARTIFACTORY_USERNAME' and 'ARTIFACTORY_PASSWORD' in conjunction with 'ARTIFACTORY_URL'.
Verified SafeView Analysis
The server operates in a read-only manner, retrieving data without modifying external systems. It properly handles sensitive credentials via environment variables (GitHub token, Jenkins credentials, Artifactory credentials, Azure credentials) and does not hardcode them. API calls to external services use standard Python libraries (`requests`, `PyGithub`, `jenkinsapi`, `azure-sdk`) with timeouts. Dynamic prompt rendering relies on regex and string replacement, not `eval`. Logging includes robust exception handling.
Updated: 2026-01-19GitHub→
0
0
Low Cost
shin902 icon
Sec7

A proxy server to efficiently manage and expose categorized tools from multiple Model Context Protocol (MCP) servers to Language Models (LLMs), optimizing context usage by loading tool schemas on-demand.

Setup Requirements

  • ⚠️Requires Node.js >= 22.0.0 (as per package.json 'engines').
  • ⚠️Requires pnpm for development dependencies (packageManager: pnpm@10.21.0).
  • ⚠️Requires at least one accessible upstream Model Context Protocol (MCP) server, as it acts as a proxy. The example configuration's `@org/serena-mcp@latest` is a placeholder and does not exist on npm; users must provide or implement a functional upstream MCP server for the proxy to be operational.
Review RequiredView Analysis
The server's core functionality involves launching external processes (for 'stdio' type upstream MCP servers via the 'command' and 'args' fields) or connecting to arbitrary network endpoints ('http'/'sse' types via 'url' field) as defined in its configuration. This design means that the overall security is heavily dependent on the trustworthiness and secure management of the configuration file (e.g., 'serena-config.json'). Untrusted or malicious configuration could lead to arbitrary command execution on the host system or connections to harmful external services. The source code itself uses `valibot` for robust schema validation of the configuration, helping prevent issues from malformed inputs, and logs errors to stderr. No hardcoded secrets or obvious malicious patterns were found in the application's source code, making the code itself reasonably secure for its intended purpose. However, the powerful capabilities it enables require a high degree of trust in the provided configuration.
Updated: 2026-01-19GitHub→
0
0
Low Cost
sharo-jef icon

wait-mcp

by sharo-jef

Sec9

An MCP Server providing a 'wait' tool, primarily used for testing timeouts, simulating delays, and rate limiting in development and integration scenarios.

Setup Requirements

  • ⚠️Requires Node.js runtime (version 18.0.0 or higher).
  • ⚠️Requires manual configuration in `claude_desktop_config.json` to integrate with Claude Desktop.
Verified SafeView Analysis
The source code is straightforward and purpose-built. It uses standard Node.js `setTimeout` for its core 'wait' functionality and includes basic input validation for the `duration` parameter (ensuring it's a non-negative number). There are no obvious signs of 'eval' usage, obfuscation, hardcoded secrets, or malicious network patterns. The server operates over stdio, limiting direct network exposure beyond the Model Context Protocol SDK. The `message` parameter is used as plain text, preventing injection. The primary function (waiting for a duration) is an intended feature for testing, not a vulnerability in itself, though extremely long durations could be a resource concern in uncontrolled environments.
Updated: 2026-01-18GitHub→
0
0
High Cost
sendsta icon

tri-tender-mcp

by sendsta

Sec8

Generates complete, multi-document tender responses and proposals from parsed tender and company profile data using a large language model.

Setup Requirements

  • ⚠️Requires FastMCP Cloud runtime for optimal operation.
  • ⚠️Requires an LLM provider configured within the FastMCP Cloud environment (e.g., OpenAI, Anthropic, etc.).
Verified SafeView Analysis
The code itself does not contain explicit 'eval' or other direct code execution vulnerabilities. Input data (parsed_tender, company_profile) is embedded directly into LLM prompts, introducing the common risk of prompt injection, which could lead to undesired LLM outputs or potential data exposure if not properly mitigated at the LLM provider level. No hardcoded secrets were found.
Updated: 2025-11-30GitHub→
0
0
Medium Cost
malwaredetective icon

GTFOBins-MCP

by malwaredetective

Sec9

This MCP server enables Large Language Models (LLMs) to query local GTFOBins data for Unix binaries that can be exploited to bypass security restrictions.

Setup Requirements

  • ⚠️Requires Python 3.11+ and a Python virtual environment.
  • ⚠️Requires a separate MCP client to interact with the server.
  • ⚠️The GTFOBins API data (api.json, functions.json) needs to be built locally using the `scripts/build_api.py` script and the GTFOBins.github.io repository (not included directly in the provided source code snapshot) before the server can function correctly.
Verified SafeView Analysis
The server primarily operates locally via STDIO, processes data from local JSON files, and does not initiate external network connections. It uses safe JSON parsing and dictionary lookups for handling input, mitigating risks like command injection or 'eval' vulnerabilities. No hardcoded secrets or malicious patterns were identified. The data provided by GTFOBins describes system exploits, but this is the intended purpose of the server and not a vulnerability in the server's code itself.
Updated: 2026-01-18GitHub→
0
0
Low Cost
burnworks icon
Sec9

This server integrates AI tools with Movable Type to facilitate AI-driven drafting and editing of blog posts, specifically focusing on creating and managing draft articles.

Setup Requirements

  • ⚠️Requires Movable Type Data API to be enabled in system and blog settings.
  • ⚠️Requires a specific 'Web Services Password' from the Movable Type user profile, distinct from the regular login password.
  • ⚠️Node.js 22.7.5 or newer is required.
Verified SafeView Analysis
The server uses environment variables for sensitive Movable Type API credentials (MT_USERNAME, MT_PASSWORD, MT_API_URL). It explicitly prohibits dangerous operations like deleting articles, publishing drafts, or editing published articles, by design. Input from the AI client is structured via MCP SDK schemas and passed through an `axios`-based client that correctly encodes parameters, mitigating common injection risks. Session data is stored locally on the file system and is not exposed over the network. The code is well-structured and avoids direct use of 'eval' or similar high-risk functions.
Updated: 2025-11-19GitHub→
0
0
Low Cost
worklocalinc icon

unicorn-site

by worklocalinc

Sec3

A magical unicorn website deployed via the MCP Server framework.

Setup Requirements

  • ⚠️Requires an MCP Server environment for deployment.
Review RequiredView Analysis
The provided source code is highly truncated/summarized. A full security audit for 'eval', obfuscation, network risks, hardcoded secrets, or malicious patterns is not possible. The score reflects this lack of visibility and the unknown risk inherent in running un-audited code.
Updated: 2025-11-26GitHub→
0
0
Low Cost
Dannycalvin icon

exchange-rate-mcp

by Dannycalvin

Sec9

This server provides real-time currency conversion using an external API, making it easy to convert amounts between different currencies.

Setup Requirements

  • ⚠️Requires EXCHANGE_RATE_API_KEY environment variable (obtainable from ExchangeRate-API.com)
  • ⚠️Requires Python 3.12 or higher
  • ⚠️Requires an active internet connection to retrieve exchange rates
Verified SafeView Analysis
The server correctly uses environment variables for sensitive API keys, preventing hardcoding. It employs `httpx` for network requests, a standard and secure library. Robust error handling is implemented for various API response errors (e.g., invalid key, unknown currency, quota reached). No 'eval', obfuscation, or other known malicious patterns were identified in the provided source code. The server's functionality relies on an external API, which is an inherent part of its design, and potential risks associated with that API (e.g., its availability or data integrity) are external to this specific server's code security.
Updated: 2026-01-19GitHub→
PreviousPage 605 of 760Next