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
Medium Cost
kfzzzzzz icon

gaode-mcp-server

by kfzzzzzz

Sec5

This server likely provides an API to interact with or process data related to Gaode Maps or a mobile content platform.

Setup Requirements

  • ⚠️Requires Gaode API Key (potentially paid service)
  • ⚠️Requires a database (e.g., MySQL, MongoDB)
Review RequiredView Analysis
A thorough security audit is impossible as no source code was provided for analysis. The score reflects an inability to verify safety rather than identified vulnerabilities. Users should exercise extreme caution as hardcoded secrets, dangerous patterns like 'eval', or malicious code cannot be ruled out without actual code review.
Updated: 2025-12-13GitHub→
0
0
Low Cost

fragrance-mcp

by lflor120

Sec5

A server for managing and processing fragrance-related data.

Review RequiredView Analysis
Insufficient information to perform a detailed security audit due to lack of code beyond .gitignore and README.md. No known risks, but no verification of safety possible.
Updated: 2025-11-22GitHub→
0
0
High Cost
albertjoseph0 icon
Sec8

Provides an authenticated Model Context Protocol (MCP) server that exposes proprietary data sources, specifically travel-industry expert-call transcripts from an OpenAI Vector Store and structured airfare trend data from local files, to ChatGPT or other MCP-capable clients.

Setup Requirements

  • ⚠️Requires Python 3.10+
  • ⚠️Requires an Auth0 tenant (or any OAuth 2.1 provider with OIDC discovery) for authentication setup
  • ⚠️Requires an OpenAI API Key (Paid Service) for vector store operations
  • ⚠️Requires `VECTOR_STORE_ID` to be populated by running an initial script (e.g., `python scripts/upload_expert_calls_to_vector_store.py`)
  • ⚠️RESOURCE_SERVER_URL needs to be updated to a public URL for external clients like ChatGPT
Verified SafeView Analysis
The server uses Auth0 for OAuth 2.1 bearer token authentication with JWT validation via JWKS, which is a standard and robust approach. Environment variables are correctly utilized for sensitive information like API keys and issuer URLs, preventing hardcoding. The Python `JWTVerifier` explicitly notes that it 'does not contain entitlements' and 'you must add your own entitlements,' indicating that fine-grained authorization logic beyond basic token validity needs to be implemented by the developer. The `SimpleTokenVerifier` is present but not used in the main application. Overall, it provides a secure foundation, but requires developer attention for full authorization implementation.
Updated: 2025-12-01GitHub→
0
0
High Cost
praneet1503 icon

astrx-mcp-server

by praneet1503

Sec9

A high-performance RAG system providing AI-enriched knowledge and semantic search capabilities for a large animal dataset.

Setup Requirements

  • ⚠️Requires API keys for SambaNova, Anthropic Claude, Google Gemini, and Blaxel (or relies on limited demo keys).
  • ⚠️Requires Modal CLI installed and authenticated (`modal setup`) for AI enrichment and semantic search embeddings.
  • ⚠️Initial data setup (`data/animals.json`, external CSVs) is required, although `scripts/download_and_merge.py` can automate parts of this.
Verified SafeView Analysis
API keys are handled via environment variables, `.env` files, and Modal secrets, or temporarily stored in session memory for Gradio. Network calls to external LLM APIs use `httpx` with timeouts. Web scraping with Playwright is isolated within Modal functions. No direct `eval` or `subprocess` execution from user input is observed. The data loading is from controlled local files or specific external URLs. Standard prompt injection risks for LLM interactions exist but do not compromise the underlying system.
Updated: 2025-11-30GitHub→
0
0
Low Cost
myvfc icon
Sec8

Provides college football player statistics from the CFBD API through an MCP (Multi-tool Coordination Protocol) endpoint.

Setup Requirements

  • ⚠️Requires a free CFBD API Key (needs sign-up at collegefootballdata.com).
  • ⚠️An `MCP_API_KEY` is recommended for securing the `/mcp` endpoint.
  • ⚠️The provided JavaScript server files (`server.js`, `cfbd-stats-server.js`, etc.) only implement the `get_player_stats` tool, despite documentation (CFBD_COMPLETE_PROMPT.md, CFBD_README.md) describing 8 comprehensive tools.
Verified SafeView Analysis
The server correctly uses environment variables for `CFBD_API_KEY` and `MCP_API_KEY`, preventing hardcoded secrets. It implements optional bearer token authentication for the `/mcp` endpoint. Input validation is minimal for `team` and `year` parameters, relying on CFBD API for handling, which is generally acceptable for public APIs. Extensive logging in some variants could expose request details, but it's not a critical vulnerability. CORS is implicitly open for all origins as `cors()` is used without specific origin restrictions in some included files, which is common for tool servers but could be tightened if needed. The primary server.js does not explicitly configure cors, but express does not restrict it by default. The server does not use `eval` or other highly dangerous patterns.
Updated: 2025-11-20GitHub→
0
0
Medium Cost
dominodatalab icon

qa_mcp_server

by dominodatalab

Sec8

Automated User Acceptance Testing (UAT) and performance analysis for the Domino Data Science Platform using an LLM-powered MCP server.

Setup Requirements

  • ⚠️Requires Python 3.11 or higher.
  • ⚠️Requires access to an active Domino Data Science Platform instance with a valid API key and host configured in a .env file.
  • ⚠️Requires Domino user and project names to be configured in a `@domino_project_settings.md` file for LLM client to provide as parameters.
Verified SafeView Analysis
The server uses environment variables for sensitive credentials (DOMINO_API_KEY, DOMINO_HOST) and reads user/project names from a markdown file, which is good practice. It interacts with the Domino platform via API, which is its core functionality. The `open_web_browser` tool could potentially open arbitrary URLs if the LLM client is compromised or poorly constrained, posing a minor risk of opening unintended browser tabs on the server host. However, in the context of a dedicated QA tool, this is likely used for specific, internal Domino URLs.
Updated: 2026-01-13GitHub→
0
0
Medium Cost
serenichron icon

mcp-cloudron

by serenichron

Sec9

MCP server for Cloudron instance management, enabling AI assistants to list apps, get status, manage resources, and perform validated operations on self-hosted applications.

Setup Requirements

  • ⚠️Requires a `CLOUDRON_API_TOKEN` with 'Read and Write' permissions from your Cloudron Admin Panel. Insufficient permissions will lead to tool failures (e.g., 401 'No such token').
  • ⚠️Requires a running and accessible Cloudron instance (`CLOUDRON_BASE_URL` must be correct).
  • ⚠️Node.js version 18 or higher is required.
Verified SafeView Analysis
The server follows strong security practices. It requires `CLOUDRON_BASE_URL` and `CLOUDRON_API_TOKEN` to be set via environment variables, preventing hardcoded credentials. All API calls use bearer token authentication over HTTPS. Crucially, it implements pre-flight validation (F37, F36, F23a) for destructive operations (e.g., uninstall app, create backup, install app, restore backup) and storage checks, adding a critical layer of safety. Input validation is performed for all tool parameters (e.g., email/password strength, app IDs, roles). No `eval` or other dangerous dynamic code execution patterns were found. Error messages are designed to avoid leaking sensitive internal details. The primary security risk lies in the permissions granted to the `CLOUDRON_API_TOKEN` itself; it should be configured with the minimum necessary 'Read and Write' scope as emphasized in the `REAL_API_TEST_RESULTS.md`.
Updated: 2025-12-27GitHub→
0
0
Low Cost
saketh395 icon

Anthropic_MCP

by saketh395

Sec5

Builds and operates a Minecraft Protocol (MCP) server-client architecture for game interaction.

Review RequiredView Analysis
Insufficient source code provided for a comprehensive security audit. Only the README file was available. Cannot assess for 'eval', obfuscation, hardcoded secrets, network risks, or malicious patterns.
Updated: 2025-11-30GitHub→
0
0
Low Cost
consigcody94 icon

minecraft-pilot

by consigcody94

Sec9

Control a Minecraft Java Edition server using natural language commands through Claude Desktop via RCON.

Setup Requirements

  • ⚠️Requires a Minecraft Java Edition Server with RCON enabled and correctly configured (port, password).
  • ⚠️Requires Node.js 16+ and npm to be installed.
  • ⚠️Requires Claude Desktop to be installed and correctly configured with the absolute path to the `mcp-server.js` file, which is a common point of error.
Verified SafeView Analysis
The project extensively documents the inherent security risks of RCON (unencrypted protocol) and provides robust warnings and mitigation strategies, including strong password recommendations, firewall configuration for local access, and SSH tunneling for remote access. The `CommandParser` includes built-in safety validation to prevent execution of dangerous commands like server shutdowns (`stop`, `restart`), mass bans (`ban *`), or global kills (`kill @a`/`@e`). No 'eval' or malicious patterns were found in the source code. Hardcoded secrets are avoided by requiring environment variables for RCON credentials.
Updated: 2025-11-21GitHub→
0
0
Medium Cost
William-Ger icon
Sec9

Provides comprehensive tools for accessing and studying the Bible, including verse lookup, search, chapter reading, and generating devotional and study guides.

Setup Requirements

  • ⚠️Requires deployment to a remote server (e.g., Railway) to obtain a public URL for connection.
  • ⚠️Requires `npx` (Node.js/npm) installed on the client machine to connect via `mcp-remote`.
Verified SafeView Analysis
The server uses `requests` to interact with the public `bible-api.com`. There are no 'eval' or similar dangerous functions found. No hardcoded secrets. The server is designed for remote hosting and listens on all interfaces, which is standard for deployed applications. Overall, it appears safe.
Updated: 2026-01-17GitHub→
0
0
Low Cost
thinkingidentities icon

ep2-filebridge

by thinkingidentities

Sec8

Facilitates cross-platform file and Git operations for AI agents and other cognates within a sandboxed repository.

Setup Requirements

  • ⚠️Requires Node.js installed to run the server components.
  • ⚠️Requires Git installed on the host machine where the server runs, with the target repository initialized at the `FILEBRIDGE_ROOT`.
  • ⚠️For full 'Gabe' (ChatGPT) functionality, an external 'Cognate Gateway' and 'Cloudflare Tunnel' (or similar public exposure) are required to route HTTPS requests to the internal HTTP server.
Verified SafeView Analysis
The server implements strong path sanitization (`safePath()`) to sandbox all file operations to a specific root directory (`/home/jim00/ep2` by default), preventing arbitrary file system access. It does not use `eval()` or direct `child_process.exec()` on user input. It relies on `simple-git` for Git operations, which generally handles command arguments safely, minimizing shell injection risks. The primary remaining risk is the inherent privilege of offering file and Git access, which requires trust in the consuming AI agents and robust input validation, or a potential exploit within `simple-git` or the Node.js `fs` module itself. The MCP-SSE server sets `Access-Control-Allow-Origin: *`, which is typical for SSE but means any origin can connect to the SSE endpoint.
Updated: 2025-12-01GitHub→
0
0
Medium Cost
lalipop05 icon
Sec9

Serves as a Model Context Protocol (MCP) server to connect Large Language Models (LLMs) with University of Texas at Dallas (UTD) course data and RateMyProfessors ratings.

Setup Requirements

  • ⚠️Requires a `NEBULA_API_KEY` which may need to be obtained from UTD Nebula Labs.
  • ⚠️The `PATH_TO_ENV` variable in `cmd/server/main.go` is hardcoded to a Windows absolute path and must be updated for different operating systems or installation locations.
Verified SafeView Analysis
API keys are sourced from environment variables, which is a good security practice for sensitive credentials. All external API communications are handled over HTTPS. GraphQL queries are constructed using named variables and parameters, mitigating direct injection risks. The primary non-critical concern is a hardcoded absolute path to the `.env` file in `cmd/server/main.go`, which is a setup issue for portability rather than a code vulnerability.
Updated: 2026-01-17GitHub→
PreviousPage 682 of 713Next