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
Low Cost
sudo-tildo icon

Minimal-MCP-Server

by sudo-tildo

Sec1

A minimalist server likely implementing or interacting with a Minecraft-like protocol, possibly for testing custom game functions or providing a lightweight backend.

Review RequiredView Analysis
Cannot perform a security audit as the source code was not provided. Without code inspection, it is impossible to verify the absence of 'eval', hardcoded secrets, network vulnerabilities, or malicious patterns. Therefore, it is considered unsafe to run.
Updated: 2025-11-30GitHub→
0
0
Medium Cost
redblac icon
Sec8

Summarizes YouTube videos and website content using Large Language Models (LLMs) via LangChain and Groq.

Setup Requirements

  • ⚠️Requires a Groq API Key (which may incur costs depending on usage).
  • ⚠️Requires Python 3.7+ and specific Python libraries (e.g., Streamlit, LangChain, validators) to be installed.
  • ⚠️The application runs as a Streamlit web interface locally.
Verified SafeView Analysis
The application handles external URLs, which inherently carries some risk. It uses `UnstructuredURLLoader` to fetch content, and `ssl_verify=False` is set for this loader, which could theoretically expose it to man-in-the-middle attacks when fetching website content, though it's common in development for convenience. User-provided Groq API keys are handled via Streamlit's password input, preventing hardcoding. Input URLs are validated. There are no obvious 'eval' or similar dangerous functions that could lead to arbitrary code execution within the provided source.
Updated: 2026-01-19GitHub→
0
0
Low Cost
bernardpacis icon

create-mcp-server-kit

by bernardpacis

Sec9

Scaffold a production-ready Model Context Protocol (MCP) server quickly.

Setup Requirements

  • ⚠️Node.js 18 or later is required.
  • ⚠️A package manager (npm, pnpm, yarn, or bun) must be installed.
Verified SafeView Analysis
The project is a CLI scaffolding tool. It uses `spawnSync` to execute `git` and package manager commands (`npm install`, etc.). While `spawnSync` can be a vector for abuse if commands are constructed from untrusted input, here it's used for standard development operations with predefined commands and arguments. Input validation for directory names and template options is handled, reducing risk. No `eval` or obvious malicious patterns were found. The generated server template uses the official MCP SDK and Zod for input validation, which is a good security practice for API inputs. The server uses stdio transport, reducing network exposure by default.
Updated: 2026-01-19GitHub→
0
0
Low Cost
Ashiq8 icon
Sec9

Provides a simple todo list management system accessible via the MCP protocol, allowing clients to add, delete, and list tasks.

Setup Requirements

  • ⚠️Requires Python 3.12 or newer.
  • ⚠️Requires the 'mcp[cli]' library to be installed (e.g., via pip).
Verified SafeView Analysis
The server's code does not use 'eval' or similar dangerous functions. File I/O is restricted to a single 'todos.json' file. Input validation is performed for the 'delete_todo' index, preventing out-of-bounds access. Outputs are JSON serialized, mitigating injection risks. No hardcoded secrets or direct network risks (beyond the MCP stdio communication) are apparent from the provided source. The design is simple and appears secure for its intended purpose.
Updated: 2025-12-02GitHub→
0
0
Low Cost

D365BCAdminMCP

by demiliani

Sec4

This project appears to be a tool for Microsoft Cloud Partners to administer or manage aspects of Dynamics 365 Business Central.

Setup Requirements

  • ⚠️Requires Node.js and npm/yarn for installation and execution.
  • ⚠️Likely requires configuration (e.g., API keys, connection strings) to connect to Dynamics 365 Business Central environments.
  • ⚠️May require Microsoft Cloud Partner Program (MCP) credentials or specific Azure AD permissions.
Review RequiredView Analysis
Limited visibility into code due to missing README and no file content provided. The presence of a .tgz package and package.json suggests a Node.js project which may involve network requests or dependencies with unknown vulnerabilities.
Updated: 2025-11-18GitHub→
0
0
High Cost
Dhruv-Limbani icon

puddle-map

by Dhruv-Limbani

Sec3

Provides an AI assistant for a data marketplace, enabling semantic search, filtering, and detailed evaluation of datasets, as well as managing buyer-vendor inquiries and negotiations.

Setup Requirements

  • ⚠️Requires Google Gemini API Key (Paid)
  • ⚠️Requires PostgreSQL Database
  • ⚠️Requires Python 3.13 or newer
Review RequiredView Analysis
The server's `APIKeyMiddleware` for authentication is defined but commented out (`# app.add_middleware(APIKeyMiddleware)`) in `server.py`. This means the server is currently unprotected and accessible to anyone without an API key, despite the `README.md` explicitly stating `API_KEY` is for authentication. This represents a critical vulnerability where all API endpoints would be exposed.
Updated: 2025-12-09GitHub→
0
0
High Cost
lmfor icon
Sec9

A data pipeline that downloads League of Legends esports data from Kaggle and trains a TensorFlow model to predict match outcomes.

Setup Requirements

  • ⚠️Python 3.13+ only (specified in pyproject.toml)
  • ⚠️Requires Kaggle API credentials for dataset download (e.g., KAGGLE_USERNAME, KAGGLE_KEY environment variables or ~/.kaggle/kaggle.json configuration file).
Verified SafeView Analysis
The code itself does not contain obvious security vulnerabilities like eval, hardcoded secrets, or malicious patterns. The primary security consideration is the reliance on external data downloaded from Kaggle, which is a common practice in ML but inherently carries a minor risk if the downloaded datasets themselves were compromised or maliciously crafted to exploit vulnerabilities in pandas or other processing libraries. However, Kaggle is a reputable source, and the code handles data loading in a standard manner.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
hamza-safwan icon

mcp-server

by hamza-safwan

Sec3

Facilitates multiplayer gaming or provides server-side logic for a game, likely Minecraft.

Review RequiredView Analysis
Cannot perform a detailed security audit as no source code content was provided for analysis. Defaulting to a low score due to unknown risks and lack of visibility.
Updated: 2025-12-07GitHub→
0
0
Medium Cost
djslajs icon

mcp-server

by djslajs

Sec7

The server provides a Multi-Capability Platform (MCP) endpoint, exposing weather information, company/project documentation, and various prompt templates as AI tools and resources for Spring AI applications.

Setup Requirements

  • ⚠️Requires `OPEN_WEATHER_API_KEY` environment variable (or relies on the hardcoded default).
  • ⚠️Requires `DOCUMENT_BASE_PATH` environment variable pointing to a directory containing markdown/JSON files for company and project documentation.
  • ⚠️Requires a Java Development Kit (JDK) 17 or newer and Maven to build and run.
Verified SafeView Analysis
A default API key `FAVWlSB7Qa6FVpUgezGuHw` is hardcoded in `application.yml` for the external weather API. While it's a default value for an environment variable, its presence in the source code is a potential risk if it were a sensitive key. The server also reads local files based on the `company.docs.base-path` property; improper configuration of this path in a production environment could lead to the unintended exposure of files.
Updated: 2025-11-27GitHub→
0
0
Medium Cost
consigcody94 icon

sql-whisperer

by consigcody94

Sec9

Provides a multi-database server for natural language to SQL translation, deep schema introspection, and query optimization via the Model Context Protocol (MCP).

Setup Requirements

  • ⚠️Requires Node.js 16+ as a runtime environment.
  • ⚠️Needs a separate Claude Desktop or Claude Code installation to function as an MCP server.
  • ⚠️Requires configuration of database connection details via environment variables within Claude's mcpServers config.
Verified SafeView Analysis
The server employs robust query validation, explicitly checking for dangerous operations (e.g., DROP TABLE, TRUNCATE, DELETE without WHERE) and common SQL injection patterns. All database clients use parameterized queries, which is a critical defense against injection. The natural language query functionality is indicated as a placeholder, implying the LLM generates SQL that then goes through the server's validation. No 'eval' or direct arbitrary code execution is present. Configuration encourages the use of environment variables for secrets, reducing the risk of hardcoded credentials.
Updated: 2025-11-21GitHub→
0
0
High Cost

memory-wiki

by Algiras

Sec8

Semantic knowledge base and MCP server for organizing, searching, and connecting information with AI-powered features, including semantic search, knowledge graph, and file ingestion.

Setup Requirements

  • ⚠️Requires OpenAI, Anthropic, or OpenRouter API key for advanced LLM features (e.g., entity extraction, summarization), or a local Ollama instance for local LLM usage if those features are desired.
  • ⚠️PDF and DOCX file ingestion requires external tools `pdftotext` (from poppler-utils) and `pandoc` respectively to be installed on the system.
Verified SafeView Analysis
The server uses `bollard` for Docker integration, specifically to manage a Qdrant container, which implies interaction with the Docker daemon. It executes external commands (`pdftotext`, `pandoc`) for document ingestion; however, argument handling via Rust's `Command` API generally sanitizes inputs, mitigating command injection risks. The web UI listens on a network port, requiring appropriate firewalling if not intended for public access. LLM integrations rely on environment variables for API keys, avoiding hardcoded secrets. Data is stored locally in JSON files, reducing remote database attack surface. Overall, security practices appear reasonable for its intended use case.
Updated: 2025-11-27GitHub→
0
0
Medium Cost
Puneeth0106 icon
Sec7

This server provides a set of tools to track and manage personal expenses, allowing users to add, list, summarize, update, and delete expenses through an API.

Setup Requirements

  • ⚠️Requires Python 3.11+ as specified in `pyproject.toml`.
  • ⚠️For PostgreSQL-based servers (`local-expense-mcp-server.py`, `remote-expense-mcp-server.py`, `remote-mcp-authentication-server.py`, `server.py`), the `DATABASE_URL` environment variable is required.
  • ⚠️For the GitHub OAuth-enabled server (`remote-mcp-authentication-server.py`), `FASTMCP_SERVER_AUTH_GITHUB_CLIENT_ID` and `FASTMCP_SERVER_AUTH_GITHUB_CLIENT_SECRET` environment variables are required.
  • ⚠️Most server implementations (`local-expense-mcp-server.py`, `remote-expense-mcp-server.py`, `server.py`) are not suitable for multi-user public deployment without an additional, external authentication/authorization layer due to their reliance on an unverified `user_id` parameter.
Review RequiredView Analysis
The database interactions use parameterized queries (both psycopg2 and sqlite3), which effectively prevents SQL injection vulnerabilities. Environment variables are correctly utilized for sensitive information such as database connection URLs and API keys (e.g., GitHub OAuth credentials). CRITICAL CONCERN: Several server implementations (`local-expense-mcp-server.py`, `remote-expense-mcp-server.py`, and `server.py`) rely on a `user_id` parameter passed by the client. While they contain an `ensure_user_identity` helper to prompt for a user's name if `guest` is provided, these servers *do not perform any authentication or authorization on the `user_id` itself*. If these servers are deployed to a publicly accessible network without an external, robust authentication layer, any individual could potentially access or manipulate expense data for any `user_id` by simply specifying it in their API requests. This poses a significant security risk for multi-user or public deployments. MINOR CONCERN: In `remote-mcp-authentication-server.py`, the `JWT_KEY` environment variable and its use as a `jwt_signing_key` for the GitHubProvider are commented out. If `FastMCP` does not automatically provide a strong default or if tokens are used without proper signing, this could compromise the integrity and authenticity of authentication tokens. Network Exposure: The servers are configured to run on `0.0.0.0`, meaning they listen on all available network interfaces. This requires proper network security (e.g., firewalling) if deployed in a production or publicly exposed environment.
Updated: 2026-01-18GitHub→
PreviousPage 332 of 760Next