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
CorpLynx icon

mc-mcp

by CorpLynx

Sec7

Enables Large Language Models (LLMs) to interact with and control Minecraft servers through a WebSocket-based Model Context Protocol (MCP).

Setup Requirements

  • ⚠️Requires Node.js 18+ and Java 17+ installed.
  • ⚠️Requires a Minecraft Server with NeoForge 1.20.1+ installed.
  • ⚠️Involves configuring and starting three separate components (Bridge Server, MCP Server, Minecraft Mod) in a specific order.
  • ⚠️The Gradle wrapper for the Minecraft mod is missing and needs to be initialized before building (./gradlew build).
  • ⚠️Requires careful manual configuration of multiple .env and .toml files with secure tokens and command whitelists.
Verified SafeView Analysis
The system implements token-based authentication between components and command whitelisting on the Minecraft mod. The 'execute_command' tool allows arbitrary command execution, which is mitigated by regex-based whitelisting, but this remains a critical point requiring careful user configuration to prevent abuse. A default 'secret' authentication token in the Minecraft mod's example config is a minor risk if not changed by users, although the documentation explicitly advises using strong, unique tokens for production.
Updated: 2025-11-30GitHub→
0
0
Medium Cost
RajwardhanMali icon

MDBQS

by RajwardhanMali

Sec3

A multi-database query system enabling natural language querying of heterogeneous databases (SQL, NoSQL, Graph, Vector) via LLM-assisted planning and parallel execution with result fusion and provenance tracking.

Setup Requirements

  • ⚠️Requires Python 3.10+
  • ⚠️Requires Docker and Docker Compose to run the multiple database services (PostgreSQL, MongoDB, Neo4j, Milvus).
  • ⚠️Requires a Google Gemini API Key for intelligent LLM planning; otherwise, it defaults to a very basic heuristic planner. This key needs to be set in a '.env' file.
  • ⚠️The main FastAPI backend (`app.main:app`) is designed to interact with four *separate* FastAPI MCP (Model Context Protocol) plugin servers (e.g., `mcp_sql_sample`, `mcp_nosql_sample`, etc.) typically running on ports 8001-8004. These plugin servers are not automatically started by the provided `run-all-servers.sh` script or the main backend, requiring manual orchestration to run the full system.
Review RequiredView Analysis
The system utilizes an LLM (Google Gemini) to directly generate database query strings (SQL, NoSQL filters, Cypher components) which are then executed without robust semantic validation or sanitization. This presents a high risk of prompt injection and subsequent database injection (SQL injection in PostgreSQL, potential NoSQL injection for MongoDB via '$where'/'$eval', Milvus query injection in `get_metadata` via f-string for `cust_id`). Although the SQL adapter claims 'ONLY SELECT allowed', this is an LLM instruction and not technically enforced, making it vulnerable to malicious query chains. Hardcoded database credentials (e.g., 'postgrespassword', 'neo4jpassword', 'minioadmin') are present in `docker-compose.yml` for development, which is a severe risk if used in production.
Updated: 2025-12-06GitHub→
0
0
Medium Cost
Sadiqraza2003 icon

KM-remote-mcp-server

by Sadiqraza2003

Sec9

AI-powered expense management assistant that helps users track, summarize, and manage their personal expenses through natural language interactions.

Setup Requirements

  • ⚠️Requires Python 3.13+
  • ⚠️Requires MySQL database accessible via DATABASE_URL environment variable
  • ⚠️Requires 'categories.json' file to be present in the same directory as 'main.py' for expense categorization
Verified SafeView Analysis
Robust user isolation implemented across all CRUD operations (add, list, summarize, edit, delete) prevents users from accessing or modifying others' data. Sensitive database connection details are loaded from environment variables. No 'eval' or obvious malicious patterns found in the provided code.
Updated: 2025-11-26GitHub→
0
0
Medium Cost
TianyiPeng icon

dedalus-mcp-server

by TianyiPeng

Sec10

An MCP server that provides general utility tools for text and math operations, and functions as a documentation server, enabling AI agents to query documentation, answer questions, and perform multi-stage analysis based on the served content.

Setup Requirements

  • ⚠️Requires OpenAI/Anthropic API Key for AI features (paid service).
  • ⚠️Requires `uv` package manager for dependency installation (recommended by Dedalus).
  • ⚠️Requires a specific `pyproject.toml` and root `main.py` structure for Dedalus deployment.
Verified SafeView Analysis
The provided `src/main.py` file implements simple utility tools with no inherent security risks like `eval` or direct network vulnerabilities. It demonstrates safe practices like handling input validation (`factorial`, `convert_temperature`) and includes asynchronous operations for I/O (`get_timestamp`). The project context (README, docs, tests, examples) indicates the server is designed to function as an AI-powered documentation server, which would involve API calls to LLMs (like OpenAI/Anthropic). While the specific `ask_docs` implementation for such AI features is not directly within the provided `src/main.py` block, the project's overall design promotes securing API keys via environment variables and includes rate-limiting mechanisms (as shown in `docs/guides/server/dedalus-deployment.md` and `tests/test_rate_limit.py`) to prevent API abuse. The codebase appears well-designed for security within its broader scope.
Updated: 2025-11-25GitHub→
0
0
Low Cost
opensm icon
Sec10

A boilerplate repository for managing new MCP servers within a GitLab DevOps environment, primarily serving as a project template.

Setup Requirements

  • ⚠️The repository currently contains only a generic GitLab README template and no actual server implementation code.
  • ⚠️Further development is required to implement the 'mcp servers' functionality.
Verified SafeView Analysis
The provided source code is limited to a generic GitLab README.md template. There is no actual server application code to analyze for security risks such as 'eval', obfuscation, network vulnerabilities, hardcoded secrets, or malicious patterns. The README file itself poses no security threat.
Updated: 2025-12-05GitHub→
0
0
High Cost
Habtamu-Dires icon

spring-mcp-stdio

by Habtamu-Dires

Sec10

This server acts as a Model Context Protocol (MCP) tool provider for Spring AI, exposing Spring I/O conference session data.

Setup Requirements

  • ⚠️Requires Java Development Kit (JDK) 17+.
  • ⚠️Operates over standard input/output (stdio) for MCP communication, not an HTTP endpoint.
  • ⚠️Requires Maven or Gradle for building and running.
Verified SafeView Analysis
The application is minimal, loading static data from a local JSON file. It exposes a single read-only tool function via Spring AI's Model Context Protocol (MCP) over standard I/O. There are no dynamic code executions, external network calls for data, hardcoded secrets, or obvious vulnerabilities. It is considered very safe.
Updated: 2025-12-05GitHub→
0
0
Medium Cost
iflorit icon
Sec8

A Model Context Protocol (MCP) server for Woffu time tracking integration, enabling AI assistants to manage clock-in/out and time tracking operations.

Setup Requirements

  • ⚠️Requires `WOFFU_TOKEN` (JWT Bearer token) which needs to be manually extracted from browser cookies and periodically refreshed.
  • ⚠️Requires `WOFFU_USER_ID` which needs to be manually extracted from the JWT token or Woffu network requests.
  • ⚠️Requires Node.js version 18.0.0 or higher.
Verified SafeView Analysis
The server primarily relies on environment variables (`WOFFU_TOKEN`, `WOFFU_USER_ID`, `WOFFU_BASE_URL`) for configuration, which is a good practice for sensitive data. It uses the `fetch` API to interact with the Woffu service. The primary security risk involves providing a malicious `WOFFU_BASE_URL` or an exposed `WOFFU_TOKEN` by the user, but the server itself does not introduce new vulnerabilities like code execution or direct file system access beyond its intended scope. Input validation for `completeDay` parameters (date and time formats) is present. As an MCP server, it's designed for local integration with an AI agent, limiting its external attack surface.
Updated: 2025-11-24GitHub→
0
0
Low Cost
salimbentounsi icon

proximity

by salimbentounsi

Sec9

A GitHub Learning Lab course repository for learning Git and GitHub, presented as an interactive slideshow.

Setup Requirements

  • ⚠️Requires Ruby and Bundler for Jekyll.
  • ⚠️Requires Node.js and npm/yarn for `reveal.js` dependency (if not vendored or installed via other means).
Verified SafeView Analysis
The provided source code defines a static Jekyll site for a GitHub Learning Lab course, utilizing `reveal.js`. It contains no obvious malicious patterns, `eval` functions, obfuscation, or hardcoded secrets within the Jekyll configuration itself. However, the `README.md` explicitly links to an external ZIP file (`proximity.zip`) as the actual 'open source project' used by the course. The contents of this external ZIP file are not included in the provided source code for analysis, and therefore, its security posture cannot be assessed. Proceeding to download and execute code from this external ZIP without independent verification would introduce unknown risks.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
DanNsk icon

MemoryGraph

by DanNsk

Sec8

Visualizes knowledge graphs from the multi-memory-mcp project in an interactive 3D force-directed graph.

Setup Requirements

  • ⚠️.NET 8.0 SDK is required.
  • ⚠️SQLite databases must adhere to a specific schema and be located in the configured 'MemoryFolderPath' (default: ./.aim/). Although sample databases are generated in Development mode, custom data requires manual setup.
Verified SafeView Analysis
The application handles graph data loading via API calls where the 'database' parameter is URL-encoded on the frontend. A critical security aspect in the backend (MemoryGraphService/SqliteDataService, not fully provided) is rigorous path validation to prevent directory traversal when accessing SQLite files, ensuring only files within the configured 'MemoryFolderPath' are accessed. Frontend HTML escaping is used to mitigate XSS risks. No 'eval' or obvious hardcoded secrets were found in the provided code snippets.
Updated: 2025-12-03GitHub→
0
0
Medium Cost
TheMacroeconomicDao icon

bybit-ai-trader

by TheMacroeconomicDao

Sec3

AI-driven cryptocurrency market analysis, signal generation, and automated trading operations on Bybit, with Telegram integration for signal delivery and a WebUI for monitoring.

Setup Requirements

  • ⚠️Requires valid Bybit API Key and Secret with appropriate read/trade permissions.
  • ⚠️Requires OpenRouter.ai API Key (`QWEN_API_KEY`) and sufficient credits for Qwen models.
  • ⚠️Requires Telegram Bot Token (`TELEGRAM_BOT_TOKEN`) and specific chat IDs (`TELEGRAM_CHAT_IDS`) for notifications.
  • ⚠️Python dependencies must be installed via `pip install -r requirements.txt`.
  • ⚠️WebUI setup and server (`bybit-analysis`) require Node.js and pnpm.
Review RequiredView Analysis
The `CURSOR_MCP_CONFIG.json` provided directly exposes `BYBIT_API_KEY` and `BYBIT_API_SECRET` within its `env` block. While the system's `load_credentials` function prioritizes environment variables, this configuration itself is a critical vulnerability if exposed. The project's historical records (e.g., `archive/fixes/FIX_PROMPTS.md`) also detail past leaks of multiple API keys and a Telegram token, with explicit instructions for Git history cleansing, indicating a significant past security lapse. The `TELEGRAM_BOT_TOKEN` and `TELEGRAM_CHAT_IDS` are also explicitly mentioned in plain text in documentation files, which is sensitive information.
Updated: 2025-12-19GitHub→
0
0
High Cost
leadfuze icon

mcp-server

by leadfuze

Sec9

Enable AI agents to enrich contacts and companies with verified business data like emails, phone numbers, and job titles for sales prospecting.

Setup Requirements

  • ⚠️Requires a LeadFuze API Key (LeadFuze is a paid service, credits consumed per match/validation)
  • ⚠️Requires Node.js 18.0.0 or higher to run locally
  • ⚠️Self-hosting requires `npm install` and `npm run build`
Verified SafeView Analysis
The server handles API keys via environment variables or Authorization headers, which is standard and secure for its purpose. CORS is properly configured to restrict access to allowed origins (e.g., Claude.ai, localhost). No `eval` or direct file system access beyond module loading. Sessions are managed to ensure per-user API key isolation. Error handling in the client provides user-friendly messages, though the raw API error text could be verbose if the upstream LeadFuze API were to return sensitive data in an error payload (this is not a direct vulnerability of this server's code, but a general consideration for API proxies).
Updated: 2025-12-14GitHub→
0
0
Low Cost
dbrooks61785 icon

ez-mcp-server

by dbrooks61785

Sec8

Provides a simple server implementation of the Model Context Protocol (MCP) using Bun and Express, featuring a basic ping tool for automation contexts.

Setup Requirements

  • ⚠️Requires Bun runtime (v1.3.3 or compatible) to execute the Node.js server.
  • ⚠️The `README.md` specifies `bun run index.js` which only prints 'Hello via Bun!' and does not start the actual MCP server. The correct command to start the MCP server is `bun run server.js`.
  • ⚠️The `manifest.json` describes a `/ping` tool with an `endpoint` of `http://localhost:3030/ping`. While `server.js` starts an MCP server on `localhost:3030` and internally defines a 'ping' tool, the primary interaction is via `/mcp`. A separate `mcp_server.py` file *does* expose a `/ping` endpoint, suggesting it might be an expected external service or a potential misconfiguration/redundancy.
Verified SafeView Analysis
The project uses `dotenv` for environment variable loading, which is a good practice for managing configurations and secrets, though no specific environment variables are explicitly referenced in the provided `server.js` code. The core server functionality relies on the `@modelcontextprotocol/sdk`, whose security would depend on its own implementation. An Express server is used, which is a mature framework. No `eval` or obvious obfuscation is present. The presence of a separate `mcp_server.py` (FastAPI) in the repository is ambiguous but is likely a separate component or example not directly integrated with the Bun server.
Updated: 2025-12-03GitHub→
PreviousPage 399 of 713Next