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)

32
2
Medium Cost
Shaumik-Ashraf icon

mcp-fhir-patient-index

by Shaumik-Ashraf

Sec5

A Ruby on Rails Master Patient Index (MPI) server with a user-friendly UI, a conformant FHIR API (R4), and Model Context Protocol (MCP) support for LLM integration, focused on managing patient demographic data.

Setup Requirements

  • ⚠️Requires Ruby 3.3 to be installed.
  • ⚠️Requires Yarn 1.x for JavaScript dependencies.
  • ⚠️Requires regeneration of Rails credentials and SOC-II compliance for production use with real patient data.
Review RequiredView Analysis
The README explicitly warns that the application is 'not ready for real-patient data out of the box' and requires credential regeneration and SOC-II compliance for real-world use. It implements basic Rails security features like strong parameters and filtering sensitive logs (e.g., SSN). The `format_ssn` helper masks SSN in the UI based on a setting, but the raw data is stored. CSRF protection is skipped for the MCP API endpoint, which is common for API-only controllers. There are no obvious hardcoded secrets directly in the repository for critical configurations (it uses Rails credentials and environment variables for deployment). No 'eval' or malicious patterns are evident.
Updated: 2025-11-26GitHub→
32
2
Low Cost
nico-martin icon

joke-mcp

by nico-martin

Sec8

Provides a Model Context Protocol (MCP) and REST API endpoint to fetch filtered jokes from JokeAPI.

Setup Requirements

  • ⚠️Requires PHP 8.0+.
  • ⚠️Dependencies must be installed via Composer (`composer install`).
  • ⚠️The 'data' directory and 'data/mcp_sessions.json' file must be writable by the web server process for session management.
Verified SafeView Analysis
Origin validation is implemented for server-side checks, although `Access-Control-Allow-Origin: *` is used for browser CORS. Session IDs are cryptographically secure. Relies on file-based session storage (`data/mcp_sessions.json`) which requires proper directory write permissions and could have concurrency issues under heavy load, but is generally safe for its intended use. External API calls are made with a timeout and user agent, and safe-mode is enforced for jokes.
Updated: 2025-11-24GitHub→
32
1
Medium Cost
Code-MonkeyZhang icon

netease-mcp-server

by Code-MonkeyZhang

Sec8

Enables AI agents to control NetEase Cloud Music desktop application, manage music playback, and access user data like playlists and recommendations via its OpenAPI.

Setup Requirements

  • ⚠️Requires macOS or Windows operating system.
  • ⚠️NetEase Cloud Music desktop client is recommended for full playback control.
  • ⚠️Requires manual configuration of the absolute project path in `settings.json` for MCP client integration.
Verified SafeView Analysis
The server stores session cookies in a cleartext JSON file (`src/storage/cookies.json`) locally. While this is explicitly stated to be for local privacy, it means the file contains sensitive authentication data. If the local system is compromised or file permissions are lax, these cookies could be exposed. The server uses `pyncm` for API interactions and `subprocess.run` / `os.startfile` for opening local QR code images and URL schemes for playback, which are generally safe operations given controlled inputs. No 'eval' or other direct command injection vectors from user input were found.
Updated: 2026-01-19GitHub→
32
2
Medium Cost
bit2me-dev icon

bit2me-mcp

by bit2me-dev

Sec9

Interact with the Bit2Me cryptocurrency exchange ecosystem to access real-time market data, manage wallets, execute trading operations, and query products like Earn (staking) and Loans via AI assistants.

Setup Requirements

  • ⚠️Requires Node.js v18 or higher.
  • ⚠️Requires a verified Bit2Me account and valid API Keys (BIT2ME_API_KEY, BIT2ME_API_SECRET) with appropriate permissions. Do NOT enable 'Withdrawal' permissions for API Keys.
  • ⚠️Manual configuration of `claude_desktop_config.json` is needed with absolute paths and environment variables.
  • ⚠️Interactions might be affected by Bit2Me API rate limits; the server includes automatic retries with exponential backoff, but excessive requests will still fail.
Verified SafeView Analysis
The server follows strong security practices. API keys are loaded from environment variables (or .env) and not hardcoded. Sensitive data is redacted from logs. API requests are signed using HMAC-SHA512 with SHA256 hashing. The `README.md` explicitly warns against enabling 'Withdrawal' permissions for API keys. It employs circuit breakers and rate limiters for resilience and abuse prevention. Pre-commit hooks include secret scanning (`gitleaks`) and `npm audit`. User input is validated to prevent common injection attacks.
Updated: 2026-01-19GitHub→
32
2
Low Cost
seanivore icon

claud-coin

by seanivore

Sec9

To incentivize contributions and knowledge sharing within AI developer communities on the Solana blockchain, particularly through Model Context Protocol (MCP) integration, token rewards, and an achievement system.

Setup Requirements

  • ⚠️Requires Rust development environment
  • ⚠️Requires Solana CLI tools
  • ⚠️Requires understanding of Solana blockchain development
Verified SafeView Analysis
The Solana program follows standard security practices for its current development phase, including signer checks and rent exemption. The project's documentation (e.g., "RISK_ANALYSIS.md", "01_MCP_TRANSPORT_LAYER.md", "06_INFRASTRUCTURE_REQUIREMENTS.md") demonstrates a strong proactive approach to security with detailed plans for TLS, authentication, rate limiting, and comprehensive audits. Current Rust code includes `TODO`s for critical future features like full SPL Token integration and complete achievement claim validation, which will require careful implementation to maintain security. Minor potential for `u64` overflow in counters (`total_tool_uses`, `total_complexity`, `times_claimed`) is present, but given `u64`'s large range, it's highly improbable for typical usage.
Updated: 2025-11-29GitHub→
32
2
High Cost

pypi-mcp

by AstroAir

Sec8

Provides AI models with a Model Context Protocol (MCP) server to query PyPI package information, analyze dependencies, check vulnerabilities, and manage Python package data.

Verified SafeView Analysis
The project uses standard Python practices and includes a SECURITY.md file, indicating awareness. It does not appear to contain 'eval' or obfuscated code. The main security consideration is that the server, when run with HTTP transport using '--host 0.0.0.0', will be publicly accessible without inherent authentication/authorization for the MCP tools. While suitable for local AI agent use, public exposure would require external security measures.
Updated: 2025-11-17GitHub→
32
2
Medium Cost
OrionHubScript icon

fetch-mcp

by OrionHubScript

Sec8

Serves as an MCP server to fetch URLs and YouTube video transcripts efficiently.

Setup Requirements

  • ⚠️Requires a JavaScript runtime (Node.js or Bun) for execution.
  • ⚠️Primarily designed as a Model Context Protocol (MCP) server, expecting an MCP client for interaction.
  • ⚠️The SSE server mode listens on port 3000 by default, configurable via the `PORT` environment variable.
  • ⚠️Project is built using Bun, implying Bun is the preferred build tool if building from source.
Verified SafeView Analysis
The server uses `got-scraping` for network requests, which includes some anti-bot features. No `eval` or direct command injection vectors were found. The `fetch_url` tool directly accepts a URL, which could pose a limited Server-Side Request Forgery (SSRF) risk if not used in a controlled environment or if URL validation were not strict enough to prevent access to internal networks. No hardcoded secrets were identified.
Updated: 2025-12-15GitHub→
32
2
High Cost
ibuuzm icon
Sec7

An AI-powered trading assistant designed for market analysis, automated trade execution, and financial decision support.

Setup Requirements

  • ⚠️Requires API keys for multiple LLM providers (e.g., OpenRouter, DeepSeek, Google, Grok, OpenAI).
  • ⚠️Requires a Polygon.io API key for market data, and a Brave Search API key for research.
  • ⚠️Requires Pushover API keys for push notifications.
  • ⚠️Requires Node.js and npm/npx in addition to Python (3.12+) and uv for running external MCP servers.
Verified SafeView Analysis
The system processes sensitive financial transactions (buying/selling shares) through AI agents interacting with MCP tools. API keys for various LLM providers, market data (Polygon), Brave Search, and push notifications (Pushover) are correctly loaded from environment variables, preventing hardcoding. SQL database interactions use parameterized queries. However, the reliance on external `uvx` and `npx` commands to run third-party MCP servers (e.g., `mcp_polygon`, `@modelcontextprotocol/server-brave-search`, `mcp-memory-libsql`) introduces supply chain risks if these external packages are compromised. The core risk lies in the autonomous nature of AI agents making real-time financial decisions.
Updated: 2026-01-19GitHub→
32
2
High Cost
Omkarjamadar icon
Sec5

Provides an AI-driven interface to control a macOS computer by automating tasks through accessibility features and a conversational agent loop.

Setup Requirements

  • ⚠️Requires macOS as the operating system for the desktop control server. (Windows and Linux implementations are placeholders.)
  • ⚠️Requires manual granting of 'Accessibility' permissions for the server application in macOS System Settings.
  • ⚠️Requires an Anthropic API Key (ANTHROPIC_API_KEY) configured as an environment variable.
  • ⚠️The Rust-based desktop control server (mcp-server-os-level) must be running separately and locally (on 127.0.0.1:8080) for the clients to function.
Review RequiredView Analysis
The system grants AI direct control over the operating system, allowing it to perform actions like launching applications, typing, clicking, and pressing keys. This is inherently a high-risk operation. While the client-side components (Next.js and CLI) communicate with the Rust-based desktop control server over a local HTTP connection (127.0.0.1:8080), a compromised AI model or malicious prompt could execute arbitrary, potentially destructive commands on the user's machine (e.g., 'delete all files'). The macOS server explicitly requires user-granted accessibility permissions, which is a necessary safeguard. No hardcoded API keys are found within the client code that would be exposed to the browser, as they are loaded from environment variables and used server-side in Next.js API routes. The core risk is the nature of giving AI full system control and the trust placed in the AI's reasoning and the input prompts.
Updated: 2026-01-19GitHub→
32
1
Low Cost
pholex icon
Sec8

This is a Model Context Protocol (MCP) server for querying and executing scheduled tasks in Qinglong Panel.

Setup Requirements

  • ⚠️Requires a running Qinglong Panel instance with Open API enabled.
  • ⚠️Requires obtaining CLIENT_ID and CLIENT_SECRET from the Qinglong Panel.
  • ⚠️Configuration requires manually editing the .env file in ~/.qinglong-mcp/.
Verified SafeView Analysis
The server handles credentials (CLIENT_ID, CLIENT_SECRET) via environment variables loaded from .env files, which is good practice. It makes outgoing HTTP requests to the configured QINGLONG_URL. No 'eval' or direct code execution from untrusted input is found. Security relies heavily on the secure storage of the .env file and the security posture of the target Qinglong Panel.
Updated: 2025-12-09GitHub→
32
15
High Cost
xxyyue icon
Sec3

A headless IDA Pro server for remote, programmatic binary analysis and reverse engineering via the Model Context Protocol (MCP).

Setup Requirements

  • ⚠️Requires IDA Pro 9.1.0 or later installed.
  • ⚠️Requires Python 3.12 or higher.
  • ⚠️Requires the IDADIR environment variable to be set to the IDA Pro installation directory.
Review RequiredView Analysis
The `py_eval` tool allows execution of arbitrary Python code within the IDA context. While intended as a powerful feature for analysis agents, this is a critical security risk if the server is exposed to untrusted input or if not run in a strictly isolated and trusted environment. The server can also be configured to listen over HTTP/SSE, which introduces network-based attack vectors if not properly secured with authentication and authorization. No apparent hardcoded secrets in the server's own code.
Updated: 2025-12-30GitHub→
32
2
Low Cost
Montimage icon

sec-mcp

by Montimage

Sec9

This server provides real-time security checks for domains, URLs, and IP addresses against multiple blacklists, designed to be integrated into Python applications, used via CLI, or run as an MCP server to enrich LLM context with threat intelligence.

Setup Requirements

  • ⚠️Requires Python 3.11+.
  • ⚠️Initial setup requires running 'sec-mcp update' to download and populate blacklist data; without it, the blacklist will be empty.
  • ⚠️For optimal performance, set the environment variable 'MCP_USE_V2_STORAGE=true' before running the server, as the default v1 storage is significantly slower.
Verified SafeView Analysis
The project uses standard Python libraries (sqlite3, httpx) with proper parameterization to prevent common vulnerabilities like SQL injection. Input validation is applied to network requests. It relies on external public blacklist feeds, which is inherent to its function, but the project itself does not introduce new network-related risks or hardcoded secrets. File system interactions for local database and downloads are handled safely. The overall design is security-conscious.
Updated: 2025-11-23GitHub→
PreviousPage 184 of 760Next