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
Low Cost

git-context

by osick

Sec10

Unable to determine the use case due to the absence of file content or a README.

Verified SafeView Analysis
No files were provided for analysis, therefore no security risks like 'eval', obfuscation, or network risks could be identified within the project's codebase. The score of 10 reflects the absence of identifiable risks *from the provided content*.
Updated: 2025-11-22GitHub→
0
0
Low Cost
AmitafAdir-RidaFatima icon

mcp-shark-viewer-vscode

by AmitafAdir-RidaFatima

Sec8

Inspect and analyze Model Context Protocol (MCP) traffic directly within Visual Studio Code, providing real-time network monitoring and debugging capabilities.

Setup Requirements

  • ⚠️Requires Node.js Version 14.x or higher to run `npx` command.
  • ⚠️Requires Visual Studio Code Version 1.56 or later.
  • ⚠️Relies on the `npx` command to download and execute the `@mcp-shark/mcp-shark` package, necessitating an internet connection for the initial server startup.
Verified SafeView Analysis
The extension spawns an external process `npx @mcp-shark/mcp-shark@latest` to run the core server functionality. While this command is hardcoded and not directly susceptible to user input injection, it relies on the integrity and security of the `@mcp-shark/mcp-shark` package from npm. Stopping the server involves `node:child_process.exec` with platform-specific commands (taskkill for Windows, kill for Linux/macOS) targeting a hardcoded port (9853), which is generally safe. There are no obvious hardcoded secrets or arbitrary code execution vulnerabilities found within the provided source code.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
bjoxiah icon
Sec9

Provides a Model Context Protocol (MCP) server for retrieving real-time and historical stock market data and company sentiment using the Alpha Vantage API.

Setup Requirements

  • ⚠️Requires Python 3.10 or higher.
  • ⚠️Requires Poetry for dependency management.
  • ⚠️Requires an Alpha Vantage API key (free tier has a limit of 25 requests/day).
  • ⚠️Requires manual configuration in Claude Desktop's `claude_desktop_config.json` with absolute paths for the virtual environment and project directory.
Verified SafeView Analysis
The server loads sensitive API keys from environment variables, which is a good practice. Error logging specifically redacts the API key from URLs. It uses the `httpx` library for asynchronous HTTP requests with a reasonable timeout. There are no obvious 'eval' statements, obfuscation, or other malicious patterns found in the provided source code. Security risk is primarily dependent on the security of the Alpha Vantage API itself and correct environment variable configuration.
Updated: 2025-11-23GitHub→
0
0
Medium Cost
itripleg icon

moha-maven

by itripleg

Sec8

Maven is an autonomous AI Chief Financial Officer (CFO) assistant that leverages LLMs and MCP for persistent identity, memory, financial decision-making, and treasury operations for the Motherhaven platform.

Setup Requirements

  • ⚠️Requires Docker, PostgreSQL, and Redis for full functionality (orchestrated via docker-compose).
  • ⚠️Requires an Anthropic API Key (paid LLM service) for core AI capabilities.
  • ⚠️Requires the 'mcp' Python package (likely a proprietary client library from Anthropic).
  • ⚠️Requires an EMAIL_API_SECRET for interaction with the motherhaven.app email system.
Verified SafeView Analysis
The project uses environment variables for sensitive API keys (Anthropic, Email API), which is good practice. File uploads (for chart analysis) are handled with `secure_filename` and a restricted set of allowed extensions. External network communication (email API, Hyperliquid API) is standard, but relies on the security of those external services and the provided API keys. Git-first persistence uses `git` commands via `subprocess.run`, which could be a risk if commit messages or file paths were unsanitized user input, but here the commit messages are programmatically generated. The Flask API and MCP server are designed to be exposed locally (or within a Docker network), but if exposed to the public internet without proper firewall rules, they would present a vulnerability. Overall, it follows reasonable security practices for its domain, but like any system handling financial transactions and API keys, caution is advised regarding network exposure and key management.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
Jaskey15 icon

n8n-mcp-server

by Jaskey15

Sec9

Enables Claude to list, inspect, and monitor workflows in a self-hosted n8n instance.

Setup Requirements

  • ⚠️Requires a self-hosted n8n instance with API access and a generated API key.
  • ⚠️Requires Node.js 18 or higher to run.
  • ⚠️Requires manual configuration in Claude Desktop's `claude_desktop_config.json` file, specifying an absolute path to the built server and setting environment variables.
Verified SafeView Analysis
The server demonstrates good security practices by using environment variables for sensitive API keys (`N8N_URL`, `N8N_API_KEY`), performing input validation for tool arguments, and handling various API errors gracefully. It explicitly focuses on read-only operations (inspection and monitoring), significantly reducing the attack surface. No `eval` or `child_process` executions of untrusted input were found. The `README` also provides explicit security recommendations, indicating developer awareness.
Updated: 2025-12-14GitHub→
0
0
Medium Cost
marc-shade icon

universal-ai-chat

by marc-shade

Sec9

Facilitates real-time, cross-platform communication and shared context/memory between different AI assistants like Claude Code, OpenAI Codex CLI, and Google Gemini CLI.

Setup Requirements

  • ⚠️Requires a running Qdrant vector database instance (defaults to localhost:6333).
  • ⚠️Requires `sentence-transformers` or `fastembed` for embedding text (which are installed via `pip install -e '.[vector]'`).
  • ⚠️Requires Python 3.10 or higher.
  • ⚠️The `STORAGE_BASE` environment variable (defaults to `/mnt/agentic-system`) must be a writable directory for SQLite databases.
Verified SafeView Analysis
The server uses SQLite for persistence and Qdrant for vector memory. SQL queries utilize parameter binding to prevent injection. Configuration relies on environment variables, which should be securely managed by the user/system. There is no obvious use of `eval` or `exec` on untrusted input, nor are sensitive hardcoded secrets present. The main `server.py` processes tool calls defined in the code, rather than dynamically executing arbitrary code from agents. Qdrant connection defaults to localhost, implying an expectation of a local/secured Qdrant instance.
Updated: 2025-11-29GitHub→
0
0
Low Cost
agentplexus icon

mcpkit

by agentplexus

Sec9

A toolkit for building MCP (Model Context Protocol) applications and servers in Go, supporting both direct in-process function calls (library mode) and standard MCP transports (server mode) with OAuth 2.1 authentication.

Setup Requirements

  • ⚠️Requires Go 1.24+ and MCP Go SDK v1.2.0+.
  • ⚠️NGROK_AUTHTOKEN environment variable is required if `ngrok` tunneling is used; custom ngrok domains may require a paid plan.
  • ⚠️Proper OAuth 2.1 configuration (Issuer, ClientID, ClientSecret, Users, RedirectURIs) is critical for public servers, especially when integrating with clients like ChatGPT.com.
Verified SafeView Analysis
The project implements OAuth 2.1 with PKCE, Dynamic Client Registration (DCR), and Protected Resource Metadata (RFC 9728, 8414, 7591, 7636). It utilizes cryptographically secure token generation (`crypto/rand`) and constant-time comparisons (`crypto/subtle`) for sensitive operations. A critical open URL redirect vulnerability (CWE-601) in the `isValidRedirectURI` function was identified and promptly fixed in v0.3.1, demonstrating a proactive approach to security. The `oauth2.Config` allows for basic authentication via a `Users` map, which requires careful management of credentials by the implementer, though a custom `Authenticator` can be provided for more robust solutions. `ngrok` integration requires a securely managed `NGROK_AUTHTOKEN`.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
Konkuk-SWA-2025 icon

MCP_server

by Konkuk-SWA-2025

Sec3

This server provides an inventory management and forecasting system, interacting with Google Sheets for data storage and SQLite for user configuration and logs, all exposed as an MCP service.

Setup Requirements

  • ⚠️Requires a Google Service Account JSON key file, hardcoded to 'bold-tooling-466206-a9-960a00bb4c78.json' in the root directory.
  • ⚠️The Google Service Account must have edit permissions for the target Google Sheets.
  • ⚠️The Prophet library, used for forecasting, can have complex installation requirements, potentially needing C++ compilers (like gcc or clang).
Review RequiredView Analysis
CRITICAL: The Google Service Account JSON key file path (`KEY_FILE_PATH`) is hardcoded in the source code. This is a severe security vulnerability as it exposes sensitive credentials and should be loaded from environment variables or a secure secret management system. The application also logs potential errors, which is good, but the core credential handling is unsafe.
Updated: 2025-12-02GitHub→
0
0
Medium Cost
harshdespande icon

MCP_Server_Project

by harshdespande

Sec8

An interactive command-line interface application for chatting with AI models via the Anthropic API, supporting document retrieval, command-based prompts, and extensible tools.

Setup Requirements

  • ⚠️Requires Anthropic API Key (Paid)
  • ⚠️Requires Python 3.9+
  • ⚠️The project contains TODOs in `mcp_server.py` and `mcp_client.py` which indicate incomplete MCP features.
Verified SafeView Analysis
The application runs locally with subprocess communication via stdio, limiting external attack surfaces. The 'edit_document' tool allows AI to modify in-memory document content, which could lead to data integrity issues if the AI is prompted maliciously, but it does not affect the file system or external resources. No hardcoded secrets or obvious malicious patterns were found. Requires an Anthropic API key, which should be protected.
Updated: 2025-12-02GitHub→
0
0
Medium Cost
Decentralised-Jobs-Protocol icon

djp-jobmcp

by Decentralised-Jobs-Protocol

Sec9

An MCP server that provides access to decentralized job listings from the Nostr network, offering search, detail retrieval, and market statistics tools for LLMs.

Setup Requirements

  • ⚠️Requires a Rust development environment to build and run.
  • ⚠️The server must be run as a standalone binary/process (`./target/release/jobmcp`) before interacting with it via an MCP client (e.g., Goose).
  • ⚠️Binds to `localhost:9993`, so client must have network access to this address (typically run on the same machine).
Verified SafeView Analysis
The server is implemented in Rust, which inherently offers strong memory safety. It binds to `127.0.0.1:9993` by default, limiting external exposure. Nostr relay URLs are public and not treated as secrets. No 'eval' or obvious dynamic code execution from untrusted input is present. Input arguments are typed, reducing injection risks. Performance metrics are logged, but no sensitive data is exposed through them. The `dotenvy` crate is used for environment variables, but `PORT` is the only one identified, which is not sensitive. Overall, the design appears robust against common web vulnerabilities.
Updated: 2025-12-14GitHub→
0
0
Medium Cost
kolikaran1992 icon

teacher_dsa

by kolikaran1992

Sec9

This MCP server acts as an AI assistant to track and guide a user's progress on LeetCode Data Structures & Algorithms problems, logging attempts and patterns without providing full solutions.

Setup Requirements

  • ⚠️Requires Python 3.10+.
  • ⚠️Requires internet access to query the LeetCode GraphQL API.
  • ⚠️Managed by Poetry; users need to install dependencies via `poetry install`.
  • ⚠️Designed to run as an MCP server via stdio, meaning it expects to be driven by an external LLM agent or orchestrator.
Verified SafeView Analysis
The server uses the 'requests' library to interact with the official LeetCode GraphQL API. It constructs URLs and payloads using a provided 'title_slug', rather than allowing arbitrary user-supplied URLs, which significantly mitigates SSRF and injection risks. No 'eval' or obvious obfuscation is present. Configuration uses Dynaconf with environment variable support ('SECRETS_DIRECTORY', 'TEACHER_DSA_'), indicating proper handling for secrets, though no external API keys are explicitly required by the LeetCode API interaction shown. The primary risk would be potential vulnerabilities in the LeetCode GraphQL endpoint itself, or if sensitive data were unexpectedly passed through the title_slug.
Updated: 2025-11-26GitHub→
0
0
Low Cost
dggnzs123 icon
Sec5

This project provides a flashing tool built on the fastmcp framework, likely for embedded devices or hardware.

Setup Requirements

  • ⚠️Requires fastmcp framework
  • ⚠️Likely requires specific hardware and drivers for flashing functionality
Review RequiredView Analysis
No actual source code files were provided for analysis beyond the README. Therefore, a comprehensive security audit for 'eval', obfuscation, network risks, hardcoded secrets, or malicious patterns could not be performed. Running flashing tools from unknown sources carries inherent risks.
Updated: 2025-11-28GitHub→
PreviousPage 376 of 713Next