Stop Searching. Start Trusting.

The curated directory of MCP servers, vetted for security, efficiency, and quality.

Browse Directory Why 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)

Low Cost

mcp-atlas

by AbhishekRP2002

Sec9

A Python library for indexing, organizing, and discovering tools across multiple MCP servers.

Setup Requirements

⚠️Requires Python 3.11 or higher.
⚠️Uses PDM (Python Development Master) as the build backend, which might require users to install PDM.

Verified SafeView Analysis

The provided source code is extremely minimal, consisting mainly of project metadata. There are no obvious security risks like 'eval', obfuscation, hardcoded secrets, or direct network operations visible in this snippet. The project setup in pyproject.toml appears standard. A higher score is given due to the lack of visible attack surface in the provided code, but this assumes the full implementation would also follow best practices.

Updated: 2025-11-27GitHub→

Low Cost

mcp-server

by y-yfan

Sec1

A simple server implementation likely for a specific protocol, potentially related to Minecraft Coder Pack (MCP).

Review RequiredView Analysis

No executable source code was provided for analysis beyond the README.md. Therefore, a meaningful security audit for 'eval', obfuscation, hardcoded secrets, network risks, or malicious patterns is impossible. The low score reflects the inability to verify the safety of running unknown code.

Updated: 2026-01-19GitHub→

Low Cost

python-webapp-base

by ursweiss

Sec7

An AI-powered development monitoring and debugging server for FastAPI applications, providing real-time insights into application health, logs, errors, and performance metrics to AI assistants like GitHub Copilot.

Setup Requirements

⚠️Python 3.11+ required
⚠️Docker and Docker Compose (for containerized deployment)
⚠️VS Code with GitHub Copilot (MCP support) for full AI integration

Verified SafeView Analysis

The server is explicitly designed for development and includes features like `SECRET_KEY` validation for production. It uses file-based IPC (`.dev/` directory) and `os.kill` for application control, which are privileged operations. While these could be risks in a production context, the project clearly states it's for development only and is excluded from Docker builds. Potential risks include malicious regex patterns via AI-provided input to log search tools, or PID manipulation for `restart_app` if the `.dev/state.json` file could be tampered with. However, these are mitigated by its confined development-only scope.

Updated: 2025-11-29GitHub→

Low Cost

eminem-bio

by worklocalinc

Sec5

Serves a static biography website for Eminem.

Setup Requirements

⚠️Requires an operational MCP Server environment for deployment.

Review RequiredView Analysis

Cannot perform a comprehensive security audit as only the README.md file was provided. No actual server or application code was available for analysis of patterns like 'eval', obfuscation, network risks, or hardcoded secrets.

Updated: 2025-11-26GitHub→

Low Cost

appium_mcp_server

by hemandhran

Sec2

Provides a server with tools to control and interact with Appium, Android emulators, and iOS simulators for mobile test automation.

Setup Requirements

⚠️Requires extensive mobile development environment setup: Python, Node.js, npm, Appium (globally installed), Android SDK, and for iOS, Xcode with Command Line Tools and a configured WebDriverAgent (macOS only).
⚠️The `ANDROID_HOME` or `ANDROID_SDK_ROOT` environment variable must be correctly set and accessible to the server process.
⚠️All iOS-related features, including simulator/device management and Xcode project building, are only available on macOS.

Review RequiredView Analysis

CRITICAL: The `run_parallel_tests` function uses `subprocess.Popen` with `shell=True` and a user-provided `test_command_pattern` which includes a placeholder (`{udid}`). This design allows for arbitrary command injection by an attacker controlling the `test_command_pattern` input, leading to potential remote code execution on the host machine where the server is running. The `start_appium_server` tool enables `--allow-cors` for the Appium server, which, while typically a local instance, could pose a risk if the MCP server or Appium server itself were made accessible beyond localhost without proper authentication.

Updated: 2025-12-15GitHub→

Low Cost

imessage-max

by cyberpapiii

Sec9

Enables AI assistants to securely read, search, and send iMessages on macOS with proper contact resolution and media enrichment.

Setup Requirements

⚠️Requires Full Disk Access for the Python interpreter/uvx to read ~/Library/Messages/chat.db.
⚠️Requires Contacts access for the Python interpreter/uvx to resolve phone numbers to contact names.
⚠️Requires Automation permission for Messages.app (when prompted) for the 'send' tool to function.

Verified SafeView Analysis

The server explicitly uses read-only access for the iMessage database and leverages macOS's Contacts framework for contact resolution, respecting system permissions. The 'send' functionality, which interacts with Messages.app via AppleScript, includes input sanitization to prevent injection attacks. External network calls for link enrichment are handled with timeouts. Clear instructions for granting required macOS permissions (Full Disk Access, Contacts, Automation) are provided, ensuring transparency and user control. No obvious 'eval' or obfuscation is present.

Updated: 2026-01-19GitHub→

Low Cost

Claude-Patent-Creator

by RobThePCGuy

Sec8

A USPTO patent creation and analysis system with dual-mode architecture, providing programmatic access via an MCP server and interactive workflows as a Claude Code plugin.

Setup Requirements

⚠️Requires Google Cloud Project with billing enabled and 'gcloud' authentication for BigQuery patent search.
⚠️Requires NumPy version pinned to '<2.0.0' due to FAISS compatibility issues.
⚠️Requires system-wide Graphviz installation for diagram generation (e.g., 'sudo apt install graphviz' on Linux).

Verified SafeView Analysis

The project adheres to good security practices by explicitly using environment variables for API keys (Google Cloud, Anthropic, OpenAI, USPTO). It also uses trusted open-source models (BGE-base-en-v1.5, MS-MARCO MiniLM-L-6-v2) and standard cloud services (BigQuery). Network operations are primarily for downloading public data and interacting with well-known APIs. The primary security considerations involve proper management of user-provided API keys and Google Cloud credentials.

Updated: 2025-12-02GitHub→

Medium Cost

pipelane-server

by shiveshnavin

Sec1

A server for building, scheduling, and managing custom data pipelines, integrating with AI agents via the Model Context Protocol (MCP) and providing a GraphQL API for interaction.

Setup Requirements

⚠️Requires `sqlite3` npm package for SQLite persistence, or connection details for MySQL.
⚠️The client-side UI needs to be built using `cd client && npm run build` before the server can be fully started.
⚠️Integration with AI models (e.g., Google Gemini) requires setting the `GEMINI_API_KEY` environment variable.
⚠️For HTTPS, `PIPELANE_HTTPS_KEY_PATH` and `PIPELANE_HTTPS_CERT_PATH` environment variables pointing to valid SSL certificate files are required.

Review RequiredView Analysis

Critical security risks identified: 1. Direct use of `eval(js)` in `EvaluateJsTask` and related functions (`evalPlaceHolder.evaluatePlaceholdersInString`, `evalPlaceHolder.evalInScope`) allows arbitrary JavaScript code execution from user-defined pipeline inputs or task configurations. This is a severe Remote Code Execution (RCE) vulnerability. 2. `ShellTask` and `LoopShellTask` allow execution of arbitrary shell commands. The `allowedCommands` filter, as configured in `server/pipe-tasks/index.ts`, can include `"*"`, effectively bypassing all restrictions and enabling RCE via shell injection. These vulnerabilities make the system unsafe for untrusted users or without robust sandboxing.

Updated: 2026-01-19GitHub→

High Cost

claude-data-analysis-ultra-main

by zenyrae123

Sec9

Automated, multi-dimensional e-commerce data analysis and business intelligence reporting.

Setup Requirements

⚠️Requires Python 3.8+ with specific data science packages (pandas, numpy, scipy, matplotlib, seaborn).
⚠️Designed to run within a Claude Code environment, leveraging its sub-agents, skills, and slash commands (`/do-more`, `/do-all`).
⚠️Relies on local data files located in a `data_storage/` directory for analysis.

Verified SafeView Analysis

The project extensively uses standard data science libraries (pandas, numpy, scikit-learn, matplotlib, seaborn). There are no direct malicious patterns, `eval` of arbitrary user input, or hardcoded sensitive credentials observed in the provided code snippets. The documentation explicitly mentions security practices like `validate-analysis` hooks to check for dangerous code patterns (e.g., `os.system`, `eval`, `exec`, `subprocess`) and `allowed-tools` to limit skill permissions, indicating a focus on security within the Claude Code environment.

Updated: 2026-01-19GitHub→

Medium Cost

gemini-mcp

by LanceVCS

Sec9

Provides multi-turn conversational support for the Gemini CLI, allowing a client application (like Claude Code) to maintain context across multiple interactions with Gemini.

Setup Requirements

⚠️Requires Gemini CLI to be installed and configured (including authentication and potential API key setup, which usually involves costs).
⚠️Requires Node.js 14.0 or higher.
⚠️Conversations auto-expire after 2 hours or when the maximum of 25 concurrent conversations is reached.

Verified SafeView Analysis

The server spawns the 'gemini' CLI process using `child_process.spawn`. Critical security mitigations include: 1) Explicit whitelisting of 'SAFE_TOOLS' which notably *excludes* dangerous commands like `run_shell_command`, `browser_run_code`, `browser_evaluate`, etc. 2) The `gemini` CLI is run with the `--sandbox` flag, which restricts file system access. 3) User prompts are passed as arguments to the `gemini` CLI, preventing direct shell injection by using an array of arguments rather than a single concatenated string. No 'eval' or direct arbitrary code execution is present within the MCP server's logic itself. The primary remaining risk lies with potential vulnerabilities within the Gemini CLI itself, particularly how it processes input when run with the specified arguments and sandbox restrictions.

Updated: 2025-12-17GitHub→

Medium Cost

mcp-openfoodtox

by sakkkysaka

Sec9

Access, search, and analyze EFSA's OpenFoodTox chemical hazards dataset to explore food safety information, toxicity endpoints, risk assessments, and substance safety profiles.

Setup Requirements

⚠️Requires Python 3.12 or later.
⚠️Requires 'uv' for Python package management.
⚠️The local SQLite database (`openfoodtox.db`) must be populated, which depends on the availability of the large source Excel file (`OpenFoodToxTX22809_2023.xlsx`) for initial setup.

Verified SafeView Analysis

The server uses `sqlite3` and `pandas.read_sql_query` for database interactions. All queries observed utilize parameterized inputs (`params=...`), which effectively prevents SQL injection vulnerabilities. No `eval` or `exec` functions were found, nor were any hardcoded secrets or malicious patterns detected. The `FastMCP` server is configured to run with `transport='stdio'`, implying local communication typically used for LLM agent integration, which limits its direct network attack surface. However, `httpx` is a dependency, and the README mentions 'Active internet connection for updates and dataset access', suggesting external network calls might occur as part of a broader system or initial setup not directly within the provided server runtime logic.

Updated: 2026-01-19GitHub→

High Cost

gemini-mcp

by mesolimbo

Sec9

A Model Context Protocol (MCP) server providing local access to Google's Gemini 3 Pro Preview API for integration with tools like Claude Code.

Setup Requirements

⚠️Requires a Google Gemini API Key (obtain from aistudio.google.com/apikey)
⚠️Requires Node.js version >= 22.21.0
⚠️Requires creation and editing of `config.json` from `config.json.example` to provide the API key.

Verified SafeView Analysis

The server uses `config.json` for the Gemini API key, which is explicitly `gitignored` as per best practices. It does not contain `eval` or obvious obfuscation. Network interaction is limited to calls to the Google Gemini API. It runs locally via stdio, not exposing external network ports, which is generally secure. Configuration validation for the API key is present at startup.

Updated: 2026-01-07GitHub→

PreviousPage 292 of 713Next