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)

30
1
Low Cost
tbrandenburg icon

acp-inspector

by tbrandenburg

Sec9

A visual testing and debugging tool for Agent Client Protocol (ACP) servers and agents.

Setup Requirements

  • ⚠️Requires Node.js >=18.0.0
  • ⚠️Project is in early, active development; features are incomplete and subject to change.
Verified SafeView Analysis
The provided source code is minimal and acts as a placeholder. It does not contain any 'eval', obfuscation, hardcoded secrets, or directly malicious patterns. The `index.js` merely logs a message and exports a version number, posing no immediate security risk. However, the project is under active development and plans include a web-based UI and a proxy server architecture. These future components will require careful implementation to mitigate standard web application and network security risks.
Updated: 2026-01-17GitHub→
30
2
Medium Cost
domdomegg icon

shell-exec-mcp

by domdomegg

Sec1

Provides a Model Context Protocol (MCP) server for executing arbitrary bash commands, supporting both foreground execution with timeouts and background job management.

Setup Requirements

  • ⚠️Requires Node.js to be installed on the host system.
  • ⚠️Commands are executed with the privileges of the Node.js process running the MCP server, posing a significant privilege escalation risk if exposed to untrusted input or run with elevated permissions.
  • ⚠️Long-running or resource-intensive bash commands can consume significant CPU, memory, or I/O on the host, potentially impacting system stability or other processes.
Review RequiredView Analysis
The primary function of this server is to execute arbitrary bash commands via `node:child_process.spawn`. If the server is exposed to untrusted input, it presents an extremely high security risk, as an attacker could execute any command on the host system, including deleting files, accessing sensitive information, or installing malicious software. The HTTP transport option further amplifies this risk by making it network-accessible. This server is designed to perform highly privileged operations; its security depends entirely on the caller's trustworthiness and stringent input validation *before* calling this server, not on the server's internal mechanisms.
Updated: 2026-01-07GitHub→
30
1
High Cost
docer1990 icon

visiontest

by docer1990

Sec9

Serves as an MCP (Model Context Protocol) server to enable LLMs and AI agents to interact with and automate native mobile applications on Android devices and iOS simulators.

Setup Requirements

  • ⚠️Requires JDK 17+ and Kotlin 2.1+ for the MCP server.
  • ⚠️Full Android functionality requires Android Platform Tools (ADB) in PATH and Android SDK for building the Automation Server APKs.
  • ⚠️iOS simulator support requires Xcode Command Line Tools (macOS only).
  • ⚠️Automation server requires manual installation of two APKs (main and test) on the Android device, with USB Debugging enabled (min SDK 21, target SDK 34).
Verified SafeView Analysis
The server demonstrates robust security practices, especially in command execution. It uses allowlists for ADB subcommands and strong regular expressions (`DANGEROUS_SHELL_CHARS`) to validate user-provided arguments, preventing shell injection. Android's automation server runs via instrumentation, isolated on the device, and requires explicit `adb forward` for host communication. JSON parameter serialization for the automation client is handled by Gson, mitigating JSON injection risks. No hardcoded secrets or malicious patterns were detected. Reflection is used for advanced UI hierarchy dumping, which is a common, well-justified technique in mobile automation tools (like Maestro) but inherently carries a minor risk of breaking with future Android versions.
Updated: 2026-01-16GitHub→
30
1
Medium Cost
dgwoOstjfn icon
Sec8

Enables AI assistants to programmatically interact with Siemens TIA Portal projects, facilitating tasks such as opening projects, reading/writing PLC blocks, compiling code, and managing PLC tags and User-Defined Types (UDTs).

Setup Requirements

  • ⚠️Requires Windows operating system to run TIA Portal and its COM-based Openness API.
  • ⚠️TIA Portal (V15.1, V16, V17, V18, V19, or V20) must be installed and have the TIA Openness API enabled, which requires an appropriate license.
  • ⚠️Python 3.9 or higher is required, with Python 3.11 recommended.
  • ⚠️Installation of .NET Framework might be necessary to resolve `pythonnet` dependency issues.
Verified SafeView Analysis
The server explicitly states it runs locally only, eliminating external network attack vectors for the server itself. It includes input sanitization for file paths and block names, and uses secure temporary file creation methods (e.g., `tempfile.mkdtemp`). Logs are correctly routed to `stderr` to avoid interfering with the MCP protocol output. However, the system relies on the Siemens TIA Portal Openness API, which is a Windows COM-based API. This introduces an inherent, external attack surface associated with TIA Portal itself and its necessary permissions (often administrative), which is beyond the direct control of this Python code. No explicit 'eval' or hardcoded sensitive credentials were found in the provided source.
Updated: 2025-12-14GitHub→
30
1
Low Cost
bautiroalt icon

MCP-Server

by bautiroalt

Sec3

A unified server for managing Model Context Protocols, integrating AI analytics (META-MINDS), file operations, real-time streaming, and monitoring with an admin panel and advanced security features.

Setup Requirements

  • ⚠️Requires Python 3.8+ and Node.js 16+.
  • ⚠️MongoDB and Redis are optional but required for full Docker deployment and persistence features.
  • ⚠️Requires environment variables (e.g., JWT_SECRET_KEY, API_KEY, database credentials) to be configured via a `.env` file or system environment.
  • ⚠️Default admin credentials 'Jatin23K' / '#JK2025sy#' are present in 'backend/data/users/users.json' and should be changed immediately.
Review RequiredView Analysis
The server has critical security risks related to file system interaction. The MCP Tools (`read_file`, `write_file`, `list_directory`, `search_files`) and File Management API endpoints (`/files/{file_path:path}`) directly use user-provided paths without sufficient validation against directory traversal attacks (e.g., `../`). This could allow unauthorized access, modification, or deletion of arbitrary files outside intended data directories. Additionally, default admin credentials (`Jatin23K`, `#JK2025sy#`) are hardcoded in `backend/data/users/users.json`, which is a common vulnerability if not changed. The broad CORS policy (`Access-Control-Allow-Origin: *`) configured for development in `firebase.json` and potentially in `main.py` poses a risk if not restricted for production APIs. While some security measures like JWT authentication, bcrypt, rate limiting, and input sanitization methods are present in `security_manager.py`, their application is not consistently demonstrated or robust enough to mitigate direct file system access vulnerabilities.
Updated: 2026-01-19GitHub→
30
1
Medium Cost
aplaceforallmystuff icon

mcp-pickaxe

by aplaceforallmystuff

Sec9

Connects AI assistants to the Pickaxe platform for managing AI agents, knowledge bases, users, and analytics via natural language.

Setup Requirements

  • ⚠️Requires Node.js 18+.
  • ⚠️Requires a Pickaxe.co account with API access and at least one Pickaxe Studio API key.
  • ⚠️Configuration involves manually editing a JSON configuration file for your MCP client (e.g., Claude Desktop/Code) to specify the server command and set environment variables for Pickaxe API keys.
Verified SafeView Analysis
The server operates using the Model Context Protocol (MCP) with StdioServerTransport, meaning it communicates via standard input/output as a child process, rather than exposing network ports directly, significantly reducing the external attack surface. API keys are correctly handled via environment variables, preventing hardcoding. Input schemas for tools provide basic validation. The code does not use 'eval' or other highly dynamic/dangerous functions. Error handling for API calls is present. No immediate critical vulnerabilities are apparent in the provided source.
Updated: 2026-01-16GitHub→
30
1
Low Cost
Frank4112 icon
Sec9

Provides a token-efficient interface to Large Language Models (LLMs) by serving domain-specific language commands and documentation from a Notion knowledge base.

Setup Requirements

  • ⚠️Requires a Notion account with API access and a Notion API_TOKEN environment variable.
  • ⚠️The Notion database ID (COMPTEXT_DATABASE_ID) must be configured, though a default is provided.
  • ⚠️For MCP client integration, specific client configurations (e.g., Claude Desktop, Cursor) are required.
Verified SafeView Analysis
The server demonstrates strong security practices including comprehensive input validation and output sanitization to prevent common injection attacks. Secrets (Notion API token) are correctly handled via environment variables. Rate limiting is implemented on all REST API endpoints to mitigate DoS attacks. Dependencies are explicitly managed and updated for known vulnerabilities. Docker builds follow security best practices like using non-root users. The main security considerations are the default permissive CORS setting and the lack of API key authentication for the public REST API, both of which are clearly documented as needing hardening for production deployments. No 'eval' or malicious patterns were identified in the provided source code.
Updated: 2026-01-19GitHub→
30
1
Medium Cost
joshuacook icon

motoko

by joshuacook

Sec6

A personal knowledge management system that uses AI agents to manage structured data in local markdown files and external data lakes, alongside an interactive chat interface and automated maintenance.

Setup Requirements

  • ⚠️Requires ANTHROPIC_API_KEY environment variable (Paid Claude API access is necessary).
  • ⚠️Assumes the `uv` package manager for installation (`uv sync`) and running scripts (`uv run`).
  • ⚠️Requires the `WORKSPACE_PATH` environment variable to be correctly set for each workspace that MCP servers and agents operate on.
  • ⚠️The Ishikawa MCP server requires Google Cloud credentials (e.g., `GOOGLE_APPLICATION_CREDENTIALS`) to access external data lakes like Firestore.
Review RequiredView Analysis
The Major agent's `fetch_image_as_base64` function takes arbitrary image URLs from user input, potentially leading to Server-Side Request Forgery (SSRF) if not adequately sanitized or restricted to trusted domains. Path traversal vulnerabilities exist in the Batou and Reports MCP servers, as `entity_id`, `report_type`, and `report_date` from user input are used directly to construct file paths (e.g., `f"{entity_id}.md"`, `f"{report_type}"`) without explicit sanitization against `..` or `/` characters. While Tachikoma's tools implement a `resolve_path` to prevent workspace escapes, Batou and Reports lack similar robust path validation. Ishikawa's `org_id` enforcement relies on an external `auth.py` and the MCP authentication context, whose security implementation is not fully visible and could be a point of failure if weak.
Updated: 2026-01-18GitHub→
30
1
Medium Cost
ry-ops icon
Sec9

Facilitates natural language management of n8n workflows, executions, and credentials through integration with Claude AI via the Model Context Protocol.

Setup Requirements

  • ⚠️Requires a self-hosted n8n instance (v1.0+) accessible from the server's environment.
  • ⚠️An n8n API Key with appropriate permissions must be generated and securely stored as an environment variable (`N8N_API_KEY`).
  • ⚠️Python 3.10 or higher is required, and the `uv` package manager is recommended for installation.
Verified SafeView Analysis
Employs robust input validation (e.g., `_validate_id`) to prevent path traversal and injection attacks on workflow and execution IDs. Secrets (n8n API Key) are loaded from environment variables, preventing hardcoding. Includes a comprehensive retry mechanism that explicitly handles different HTTP status codes, preventing retries on client errors (e.g., 401, 403, 404). Warns users about unencrypted HTTP connections. Explicitly checks for sufficient `mcp` dependency version to address known CVEs (as per `test_security.py`). No 'eval' or malicious obfuscation patterns were found.
Updated: 2025-12-10GitHub→
30
1
Low Cost
DynamicDevices icon

ai-lab-testing

by DynamicDevices

Sec7

MCP server exposing remote embedded hardware testing capabilities to AI assistants, making remote embedded hardware development easy and accessible for engineers by providing intelligent tooling with helpful guidance, best practices, and automated workflows.

Setup Requirements

  • ⚠️Requires Python 3.10+.
  • ⚠️Requires WireGuard tools for VPN features.
  • ⚠️Requires `fioctl` CLI tool for Foundries VPN features.
  • ⚠️Google Sheets export requires a Google Cloud project, Google Sheets API enabled, a service account, and a downloaded `credentials.json` file.
  • ⚠️Manual client peer registration on the WireGuard server is required for initial Foundries VPN setup.
  • ⚠️SSH password caching stores passwords in plaintext.
  • ⚠️Mermaid-cli (`mmdc`) is required for PNG export of network diagrams.
Verified SafeView Analysis
The server explicitly documents its security practices, including not committing secrets to the repository and storing cached credentials in `~/.cache/ai-lab-testing/credentials.json` with `600` permissions. It prioritizes SSH public keys for authentication. However, it notes that cached passwords for SSH are currently stored in plaintext. Custom changes to the Foundries WireGuard server, such as the `--allow-device-to-device` flag, are acknowledged to reduce network isolation for development purposes, but preserve higher security for production when not enabled. Setup scripts requiring `sudo` and handling of sensitive VPN/Google Sheets credentials (which are advised to be protected via environment variables or secured files) are present, but the repository maintains a private status, which mitigates some risks. The plaintext password storage is the primary explicit vulnerability noted.
Updated: 2025-11-21GitHub→
30
1
Low Cost
suonian icon
Sec6

Serves as a proxy for AI assistants to interact with the Yuque knowledge base platform via the Model Context Protocol (MCP).

Setup Requirements

  • ⚠️Requires a Yuque API Token, which is mandatory for interaction and needs to be configured via environment variable, HTTP header, or the `yuque-config.env` file.
  • ⚠️Requires Python 3.7+ installed locally if not deploying with Docker.
  • ⚠️The macOS service installation script (`install_service.sh`) modifies the `com.yuque.mcp.plist` file in the project directory itself, which might conflict with source control.
  • ⚠️Redis is an optional dependency for caching; if not available, the server automatically falls back to in-memory caching.
Verified SafeView Analysis
The `docker-compose.yml` includes a hardcoded example `YUQUE_TOKEN` value as a default, which is a security anti-pattern. While intended for local testing or as a fallback, it's preferable to avoid any hardcoded secrets. The `install_service.sh` script modifies the `com.yuque.mcp.plist` file directly within the project's cloned directory during installation, which can lead to unexpected behavior or issues with version control. The server's CORS policy is set to allow all origins (`*`), which is acceptable for a locally-run proxy but broader than strictly necessary. Authentication token handling is well-documented with priority given to HTTP headers, environment variables, and config files, which is good practice.
Updated: 2026-01-12GitHub→
30
1
Low Cost
23Maestro icon

prospect-pipeline

by 23Maestro

Sec8

A FastAPI service that acts as an API translation layer between a Raycast extension and a legacy Laravel/AngularJS backend, normalizing requests and responses, and managing session state.

Setup Requirements

  • ⚠️Requires Python virtual environment setup (`venv`, `pip install -r requirements.txt`).
  • ⚠️Requires NPID credentials (`NPID_EMAIL`, `NPID_PASSWORD`) to be configured in `.env`.
  • ⚠️For auto-start on macOS, `launchd` setup is required.
  • ⚠️Raycast extension preferences (`dropboxToken`, `scoutApiKey`) must be configured for full functionality.
Verified SafeView Analysis
The project uses environment variables for sensitive credentials (NPID_EMAIL, NPID_PASSWORD, SCOUT_API_KEY) and Raycast preferences for others (dropboxToken). Python script execution primarily uses `child_process.spawn` with `shell: false` and input validation, which is a good security practice against command injection. An older `python-rest-bridge.ts` file uses `exec` with manual escaping, which is generally riskier, but `python-executor.ts` (used by `python-server-client.ts`) is the primary execution path and employs safer practices. No obvious use of `eval` or code obfuscation was detected.
Updated: 2026-01-13GitHub→
PreviousPage 230 of 760Next