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)

0
0
Medium Cost
Relampag0 icon

forensic-log-mcp

by Relampag0

Sec4

This server acts as a forensic tool to intercept, log, and analyze network traffic (likely Minecraft Protocol, given the 'mcp' context) by operating as a Man-in-the-Middle proxy.

Setup Requirements

  • ⚠️Requires Node.js environment.
  • ⚠️Requires generation and installation of MITM root certificates on client devices for HTTPS/TLS interception to function without security warnings (this is a significant security override).
  • ⚠️May require administrative privileges for DNS proxy (port 53).
Review RequiredView Analysis
The core functionality is a Man-in-the-Middle (MITM) proxy, which inherently carries significant security risks including intercepting and potentially exposing sensitive network traffic. It uses `execSync` for certificate generation, which is a powerful command, although seemingly used securely for its intended setup purpose. Requires explicit trust of self-signed certificates for HTTPS/TLS interception. Prone to misuse if not handled responsibly.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
EarthTan icon
Sec9

A simplified local file system MCP server designed for managing Obsidian note libraries and Markdown files, enabling AI assistants to securely interact with and manipulate knowledge bases.

Setup Requirements

  • ⚠️Requires Python 3.10+.
  • ⚠️Requires MCP SDK to be installed (`pip install mcp[cli]`).
  • ⚠️Obsidian must be installed and accessible in the client's environment for 'open_file_with_obsidian' and other Obsidian-specific features.
  • ⚠️The root directory for file operations needs to be configured via the `MCP_FILESYSTEM_ROOT` environment variable, or it defaults to the script's directory.
Verified SafeView Analysis
The server implements strong security measures for file operations, including root directory restriction via `resolve_path`, a file type whitelist (e.g., '.md', '.json', '.txt', '.canvas') via `_has_allowed_extension`, and file size limits (10MB) for reads. All file paths provided to tools are rigorously validated against these constraints. The `open_file_with_obsidian` tool uses `subprocess.run` to open files, which is controlled by the validated file paths, mitigating direct command injection risks. The `mcp` SDK's HTTP transports include DNS rebinding protection, enhancing network security if HTTP is enabled. No 'eval' or obvious hardcoded secrets were found.
Updated: 2025-11-25GitHub→
0
0
High Cost
itsablabla icon

garza-os-github

by itsablabla

Sec2

Automatically indexes voice memos from VoiceNotes, extracts entities using Claude, and syncs to Craft for knowledge management.

Setup Requirements

  • ⚠️Requires a paid Anthropic API key.
  • ⚠️Requires Cloudflare account setup and `wrangler` CLI for deployment.
  • ⚠️Needs VoiceNotes application webhook configured and an API key to fetch recordings.
  • ⚠️Requires a pre-existing Craft workspace and API key for syncing.
Review RequiredView Analysis
Multiple critical security risks identified across the repository: numerous hardcoded API keys/tokens are present in various Node.js servers (e.g., `cf-mcp/server.js`, `beeper-rest-api/server.js`, `desktop-commander-mcp/worker.js`), shell scripts (`scripts/daily-bible.sh`), and Cloudflare Worker files. The system's own documentation (`docs/security-checklist.md`) explicitly flags plaintext secrets in Craft and unproxied MCP endpoints as immediate concerns. The orchestrator's use of `shell=True` in some `subprocess` calls also poses a potential risk if inputs aren't perfectly sanitized. Widespread use of hardcoded credentials makes the overall system highly vulnerable.
Updated: 2026-01-19GitHub→
0
0
Low Cost
mkaiho icon
Sec1

To provide a sandbox environment for developing, testing, or experimenting with an MCP (Minecraft Protocol) server.

Review RequiredView Analysis
Insufficient source code provided (only README title). Cannot perform a meaningful security audit for executable code, potential vulnerabilities, or dangerous patterns like 'eval' or hardcoded secrets.
Updated: 2025-11-19GitHub→
0
0
Low Cost
RyutaSuzuki77 icon

mcp-server-write-log

by RyutaSuzuki77

Sec7

An MCP server designed to store conversation logs as text files in a specified local directory.

Setup Requirements

  • ⚠️Requires the LOG_BASE_DIR environment variable to be set, pointing to the desired directory for log storage.
  • ⚠️Requires Node.js runtime environment.
  • ⚠️Requires TypeScript and ts-node for direct execution from source files.
Verified SafeView Analysis
The server writes user-provided 'text' directly to a file within a directory specified by the 'LOG_BASE_DIR' environment variable. While the filename is internally generated with a timestamp, preventing direct path traversal via filename, an insecurely configured 'LOG_BASE_DIR' (e.g., pointing to a sensitive system directory or one with limited space) could allow arbitrary content to be written to files in that location, potentially filling up disk space or overwriting non-critical data if the server process has broad write permissions. There are no obvious signs of 'eval', obfuscation, hardcoded secrets, or direct network vulnerabilities in the provided code, beyond its intended function of writing user-supplied data to the file system.
Updated: 2026-01-17GitHub→
0
0
Medium Cost
acuvity icon

maxibridge

by acuvity

Sec3

Maxibridge acts as a policeable dynamic gateway for Multiple Context Protocol (MCP) servers, allowing external agents to connect, discover, and interact with various backend MCP services with security and policy enforcement.

Setup Requirements

  • ⚠️The backend can execute arbitrary commands (`-- command [args...]`) on the host system. This requires significant operational expertise to securely sandbox and ensure only trusted binaries are ever executed.
  • ⚠️Secure deployment requires extensive TLS configuration, including server certificates, client certificates, and Certificate Authorities for both frontend and backend components.
  • ⚠️If policy enforcement is desired, a separate Policer (either a Rego policy file or an external HTTP service) must be configured and maintained.
Review RequiredView Analysis
The backend component of Maxibridge directly executes arbitrary commands passed via command-line arguments (e.g., `maxibridge backend -- <command> [args...]`). This is an extreme security risk (G204 identified) as it allows the execution of any binary on the host if an attacker gains control over these arguments, even indirectly. While `setCaps` and `chroot` (on Linux/Darwin) are used to attempt sandboxing, fully securing arbitrary command execution is exceptionally difficult. The `cmd_others.go` build tag does not enable `chroot`, leaving non-Linux/Darwin systems even more exposed. Input validation and policy enforcement via `policer` exist at a higher level, but do not mitigate the underlying risk of spawning unsandboxed processes. The `pkgs/scan/sbom.go` uses `os.ReadFile` (G304 flagged) to load SBOMs, which could be vulnerable to path traversal if the SBOM file path is user-controlled. Hardcoded secrets are not evident; credentials are managed through environment variables or flags.
Updated: 2025-12-03GitHub→
0
0
Medium Cost
viraljetani icon

mcp-servers

by viraljetani

Sec9

A collection of micro-servers for local caching and searching of AWS CloudWatch logs, providing contextual data for debugging and analysis.

Setup Requirements

  • ⚠️Requires Node.js (v18 or later)
  • ⚠️Requires AWS CLI configured with credentials and at least one profile
  • ⚠️Requires the AWS_PROFILE environment variable to be set when running the server
Verified SafeView Analysis
The server uses AWS CLI profiles for authentication and does not expose secrets or hardcode credentials. It runs on localhost, limiting network exposure. The `.env` and `log_cache/` directories are correctly gitignored to prevent accidental exposure of configuration or downloaded logs. While the local endpoint does not have explicit authentication, it's designed for local debugging and relies on secure AWS profile configuration.
Updated: 2025-11-30GitHub→
0
0
Low Cost
wangdruk icon
Sec5

This project provides a comprehensive security research report analyzing AI Agents (MCP Servers) for privacy, data residency, and national security implications.

Review RequiredView Analysis
Only README.md was provided; no executable source code was available for analysis. Therefore, a comprehensive security audit of the project's implementation for 'eval', obfuscation, network risks, hardcoded secrets, or malicious patterns could not be performed. The score is neutral due to lack of information.
Updated: 2025-11-24GitHub→
0
0
High Cost
DuinoDu icon

install-x

by DuinoDu

Sec4

Automates library installation across multiple programming languages (Python, JavaScript, Rust, C, C++) for AI assistants, supporting complex dependencies like CUDA and ML frameworks.

Setup Requirements

  • ⚠️Requires Python 3.8+ (often specifically 3.10 as per scripts), Node.js, npm, Cargo, Git, wget/curl, and Make.
  • ⚠️Many installations require CUDA for GPU acceleration; CUDA installation and configuration are prerequisites for ML libraries.
  • ⚠️Requires `sudo` access for system-level dependency installations (e.g., `apt install`).
  • ⚠️Relies on `rye` for Python dependency management and virtual environment creation.
  • ⚠️Blender and FFmpeg are prerequisites for certain 3D/video-related projects.
Review RequiredView Analysis
The server executes dynamically named shell scripts (e.g., `library_name.sh`) based on user input for `install(library_name)`. While the `is_supported` check attempts to validate `library_name`, the execution of arbitrary shell scripts in `src/install_x/install/` remains a significant risk if the naming convention is exploited or if a malicious package is registered on PyPI/npm/crates.io with a name matching a local trusted script. Many installation scripts utilize `sudo apt install` and `wget` without explicit content hash verification, `git clone` from external repositories, and `pip install` from direct GitHub links, leading to high exposure to supply chain attacks and privilege escalation if external sources are compromised. The implementation of `_install_python_package` incorrectly attempts to execute a shell script for *any* detected Python package, even simple PyPI libraries like 'numpy' that do not have corresponding `.sh` scripts, which is a functional bug, but also slightly mitigates arbitrary script execution for non-existent `.sh` files.
Updated: 2026-01-14GitHub→
0
0
Low Cost
sudsarkar13 icon

deno-mcp

by sudsarkar13

Sec7

Provides a comprehensive MCP server for AI assistants to interact with the complete Deno CLI toolchain, enabling seamless Deno development workflows.

Setup Requirements

  • ⚠️Requires Deno installed and in PATH.
  • ⚠️Requires Node.js v18.0.0 or higher.
  • ⚠️Requires an MCP-compatible client (e.g., Claude Desktop, VS Code Continue extension) to interact with the server's core functionality.
  • ⚠️For containerized deployments, Docker is required.
Verified SafeView Analysis
The server's primary function is to expose Deno CLI functionality, including arbitrary code execution (deno_eval) and server startup (deno_serve). While it leverages Deno's strong permission model and implements input validation, the `render-server.ts` variant, designed for public deployment, enables CORS with `Access-Control-Allow-Origin: *` on its `/mcp` endpoint. If deployed publicly without additional authentication and authorization layers at an ingress or API gateway, this open CORS could allow unauthorized execution of Deno commands from any web origin. The `SECURITY.md` explicitly advises proper authentication when exposed.
Updated: 2025-12-19GitHub→
0
0
Low Cost
sbroenne icon
Sec10

This repository provides video tutorials and documentation for automating Excel tasks using natural language prompts via the Model Context Protocol (MCP) and AI assistants.

Setup Requirements

  • ⚠️Requires Windows 10/11 with Microsoft Excel installed (Microsoft 365 or Excel 2016+).
  • ⚠️Requires an AI assistant that supports MCP (e.g., VS Code with GitHub Copilot, Claude Desktop, Cursor, or Windsurf), which may incur subscription costs or require specific installations.
  • ⚠️For VBA automation tutorials, Excel's VBA Trust Settings must be configured to 'Trust access to the VBA project object model'.
Verified SafeView Analysis
The provided source code consists solely of Markdown files (documentation and tutorial outlines). It contains no executable server logic, no 'eval' statements, no network calls, and no hardcoded secrets. Therefore, the source code of this repository itself is extremely safe to analyze. Security risks would only arise from running the external 'MCP Server for Excel' project that these tutorials describe, which is not part of this repository's source code.
Updated: 2025-11-25GitHub→
0
0
Low Cost
huykaiser icon

mcp-server

by huykaiser

Sec8

This server exposes a set of tools and resources, including arithmetic operations, web browser control, data retrieval, and dynamic greetings, accessible via the MCP protocol over HTTP.

Setup Requirements

  • ⚠️Requires Python 3.13 or newer
  • ⚠️Requires the 'mcp' library (mcp[cli]>=1.22.0) to be installed
Verified SafeView Analysis
The `webbrowser.open` function call, while hardcoded to a specific URL in this demo, introduces a capability on the server that could be risky if the URL were dynamically controlled. However, there are no obvious hardcoded secrets or arbitrary code execution vulnerabilities (like `eval`) present.
Updated: 2025-11-28GitHub→
PreviousPage 528 of 760Next