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
Medium Cost
ziv-daniel icon

node-red-mcp

by ziv-daniel

Sec9

Integrates AI agents with Node-RED for real-time flow management, monitoring, and dynamic automation.

Setup Requirements

  • ⚠️Requires Node.js 22+ and Yarn 4.x (via Corepack).
  • ⚠️Requires a running Node-RED instance (local or remote) to connect to.
  • ⚠️For Claude Desktop integration, specific configuration in `claude_desktop_config.json` is necessary.
Verified SafeView Analysis
The server employs robust security measures including Zod for comprehensive input validation, Helmet.js for security headers, CORS configuration, and rate limiting. Authentication supports JWT and API keys, with flexible (and optionally less strict) modes for Claude.ai integration, which is clearly documented. Hardcoded development secrets are present but are identified in the entrypoint script and configuration validation for production environments, prompting users to change them. No 'eval' or obfuscation found. Running as root is explicitly warned against.
Updated: 2026-01-19GitHub→
30
1
Medium Cost
Vijay-Duke icon

mcp-gitlab

by Vijay-Duke

Sec9

An MCP server that enables LLMs to interact with GitLab repositories, manage merge requests, issues, and perform various Git operations.

Setup Requirements

  • ⚠️Requires either GITLAB_PRIVATE_TOKEN or GITLAB_OAUTH_TOKEN environment variable for authentication with appropriate scopes (api, read_repository, write_repository).
  • ⚠️Requires Python 3.10 or newer.
  • ⚠️Requires the 'mcp' Python package to be installed (or use 'uvx' for zero-install).
Verified SafeView Analysis
The server demonstrates strong security practices: - Robust input validation (e.g., `validate_project_path`, `validate_file_path`) prevents common injection attacks and path traversal. - Output sanitization (`sanitize_output`) explicitly redacts GitLab tokens (e.g., `glpat-`) from responses. - Log messages are sanitized (`sanitize_log_message`) to prevent log injection. - The `download_job_artifact` tool explicitly returns artifact metadata rather than the file content itself, preventing unauthorized data exfiltration through the LLM. - Authentication tokens (`GITLAB_PRIVATE_TOKEN`, `GITLAB_OAUTH_TOKEN`) are correctly loaded from environment variables, avoiding hardcoding. - The `GitDetector` accesses local `.git` files, which, while standard for Git, could be a low-risk vector if arbitrary paths were accepted without proper context from an LLM. However, path inputs are sanitized, mitigating this risk significantly.
Updated: 2026-01-19GitHub→
30
1
Medium Cost
nasuni-labs icon
Sec7

Integrate Claude AI with Nasuni Management Center (NMC) to manage infrastructure, monitor health, and generate custom reports.

Setup Requirements

  • ⚠️Requires Python 3.11+ to run.
  • ⚠️Requires the Claude Desktop Client for local deployment and interaction.
  • ⚠️NMC API access requires a user with 'Enable NMC API Access' permission; SSO accounts are not supported.
  • ⚠️API connections default to `VERIFY_SSL=false`, which should be set to `true` for production or public-facing NMC instances if valid SSL certificates are used.
Verified SafeView Analysis
The server uses `python-dotenv` for secure handling of API credentials via a `.env` file, which is good practice. However, `VERIFY_SSL` defaults to `false` in the configuration, potentially allowing insecure connections to NMC if not explicitly set to `true` and understood by the user. While convenient for internal servers with self-signed certificates, this default poses a security risk for public-facing NMC instances. No obvious `eval` or direct code execution from untrusted inputs were identified in the core server logic; dynamic imports for testing in `installer.py` are less critical in a local setup.
Updated: 2026-01-19GitHub→
30
1
Medium Cost
eeeeeeeason icon

backup_mcp

by eeeeeeeason

Sec1

Facilitates AI large models to efficiently interact with SpinQ's quantum computing hardware resources by acting as a Micro-Controller Platform (MCP) server for Quantum Assembly (QASM) circuit submission.

Setup Requirements

  • ⚠️Requires Python 3.10 or higher. Conda is recommended for environment management, and installer scripts are provided for Windows and macOS.
  • ⚠️Requires an active internet connection to download Python dependencies via `pip` and to connect to the external SpinQ Cloud platform (cloud.spinq.cn:6060).
  • ⚠️Requires a registered SpinQ Cloud account, a configured SSH public key on the local machine, and the `PRIVATEKEYPATH` and `SPINQCLOUDUSERNAME` environment variables explicitly set for authentication.
Review RequiredView Analysis
CRITICAL: The system uses `eval()` on parsed QASM expression strings, specifically within `spinqit_task_manager/compiler/qasm/Qasm2EventListener.py` (`eval(pexp)` and `eval(lexp)`). If the input `qasm_str` is not strictly validated and sanitized, a malicious QASM input could embed arbitrary Python code, leading to severe remote code execution (RCE) vulnerabilities. For example, injecting `__import__('os').system('malicious_command')` into a QASM parameter could be executed. Additionally, sensitive `PRIVATEKEYPATH` (SSH private key) and `SPINQCLOUDUSERNAME` are read from environment variables for cryptographic signing and cloud authentication, which requires robust secure environment management.
Updated: 2025-12-14GitHub→
30
1
Low Cost

snowflake-mcp-server

by snowflake-mcp

Sec4

This server acts as a bridge between AI applications and Snowflake data warehouses, providing tools for database interaction and operations.

Setup Requirements

  • ⚠️Requires a Python virtual environment (venv) to be created and activated.
  • ⚠️The example configuration specifies 'python3.13', implying a specific Python version requirement that may cause compatibility issues with other versions.
  • ⚠️Absolute paths to the `main.py` script and the `venv`'s Python executable must be accurately provided in the Cursor IDE configuration, replacing 'yourPath' placeholders.
  • ⚠️Requires Snowflake connection details (e.g., username/password or SSO configuration) which are not part of the provided setup instructions and must be managed separately.
Verified SafeView Analysis
The server's core function is to execute AI-generated queries directly on a Snowflake data warehouse. This presents a high risk for SQL injection, unauthorized data access, or unintended data modifications if the AI's output is not meticulously sanitized and validated before being passed to the server. While the server code itself might be robust, its role as a direct interface to critical data systems necessitates stringent security measures at the AI application level.
Updated: 2025-11-17GitHub→
30
1
Low Cost
thepwagner icon

urfave-cli-mcp

by thepwagner

Sec9

Reuses existing urfave/cli applications as Model Context Protocol (MCP) servers, allowing them to be invoked as tools by MCP clients.

Setup Requirements

  • ⚠️The underlying `urfave/cli` application must print its intended results to `stdout` for the MCP client to receive them.
  • ⚠️Requires a Go runtime environment to compile and run the application.
Verified SafeView Analysis
The server executes `os.Args[0]` (the current executable) with arguments derived from MCP tool calls. This design mitigates direct command injection as it avoids shell execution. The primary risk would be vulnerabilities present in the wrapped `urfave/cli` application itself. The library includes a safeguard against invoking the 'mcp' command recursively.
Updated: 2026-01-18GitHub→
30
1
High Cost
ismaeldosil icon

finashopping-mcp

by ismaeldosil

Sec9

This MCP server enables Claude Desktop to search, compare, and calculate information about Uruguayan financial products like loans, credit cards, and insurance, and provides financial guidance.

Setup Requirements

  • ⚠️Requires Node.js version 20.0.0 or higher.
  • ⚠️Requires `FINASHOPPING_SERVICE_USERNAME` and `FINASHOPPING_SERVICE_PASSWORD` environment variables for backend API authentication. Without these, the server will not function.
  • ⚠️Intended for use with Claude Desktop and the Model Context Protocol (MCP).
Verified SafeView Analysis
The server's code is clear TypeScript and does not show signs of obfuscation or direct use of dangerous functions like `eval`. It connects to a backend API using `axios`, handling JWT authentication with automatic token refresh. Crucially, it relies on `FINASHOPPING_SERVICE_USERNAME` and `FINASHOPPING_SERVICE_PASSWORD` environment variables for backend authentication, which is a good practice to avoid hardcoding credentials. Error handling for network issues is present. The primary security consideration for the user is ensuring these environment variables are securely managed.
Updated: 2026-01-11GitHub→
30
1
Low Cost
mmorris35 icon

devplan-mcp-server

by mmorris35

Sec8

Generate detailed, Haiku-executable development plans and specialized AI agents for Claude Code, incorporating lessons learned and issue remediation workflows.

Setup Requirements

  • ⚠️Requires Cloudflare account and Wrangler CLI for deployment
  • ⚠️Requires Cloudflare KV Namespace binding (`DEVPLAN_KV`)
  • ⚠️Requires Cloudflare Durable Object Namespace binding (`MCP_OBJECT`)
  • ⚠️Authentication is disabled by default; must set `AUTH_ENABLED = "true"` in `wrangler.toml` and manage API keys for production use
Verified SafeView Analysis
The server includes authentication (API key validation, rate limiting) which is good, but `AUTH_ENABLED` defaults to `false` in `wrangler.toml`, meaning it's open-access unless explicitly configured. The `createApiKey` admin function is not exposed as a public endpoint, mitigating a potential risk. IP addresses are hashed for privacy-preserving usage tracking. Cloudflare bot detection is used for MCP endpoints. Overall, robust security features are available, but deployment requires careful configuration of the `AUTH_ENABLED` variable.
Updated: 2026-01-19GitHub→
30
1
High Cost
PyJudge icon

pdf4vllm-mcp

by PyJudge

Sec8

PDF content extraction and search, optimized for messy documents and vision language models (LLMs), with features for text corruption detection, reading order preservation, and token management.

Setup Requirements

  • ⚠️The `grep_pdf` tool requires the external `pdfgrep` system utility to be installed (e.g., `brew install pdfgrep` on macOS or `apt install pdfgrep` on Ubuntu).
  • ⚠️Requires Python 3.10+.
  • ⚠️The `read_pdf` tool, especially in `auto` or `image_only` mode when extracting images, can generate very high token counts due to base64 encoding of image data, potentially leading to increased LLM costs and context window limitations. Configuration options are available to manage this.
Verified SafeView Analysis
The server uses `subprocess.run` to execute the external `pdfgrep` utility for the `grep_pdf` tool. While arguments are passed as a list to prevent shell injection, the `pattern` argument is interpreted as a regex by `pdfgrep` by default, which could theoretically be exploited for a ReDoS (Regular Expression Denial of Service) attack. This risk is partially mitigated by a 60-second timeout and a `max_count` limit for matches. Path traversal risks for file access are explicitly addressed and mitigated by the `validate_path_security` function, ensuring all file operations are constrained to the current working directory.
Updated: 2026-01-12GitHub→
30
1
Medium Cost
miyamamoto icon

jvlink-mcp-server

by miyamamoto

Sec8

This server allows users to analyze JRA-VAN horse racing data using natural language queries, translating them into SQL for detailed statistical analysis and trend identification.

Setup Requirements

  • ⚠️Requires JRA-VAN DataLab membership (a paid service) to acquire the underlying horse racing data.
  • ⚠️Requires `jrvltsql` (a separate Windows-only tool) to create and maintain the database files.
  • ⚠️Requires Python 3.11 or higher runtime environment.
Verified SafeView Analysis
The server employs robust SQL injection prevention mechanisms, including explicit checks for dangerous keywords (DROP, DELETE, UPDATE, etc.) in `execute_safe_query` and parameter escaping for LIKE clauses. However, the default setup for network access (SSE/HTTP mode) is unauthenticated, as acknowledged in the documentation (`REMOTE_SETUP.md`), which poses a risk if exposed to untrusted networks without additional security measures like authentication and HTTPS/TLS.
Updated: 2025-12-14GitHub→
30
4
Low Cost
CrackingShells icon

Hatch

by CrackingShells

Sec2

Hatch is a package manager for Model Context Protocol (MCP) servers, providing environment isolation, multi-type dependency resolution (system, Python, Docker, other Hatch packages), and multi-host deployment to various AI tools and IDEs.

Setup Requirements

  • ⚠️Requires Python 3.12+.
  • ⚠️Conda or Mamba recommended for Python environment isolation.
  • ⚠️Docker required for Docker-based dependencies.
  • ⚠️Linux package manager (e.g., `apt`) required for system dependencies; macOS and Windows system package managers not yet supported.
  • ⚠️Development setup requires `pip install -e .` and `npm install`.
Review RequiredView Analysis
Critical security risks identified: 1. **Lack of Package Integrity Verification**: Downloaded packages (Hatch, Python, Docker) are NOT cryptographically verified (no checksums, no signatures). This is explicitly stated in 'Limits and Known Issues' and means malicious packages or compromised registries/networks could lead to arbitrary code execution without detection. 2. **System-Level Code Execution with Elevated Privileges**: The 'System Installer' executes system package manager commands (e.g., `apt`) which can require `sudo`. Combined with the lack of package integrity verification, this presents a severe risk of system compromise if untrusted packages specify malicious system dependencies. 3. **Default Auto-Approval in Non-TTY Environments**: The dependency installation orchestrator automatically approves installation prompts in non-TTY environments. While useful for CI/CD, this automates the execution of unverified code, exacerbating the risk. 4. **Race Conditions for Critical State Files**: 'Limits and Known Issues' notes non-atomic file I/O for `environments.json` and package caches, leading to potential corruption. This can have security implications if state is manipulable. 5. **Supply Chain Risk**: Direct Git URL dependencies for `hatch_validator` and `@artessan-devs/sr-uv-plugin` in `pyproject.toml` introduce additional risk if those repositories are compromised. The project's own documentation clearly states it is 'less suitable for: Production deployments, Multi-tenant systems, High-security environments'.
Updated: 2026-01-06GitHub→
30
1
Low Cost
DreamCats icon

mcp-server

by DreamCats

Sec9

A flexible MCP server providing various time-related functionalities, including current time, timestamps, time range processing, timezone conversions, relative time calculations, and comprehensive time information, using the FastMCP framework.

Verified SafeView Analysis
The `super-time` module itself primarily performs time-related calculations and does not appear to involve direct external network calls, complex authentication mechanisms, or access sensitive external resources. No use of `eval` or obvious hardcoded secrets was found within the provided source for this module. Its overall security posture is largely dependent on the underlying `FastMCP` framework and the secure configuration of its deployment environment.
Updated: 2026-01-11GitHub→
PreviousPage 225 of 760Next