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
4lejandrito icon
Sec4

The server provides a Model Context Protocol (MCP) endpoint for Liferay DXP, enabling AI agents to interact with Liferay content as context.

Setup Requirements

  • ⚠️Requires Docker to build and run the server image.
  • ⚠️Implies a Liferay DXP instance is expected or integrated, though the setup focuses on the MCP server itself.
Review RequiredView Analysis
The README explicitly documents hardcoded basic authentication credentials ('test@liferay.com:test') for accessing the MCP server endpoint. This is a critical security vulnerability and should be replaced with a secure authentication mechanism for any non-development or production deployment. No other security risks like 'eval' or obfuscation are apparent from the truncated README content.
Updated: 2025-12-01GitHub→
0
0
Low Cost
William12556 icon

mcp-sed-awk

by William12556

Sec9

Enables LLMs to perform secure and token-efficient text processing and file manipulation using native sed, awk, and diff utilities.

Setup Requirements

  • ⚠️Requires Python 3.9 or higher.
  • ⚠️Requires FastMCP 2.0+ library.
  • ⚠️Requires `sed`, `awk`, and `diff` system binaries to be installed and available in PATH.
  • ⚠️Resource limits (memory and CPU time) are only applied on Linux systems; macOS/Windows will only enforce timeouts.
  • ⚠️Requires explicit configuration of allowed directories via CLI arguments or the `ALLOWED_DIRECTORIES` environment variable for any file operations to succeed.
Verified SafeView Analysis
The server implements a robust, multi-layered security architecture: 1. Input Validation: `SecurityValidator` actively sanitizes sed patterns and AWK programs, preventing command injection, ReDoS attacks (nested quantifiers, excessive repetition, deep nesting), and filters shell metacharacters through blacklists and structural checks. 2. Access Control: `PathValidator` enforces a strict directory whitelist, canonicalizes paths, resolves symlinks, and prevents path traversal and TOCTOU vulnerabilities. 3. Resource Protection: `BinaryExecutor` enforces file size limits (10MB), operation timeouts (30s), and on Linux systems, applies memory (100MB) and CPU time (30s) limits using `setrlimit`. 4. Safe Execution: All native binary executions (sed, awk, diff) use `subprocess.run(shell=False)` to prevent shell injection. 5. Error Recovery: `sed_substitute` creates automatic backups and rolls back changes on failure, while `preview_sed` uses temporary files for non-destructive operations with guaranteed cleanup. 6. Audit Trail: `AuditLogger` records all security-relevant events (validation failures, access violations, executions) with data sanitization and fail-safe logging to prevent log injection. No `eval()` or similar dangerous functions were identified. No hardcoded secrets were found; sensitive configurations like allowed directories are passed via CLI or environment variables.
Updated: 2026-01-08GitHub→
0
0
Medium Cost
parthamjangir2020 icon

claude-connector-perfexcrm

by parthamjangir2020

Sec3

Provides AI-powered integration for Claude Desktop to manage and query data within Perfex CRM through direct database access via a Model Context Protocol (MCP) server.

Setup Requirements

  • ⚠️Requires a specific version of Claude Desktop with Model Context Protocol (MCP) support.
  • ⚠️Requires manual creation and secure management of a '.env' file containing sensitive database credentials.
  • ⚠️Demands creating and configuring a dedicated database user for Perfex CRM with appropriate (potentially broad) permissions.
Review RequiredView Analysis
The 'execute_sql' tool allows arbitrary raw SQL queries to be executed directly against the Perfex CRM database. While other tools use prepared statements for parameters, the 'sql' argument itself is directly taken from input, posing a severe SQL injection risk if the LLM's output for this argument is not perfectly safe or if an attacker gains control. This grants full control over the database, including modification, deletion, and exfiltration of all data. The MCP server operates with a single database user, lacking granular, in-server role-based access control. Database credentials are handled via environment variables, which is a good practice for secure storage, but the broad capabilities of the 'execute_sql' tool remain a critical vulnerability.
Updated: 2025-12-10GitHub→
0
0
Low Cost
ed-marquez icon
Sec9

A RESTful proxy for the Hedera MCP 'SearchHedera' tool, enabling platforms like Custom GPTs to interact with it.

Setup Requirements

  • ⚠️Designed for deployment on Vercel, potentially requiring a Vercel account and CLI for local development or deployment.
  • ⚠️Relies on the external Hedera MCP server (https://docs.hedera.com/mcp) being available and maintaining its API contract.
  • ⚠️Requires Node.js for local development or execution.
Verified SafeView Analysis
The proxy is a simple pass-through without complex logic, making it relatively secure. No hardcoded secrets, 'eval' usage, or obvious malicious patterns were found. It relies on the security and availability of the external Hedera MCP server, which is beyond the scope of this proxy's code.
Updated: 2025-11-26GitHub→
0
0
Low Cost
ipnet-mesh icon

meshcore-mcp

by ipnet-mesh

Sec5

Enables AI assistants and web-based tools to control and communicate with MeshCore mesh network devices via an HTTP MCP server.

Setup Requirements

  • ⚠️Requires a MeshCore-compatible hardware device (via Serial, BLE, or TCP) to be functional.
  • ⚠️Requires Python 3.10 or higher.
  • ⚠️The server defaults to binding on 0.0.0.0:8000 without authentication; external security (e.g., reverse proxy, firewalls) is critical for secure deployment, especially in production environments.
Review RequiredView Analysis
The server explicitly states that it does not include authentication by default and binds to 0.0.0.0. For production use, it critically requires external security measures like a reverse proxy with authentication, HTTPS/TLS, and firewall rules. Without these, direct exposure to the network poses a significant security risk.
Updated: 2025-12-05GitHub→
0
0
Medium Cost
JasonBates icon

image-gen-mcp

by JasonBates

Sec9

Generates images using the laozhang.ai Gemini 3 Pro API and saves them to an Obsidian vault.

Setup Requirements

  • ⚠️Requires a laozhang.ai API Key (paid service)
  • ⚠️Requires uv package manager
  • ⚠️Requires Python 3.11+
  • ⚠️Requires an Obsidian vault to save generated images
Verified SafeView Analysis
The server correctly loads API keys from environment variables and provides configurable paths for saving images. Filenames generated from prompts are sanitized, preventing path traversal. File operations are limited to user-defined directories. The use of httpx for API calls and pydantic for settings are standard secure practices. The LLM call for prompt variations is structured to parse JSON output, mitigating direct code execution via LLM responses. Reference images are read as bytes and passed to the API, without local execution of their content. User configuration of the Obsidian vault path to a sensitive system directory could pose a risk, but this is user-dependent and not a direct vulnerability in the server's code.
Updated: 2026-01-19GitHub→
0
0
Low Cost

mcp-delegator

by littlebearapps

Sec9

Orchestrates and delegates AI agent tasks (specifically OpenAI Codex) from Claude Code, enabling asynchronous execution and advanced development workflows.

Setup Requirements

  • ⚠️Requires Node.js >= 20.0.0.
  • ⚠️Requires OpenAI Codex CLI installed and configured.
  • ⚠️Requires ChatGPT Pro subscription or CODEX_API_KEY environment variable.
  • ⚠️Codex Cloud environments require manual configuration (~/.config/mcp-delegator/environments.json) due to lack of programmatic API for OpenAI Codex Cloud.
  • ⚠️SDK-based tasks may use incorrect Python versions if virtual environment is not activated in the MCP server's process context.
Verified SafeView Analysis
Robust input validation prevents command injection and path traversal. Automatic secret redaction for 15+ patterns. Mutation gating requires explicit user confirmation for file-modifying operations. Risky Git operations are detected and require explicit user confirmation with automatic safety checkpointing. Uses child_process.spawn to prevent shell injection. Comprehensive CI/CD security plan including CodeQL, Dependabot, and npm Trusted Publisher. Deduction for wrapping codex CLI, which is an external dependency.
Updated: 2025-11-24GitHub→
0
0
Low Cost
Ilm-Alan icon

claude-tmux

by Ilm-Alan

Sec3

Orchestrates multiple Claude Code instances in isolated tmux sessions for long-running, interactive coding tasks.

Setup Requirements

  • ⚠️Requires tmux to be installed on the host system.
  • ⚠️Requires Claude Code CLI to be installed on the host system.
Review RequiredView Analysis
The `spawn` tool is vulnerable to command injection via the `prompt` parameter. A malicious `prompt` (e.g., containing double quotes like `"`) can break out of the intended `"$(cat ${tempFile})"` shell construct when interpreted by the shell within the tmux session. This allows arbitrary shell commands to be executed within the created tmux session, potentially accessing or manipulating files in the `workdir` or other resources available to the session. Additionally, the Claude Code CLI is launched with the `--dangerously-skip-permissions` flag, explicitly indicating a reduced security posture for the Claude instance itself.
Updated: 2026-01-17GitHub→
0
0
Medium Cost
HamdiOzkurt icon
Sec8

This server analyzes Turkish web content by scraping URLs, summarizing text using an LLM (optional), extracting keywords, and generating visual reports (word cloud, frequency chart) for integration with n8n automation workflows.

Setup Requirements

  • ⚠️Requires a GOOGLE_API_KEY for Google Gemini (paid API) to enable LLM-based summarization; otherwise, it falls back to a classic summary.
  • ⚠️Requires n8n automation platform knowledge and setup for full workflow integration.
  • ⚠️Requires Python environment setup and dependency installation via pip.
Verified SafeView Analysis
The code demonstrates good practices for handling sensitive information (loading API keys from .env). It performs extensive input sanitization using regex to clean scraped text from HTML tags, scripts, styles, and common spam patterns, significantly mitigating injection risks before processing or feeding to an LLM. No 'eval' or similar dangerous patterns are used directly on user input. The server listens on `0.0.0.0:8000`, which means it is externally accessible by default if not firewalled, a standard consideration for any network-facing service.
Updated: 2025-12-01GitHub→
0
0
Medium Cost
nagareproject icon

server-mcp

by nagareproject

Sec7

A server implementation for the Nagare Model Context Protocol, enabling interaction with tools, resources, prompts, and sampling capabilities, primarily for AI/ML-driven applications.

Setup Requirements

  • ⚠️Requires a specific HTTP publisher (gunicorn or waitress) for SSE or the nagare-publishers-mcp-stdio package for STDIO protocol support.
  • ⚠️For STDIO protocol, logging must be explicitly configured to avoid stdout to prevent interference with protocol communications.
  • ⚠️The server is part of the Nagare framework ecosystem, requiring familiarity with Nagare application configuration and deployment.
Verified SafeView Analysis
The code uses `exec` to dynamically create function prototypes from introspected Python function signatures or Pydantic models. While `exec` is generally a high-risk function, its usage here appears to be controlled internally for AST manipulation based on validated inputs, rather than arbitrary user-controlled code execution. Resource functions, if implemented by users to accept arbitrary file paths from client input, could introduce path traversal vulnerabilities; however, the provided examples use hardcoded paths, making them safe within the example context. The server also relies on dynamically loaded plugins via `entry_points`, meaning the overall security posture is also dependent on the trustworthiness of any installed plugins. No hardcoded secrets were identified.
Updated: 2025-12-14GitHub→
0
0
Low Cost
cubeguerrero icon

mcp_demo

by cubeguerrero

Sec6

This is a demo MCP server built with Vert.x and the MCP Java SDK, showcasing both blocking and non-blocking tool implementations for concurrent request handling.

Setup Requirements

  • ⚠️Requires a local MySQL server instance running (Docker command provided in README).
  • ⚠️Requires Java 21.
  • ⚠️Vert.x version 4.5 is required.
  • ⚠️Uses MCP SDK 0.11 (5-6 versions behind current SDK).
Verified SafeView Analysis
The database connection details (host, port, database name, username, password) are hardcoded directly in `MySqlClientProducer.java`. While acceptable for a local demo, this is a critical security vulnerability for any non-demo or production deployment, as it exposes sensitive credentials. No 'eval' or similar dangerous patterns were found. The server exposes an `/mcp` endpoint and `/health` check on a configurable port, which is standard for a server.
Updated: 2025-12-08GitHub→
0
0
Low Cost
sheyboy icon
Sec8

A remote Model Context Protocol (MCP) server deployed on Cloudflare Workers, providing unauthenticated calculator tools that can be consumed by AI agents or playgrounds.

Setup Requirements

  • ⚠️Requires a Cloudflare account and Wrangler CLI for deployment.
  • ⚠️Requires Node.js and npm/yarn/pnpm for local development and dependency management.
  • ⚠️The server is 'authless' by design, meaning it is publicly accessible without authentication. This is suitable for a demo but unsuitable for production use without adding authentication layers.
Verified SafeView Analysis
The server is explicitly designed to be 'authless' as an example, meaning anyone with the URL can access its tools. While this is intentional for the demo, it is a critical security consideration for any production deployment where access control would typically be required. Input validation for the 'add' and 'calculate' tools uses `zod` to ensure inputs are numbers and operations are valid enums, mitigating basic injection risks. Division by zero is also handled. No direct use of 'eval' or other dynamic code execution from user input is observed. Dependencies are standard for Cloudflare Workers and AI SDKs, and their security is assumed.
Updated: 2025-11-27GitHub→
PreviousPage 614 of 760Next