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(7756)

55
1
High Cost
GitHubNexon icon

blink

by GitHubNexon

Sec9

An AI-powered agentic command-based assistant that can read, create, and modify code files using Replicate's Claude models.

Setup Requirements

  • ⚠️Requires a Replicate API token (free tier available, but requires signup).
  • ⚠️Requires Python 3.8+.
  • ⚠️Requires an active internet connection for API calls.
Verified SafeView Analysis
The server demonstrates strong security practices, particularly in API token handling (in-memory, cleared on exit, never saved to disk, validated on startup) and file system interactions (using `pathvalidate.sanitize_filepath` and explicit path resolution to the `workspace_root`). There is no use of `eval` or `exec` on user-controlled input, mitigating common code injection risks. All file operations are channeled through a robust file handler, reducing path traversal vulnerabilities. The primary remaining risk is the inherent nature of AI code generation, where a malicious prompt could potentially lead the AI to generate insecure code, but the server's implementation itself is secure.
Updated: 2025-12-11GitHub→
55
1
Medium Cost

codex_mcp_server_ebka

by gustavorobertux

Sec8

Integrates the Ebka Caido plugin's functionalities with Codex CLI sessions, allowing Large Language Models (LLMs) to interact with and automate security testing tasks within Caido.

Setup Requirements

  • ⚠️Requires Node.js 16+ to be installed.
  • ⚠️Requires a running Caido instance with the Ebka plugin installed and network accessible.
  • ⚠️Manual configuration of the absolute path to the compiled server script in Codex's `config.toml`.
  • ⚠️Manual copying of `auth_token` and `api_endpoint` from the Ebka plugin in Caido into the Codex session.
Verified SafeView Analysis
The server primarily acts as an intermediary, connecting to a user-specified Caido API endpoint with a user-provided authentication token. No 'eval' or obfuscation is indicated. Network risks are controlled by the user's configuration, directing connections to a defined and intended target. The safety is largely dependent on the trustworthiness of the Caido instance and the security of the provided credentials.
Updated: 2025-11-17GitHub→
55
94
Low Cost
hatayama icon

uLoopMCP

by hatayama

Sec6

Acts as a Model Context Protocol (MCP) server to bridge Unity Editor operations to LLM tools, enabling autonomous AI-driven development loops (compile, test, log analysis, scene manipulation).

Setup Requirements

  • ⚠️Requires Node.js 22 or higher.
  • ⚠️Requires Unity 2020.3 or higher.
  • ⚠️Requires Unity MCP Bridge package installed in Unity.
  • ⚠️The `execute-dynamic-code` tool requires `Microsoft.CodeAnalysis.CSharp` package, installed via OpenUPM NuGet registry in Unity.
  • ⚠️Several powerful tools (e.g., `run-tests`, `execute-menu-item`, `execute-dynamic-code`, custom tools) are disabled by default for security and must be explicitly enabled in Unity's `uLoopMCP` window's 'Security Settings'.
Verified SafeView Analysis
The `execute-dynamic-code` tool allows arbitrary C# code execution within the Unity Editor. While it provides 3 security levels (Disabled, Restricted, FullAccess), and 'Restricted' is recommended and blocks dangerous operations (file I/O, network, process execution, reflection), enabling 'FullAccess' (Level 2) poses significant risks, allowing arbitrary code to run with Unity's permissions. Users must exercise extreme caution. Communication between the TypeScript server and Unity Editor is via TCP/IP on localhost, limiting external network attack surfaces. Input validation and path sanitization are implemented in components like `VibeLogger` and `ContentLengthFramer` to prevent memory exhaustion and directory traversal attacks. Robust error handling for exceptions and process signals helps prevent orphaned processes and ensures graceful shutdown.
Updated: 2025-12-14GitHub→
55
1
Low Cost
vibecodiq icon

asa-starter-kit

by vibecodiq

Sec9

A deterministic Python CLI for generating and managing production-ready, slice-based FastAPI backend code, ensuring architectural standards and preserving custom logic during regeneration.

Setup Requirements

  • ⚠️Requires Python 3.10+.
  • ⚠️Optional `devbox` environment setup (otherwise requires manual virtual environment and `pip` management).
Verified SafeView Analysis
The core ASA CLI tool focuses on deterministic code generation and architectural enforcement (e.g., boundary linting), which inherently promotes secure development practices. It does not use `eval` or other known dangerous functions. Hardcoded secrets are not present in the provided core logic or demo snippets. The generated FastAPI application's runtime security depends heavily on the user's implementation of business logic within the provided markers (e.g., for JWT generation, database interactions). The linter actively prevents cross-domain import violations.
Updated: 2025-12-05GitHub→
55
1
High Cost
luisrodriguesphd icon

mcp-rag-agent

by luisrodriguesphd

Sec9

A RAG-based agent that answers questions about internal policies using semantic search via MongoDB Atlas Vector Search and OpenAI embeddings, with automated RAGAS-based evaluation.

Setup Requirements

  • ⚠️Requires OpenAI API Key (Paid) for embeddings, LLM interactions, and RAGAS evaluation.
  • ⚠️Requires MongoDB Atlas Account with Vector Search capabilities (Paid) for document storage and retrieval.
  • ⚠️The 'mcp dev' command for the development UI requires Node.js, though not essential for core functionality.
Verified SafeView Analysis
The project follows good practices by using environment variables for API keys and sensitive configurations, preventing hardcoded secrets. No obvious malicious patterns like 'eval' or direct shell command injection (outside of the controlled 'start.sh' setup script) are present. The MCP server's ability to execute commands is tied to trusted internal modules, which is a standard pattern for such frameworks. Reliance on external APIs (OpenAI, MongoDB) introduces inherent network security considerations.
Updated: 2025-11-30GitHub→
55
1
Low Cost
For-Sunny icon

galaxy-brain

by For-Sunny

Sec4

This MCP server enables AI agents to perform a complete cognitive loop by combining structured sequential thinking with chained sequential execution of operations.

Setup Requirements

  • ⚠️Requires Python 3.10+
  • ⚠️Relies on modifying the `claude_desktop_config.json` file for integration with Claude Desktop (handled by install script, but manual setup requires awareness)
  • ⚠️Execution of certain 'doing' operations (e.g., `shell.run`, `python.execute`) can have security implications if input is not carefully controlled.
Review RequiredView Analysis
The `DoingService` allows execution of arbitrary shell commands (`shell.run`) via `subprocess.run(shell=True)` and Python code (`python.execute`) by writing to a temporary file and executing it. While it includes a `_security_check` with `DANGEROUS_PATTERNS` regex to block some malicious commands (e.g., `rm -rf /`), this is not foolproof against all forms of command injection or malicious Python code. The `python.eval` method is more sandboxed with a strict `allowed_builtins` list. If the server is exposed to untrusted input, there is a significant risk of arbitrary code execution.
Updated: 2025-12-05GitHub→
55
1
Medium Cost
albertoferrazzoli icon

SlotixMCP

by albertoferrazzoli

Sec9

Manages appointments, clients, availability, statistics, notifications, and coupons for Slotix-powered businesses via AI assistants.

Setup Requirements

  • ⚠️Requires a Slotix account with an active subscription.
  • ⚠️Requires a Slotix API key (`SLOTIX_API_KEY`) to be set as an environment variable.
Verified SafeView Analysis
The server correctly uses environment variables for the API key, avoiding hardcoded secrets. It employs `httpx` for secure HTTP communication and robust error handling for API responses. No `eval` or other dangerous code execution patterns were identified. The primary security consideration relies on the user protecting their `SLOTIX_API_KEY` and understanding the permissions it grants to their Slotix account.
Updated: 2025-12-14GitHub→
55
1
Low Cost
neverinfamous icon

postgresql-mcp

by neverinfamous

Sec9

Enables AI assistants to interact with PostgreSQL databases, providing specialized tools for database operations, performance monitoring, schema management, and extension control through the Model Context Protocol.

Setup Requirements

  • ⚠️Requires Node.js 18+ to be installed.
  • ⚠️Requires an accessible PostgreSQL database (versions 12-18 tested).
  • ⚠️Many advanced performance and extension tools require specific PostgreSQL extensions (e.g., pg_stat_statements, pgvector) to be installed and configured in the database.
Verified SafeView Analysis
The server uses parameterized queries via the 'pg' library to prevent SQL injection for direct query execution. It explicitly defines OAuth 2.0 for authentication and handles database connection details securely, including SSL options. Tools generating SQL return the SQL string for client-side use, not for direct, unsafe execution within the server. No 'eval' or other dangerous dynamic code execution patterns were found.
Updated: 2025-12-14GitHub→
55
1
Medium Cost
CamoRageaholic1 icon

unifi-mcp-server

by CamoRageaholic1

Sec9

Enables AI assistants (e.g., Claude) to manage and monitor UniFi network infrastructure through natural language commands via the Model Context Protocol (MCP).

Setup Requirements

  • ⚠️Requires Node.js 18+ (20 LTS recommended).
  • ⚠️Requires an active UniFi Network Controller with network access and admin credentials.
  • ⚠️Potential SSL certificate issues with the UniFi controller might necessitate setting UNIFI_VERIFY_SSL=false (with associated security implications, though documented).
Verified SafeView Analysis
The project uses environment variables for credentials and Zod for configuration validation, mitigating hardcoded secret risks. Docker Compose provides security hardening (no-new-privileges, read-only filesystem). SSL verification is configurable (`UNIFI_VERIFY_SSL`), with documentation warning about disabling it. No `eval` or obfuscation found. The core `node-unifi` library is well-established.
Updated: 2025-11-29GitHub→
55
147
Medium Cost
loonghao icon
Sec8

Provides a Model Context Protocol (MCP) server to allow AI assistants and other MCP clients to programmatically control Adobe Photoshop on Windows.

Setup Requirements

  • ⚠️🔴 WINDOWS OS ONLY: Relies on Windows-specific COM interfaces and will not run on macOS or Linux.
  • ⚠️Requires Adobe Photoshop (CC2017-2024 tested) to be installed locally.
  • ⚠️Requires Python 3.10 or higher.
Verified SafeView Analysis
The server's core functionality involves executing JavaScript (ExtendScript) commands within Adobe Photoshop via COM interfaces, and opening/saving files based on provided paths. While this is the intended purpose, it means the server has extensive control over Photoshop and the local file system. The `execute_javascript` method attempts to wrap scripts in `try-catch` and disable dialogs for stability, and text inputs are sanitized. No obvious hardcoded secrets, 'eval' calls (other than the inherent ExtendScript execution in Photoshop), or arbitrary network listeners were found. The primary security consideration is that an AI assistant, if compromised or misused, could instruct Photoshop to perform actions (e.g., file manipulation) with the user's privileges.
Updated: 2025-12-12GitHub→
55
1
Medium Cost

mcp-langchain

by SyedAanif

Sec6

This project demonstrates using LangChain to orchestrate interactions with local micro-agents providing math and weather services.

Setup Requirements

  • ⚠️Requires an external LLM API Key (e.g., OpenAI, Anthropic) configured via environment variables for LangChain agent operations.
  • ⚠️Requires `math_server.py` and `weather_server.py` to be running concurrently in separate processes before starting the main agent (`main.py`).
Verified SafeView Analysis
LangChain agents can pose security risks if not carefully constrained, especially regarding arbitrary code execution via tools. The local microservices (math, weather) could introduce network risks if exposed without proper authentication or bind to insecure interfaces. The missing README prevents a deeper security analysis.
Updated: 2025-11-18GitHub→
55
580
Medium Cost
mondaycom icon

vibe

by mondaycom

Sec8

Provides intelligent assistance for working with Vibe Design System components, offering metadata, usage examples, accessibility information, icon discovery, and migration guidance for React UI development.

Setup Requirements

  • ⚠️Requires Yarn as the preferred package manager.
  • ⚠️Utilizes Storybook for local component development and previewing.
  • ⚠️Codemod functionality relies on `jscodeshift` for code transformations, which should be used with caution and version control.
  • ⚠️Requires `lerna` for monorepo management during development.
Verified SafeView Analysis
The server uses `execAsync` and `vm.runInContext` to fetch and process metadata from UNPKG (a public CDN). While this involves external code execution and evaluation, the URLs are hardcoded to trusted sources (`unpkg.com`), mitigating risks of arbitrary code execution from user input. The codemod functionality inherently modifies user code, which requires trust in the tool's transformations.
Updated: 2025-12-10GitHub→
PreviousPage 44 of 647Next