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(8554)

0
0
Low Cost
sco3 icon
Sec5

Acts as an intermediary, wrapping a standard I/O (stdio) based process and exposing its real-time output and input capabilities via a Server-Sent Events (SSE) web interface.

Setup Requirements

  • ⚠️Requires Node.js runtime (version unknown, likely recent LTS)
  • ⚠️Requires a separate target process (e.g., a specific Minecraft server executable or tool) to wrap and manage via standard I/O
Review RequiredView Analysis
Source code not provided for detailed analysis. Based on the name, it's likely a Node.js application that manages a child process. Potential risks include unsanitized command execution if it spawns child processes, or improper handling/exposure of internal process state if not carefully implemented via SSE. No hardcoded secrets or malicious patterns could be identified without the actual source code.
Updated: 2026-01-18GitHub→
0
0
Medium Cost
sivola icon
Sec8

This server provides a multi-cluster proxy solution for Kubernetes environments, enabling centralized management and communication across distributed clusters.

Setup Requirements

  • ⚠️Requires access to Kubernetes clusters, typically via kubeconfig or in-cluster service accounts.
  • ⚠️Go development environment (version 1.18+) required for building.
  • ⚠️Containerization (e.g., Docker) is recommended and likely required for production deployment.
Verified SafeView Analysis
As a Kubernetes multi-cluster proxy, this server inherently interacts with sensitive cluster resources. Critical security considerations include robust authentication/authorization mechanisms (e.g., K8s RBAC, mTLS), careful management of network access, and ensuring no hardcoded secrets are present. Misconfiguration could lead to unauthorized access or data exfiltration across clusters. Without specific code, assuming standard Go security practices and no obvious 'eval' or obfuscation.
Updated: 2026-01-19GitHub→
0
0
Low Cost
ArnoNuyts icon

Todo.txt-MCP

by ArnoNuyts

Sec8

Manages todo.txt files via a Model Context Protocol (MCP) server, enabling AI agents to list, add, edit, and mark tasks as done, with support for local file or WebDAV storage.

Setup Requirements

  • ⚠️Requires Deno runtime installed locally or Docker/Docker Compose for containerized deployment.
  • ⚠️WebDAV backend requires URL, username, and password configured via environment variables or `todo.txt-mcp-config.json`.
Verified SafeView Analysis
The server utilizes Deno's permission model for controlled resource access (--allow-net, --allow-read, --allow-write, --allow-env). Input validation is performed using Zod, mitigating common injection risks. Sensitive WebDAV credentials are configured via environment variables or a local configuration file, avoiding hardcoding. WebDAV authentication uses standard Basic Auth, meaning credentials are sent base64-encoded over HTTPS, which is typical for WebDAV but less secure than token-based approaches. No `eval` or dynamic code execution patterns were found. Todo IDs use SHA-256 hashing (truncated) for identification.
Updated: 2025-12-19GitHub→
0
0
Medium Cost
thomascoffee icon

valuationcontrolMCP

by thomascoffee

Sec1

A server for managing and controlling valuation processes, potentially in a multi-party context.

Review RequiredView Analysis
Source code not provided for analysis. Cannot identify specific security risks such as 'eval' usage, obfuscation, network vulnerabilities, hardcoded secrets, or malicious patterns. Defaulting to the lowest score due to the complete lack of information to perform an audit.
Updated: 2025-11-29GitHub→
0
0
Low Cost

mcp-server

by Tamilmani18

Sec1

The project appears to be a server component, potentially implementing a specific network protocol, but its exact functionality is unknown due to the lack of provided source code.

Review RequiredView Analysis
No source code beyond the README content was provided for analysis. Therefore, it is impossible to audit for security risks such as 'eval' usage, obfuscation, network vulnerabilities, hardcoded secrets, or malicious patterns. A server inherently handles network requests, and without any implementation details, its safety cannot be determined. Running unknown server code without prior review carries significant risk.
Updated: 2025-11-25GitHub→
0
0
High Cost
gaboLectric icon

ast-sast-mcp-server

by gaboLectric

Sec9

Provides static analysis (SAST) for TypeScript code, identifying security vulnerabilities and quality issues for AI agents.

Setup Requirements

  • ⚠️Requires Node.js >= v18.0.0
  • ⚠️Requires an MCP client (e.g., Claude Desktop, VS Code Copilot, Cursor)
  • ⚠️MCP client configuration requires an absolute path to the server's `build/server.js` file
Verified SafeView Analysis
The server's primary function is Static Analysis Security Testing (SAST). The core logic in `src/analyzer.ts` is designed to *detect* common security risks like `eval()` and hardcoded secrets, not to utilize them. The `src/server.ts` code itself appears well-contained and does not expose direct vulnerabilities or use dangerous patterns. The `client_demo.ts` includes examples of 'unsafe code' to demonstrate the analyzer's capabilities, but these are test inputs, not part of the server's operational code. No hardcoded secrets or 'eval' calls are found in the server's functional implementation. The use of `@modelcontextprotocol/sdk` and `zod` for request validation enhances robustness. The server primarily uses stdio for communication, limiting direct network attack surface for this specific deployment method.
Updated: 2025-11-27GitHub→
0
0
Medium Cost
duckduck93 icon

mysql-mcp-server

by duckduck93

Sec9

Exposes MySQL database functionalities as tools via Model Context Protocol (MCP) over stdio.

Setup Requirements

  • ⚠️Requires a running MySQL-compatible database instance.
  • ⚠️MySQL connection details (host, port, user, password, database) must be provided via environment variables.
  • ⚠️Intended to be launched and controlled by an MCP client that handles its stdin/stdout, not for standalone interactive use.
Verified SafeView Analysis
The server utilizes parameterized queries via `mysql2/promise.execute` for `query` and `execute` tools, effectively mitigating SQL injection risks for user-provided SQL and parameters. Table names are also safely handled as parameters in `information_schema` queries (e.g., `describe_table`, `show_indexes`). It operates over stdio, meaning no network ports are exposed by the server itself, reducing direct network attack surface. Environment variables are used for all database credentials, preventing hardcoded secrets. Error logging to `process.stderr` includes input parameters for debugging, which is a minor consideration if sensitive data is passed directly in parameters and logged.
Updated: 2025-12-11GitHub→
0
0
Medium Cost
BACH-AI-Tools icon
Sec8

Provides a Model Context Protocol (MCP) server for AI assistants to seamlessly manage Alibaba Cloud resources through API and OOS integrations.

Setup Requirements

  • ⚠️Requires an Alibaba Cloud Account and configured Access Key ID/Secret (paid services).
  • ⚠️Requires Python 3.10 or higher.
  • ⚠️Requires 'uv' for installation and 'uvx' for execution.
Verified SafeView Analysis
The server primarily uses environment variables or request headers for Alibaba Cloud credentials, which is a good practice. It dynamically constructs API endpoints based on service and region, which is standard for cloud SDKs. No 'eval', obfuscation, or obvious malicious patterns were found. Proper IAM roles and principle of least privilege should be applied to the configured Alibaba Cloud credentials.
Updated: 2025-12-04GitHub→
0
0
Medium Cost
escotilha icon

claude-setup

by escotilha

Sec4

Provides AI-powered M&A analysis capabilities, including deal triage, financial proposal generation, and board presentation creation, for Claude Code agents.

Setup Requirements

  • ⚠️Requires the `nuvini-ma-system-complete` repository to be cloned at the exact absolute path `/Volumes/AI/Code/MNA/nuvini-ma-system-complete/` for its Python modules.
  • ⚠️Requires manual editing of `~/Library/Application Support/Claude/claude_desktop_config.json` to configure the server for Claude Desktop.
  • ⚠️Requires installation of Python dependencies including `mcp`, `pdfplumber`, `openpyxl`, `python-pptx`, `scipy`, `pandas`, `numpy`.
Verified SafeView Analysis
The server's Python code (server.py) loads external Python modules from a fixed absolute path (`/Volumes/AI/Code/MNA/nuvini-ma-system-complete/`). The security of this MCP server relies heavily on the integrity and security of these external (unprovided) modules. The `settings.json` configuration for all MCP servers includes `--dangerously-skip-permissions`, which significantly reduces security by bypassing granular permission checks for invoked tools. Additionally, `npx -y` is used for auto-installing other official MCP servers, which can introduce supply chain risks if package sources are compromised. The `install.sh` script copies files to sensitive user directories (`~/.claude`, `~/.config/claude/skills`, `~/bin`) and makes scripts executable, requiring high trust in the repository.
Updated: 2025-11-27GitHub→
0
0
Medium Cost
DiTo97 icon

numbeo-mcp

by DiTo97

Sec9

Provides a Micro-Capability Platform (MCP) server to access Numbeo API data, offering insights into cost of living, crime rates, healthcare, and quality of life for cities and countries.

Setup Requirements

  • ⚠️Requires Python 3.12 or higher.
  • ⚠️Requires a Numbeo API Key (paid service from numbeo.com/api/).
  • ⚠️API key must be provided via 'api_key' in request metadata or 'Authorization: Bearer <key>' header, not environment variables.
Verified SafeView Analysis
The server uses Pydantic for strict input validation, reducing risks from malformed inputs. It explicitly avoids hardcoding API keys, expecting them from the MCP client's metadata or authorization headers. The API key is then forwarded to the upstream Numbeo API as a query parameter, which is a Numbeo API design choice rather than a vulnerability introduced by this server. No 'eval', 'exec', or other direct code execution vulnerabilities were found. The use of standard HTTPX for API calls is secure.
Updated: 2025-12-11GitHub→
0
0
Medium Cost
Flurin17 icon
Sec9

This server acts as an intermediary, exposing Velociraptor's digital forensics and incident response (DFIR) capabilities via the FastMCP protocol to AI agents (e.g., Codex, ChatGPT).

Setup Requirements

  • ⚠️Requires Podman with podman-compose (or Docker) for local lab setup.
  • ⚠️Requires Python 3.10+.
  • ⚠️Requires a pre-generated Velociraptor mTLS API config (api.config.yaml), typically generated by the provided lab.
  • ⚠️Requires `fastmcp` and `pyvelociraptor` Python packages to be installed.
Verified SafeView Analysis
The project uses mTLS for API communication, generates unique credentials for the API client, and explicitly sanitizes user-provided strings to prevent VQL injection in most tool functions. Default admin credentials are only for the local lab setup and are intended to be overridden by environment variables. The `query_vql` tool allows arbitrary VQL execution, which is an intentional feature for agents, shifting responsibility for safe VQL to the agent.
Updated: 2025-12-03GitHub→
0
0
Medium Cost
yanexr icon
Sec9

Enables AI assistants to search for images on Wikimedia Commons, providing detailed metadata and optional thumbnail composites for visual comparison.

Setup Requirements

  • ⚠️Requires Node.js version 18 or higher.
  • ⚠️Requires a compatible MCP Client (e.g., VS Code, Cursor, Claude Code) for integration.
  • ⚠️The `sharp` dependency involves native binaries, which are typically handled by `npm`/`pnpm` but can occasionally cause installation issues on unusual environments.
Verified SafeView Analysis
The server uses `zod` for robust input validation, mitigating common injection risks. External network requests are directed to the trusted Wikimedia Commons API. Image processing is handled by the `sharp` library, a well-regarded tool. While image processing of untrusted external content can inherently carry some risk, `sharp` is designed for security. The server communicates via StdioServerTransport, limiting direct network exposure to external clients. No hardcoded sensitive credentials were found.
Updated: 2025-11-20GitHub→
PreviousPage 645 of 713Next