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
justincampbell icon

ourgroceries-mcp

by justincampbell

Sec8

Manages grocery lists on OurGroceries.com, allowing users to retrieve, add, remove, update, and toggle items across their lists.

Setup Requirements

  • ⚠️Requires an existing OurGroceries.com account.
  • ⚠️Authentication relies on web scraping which can break if OurGroceries.com changes its login page or HTML structure.
  • ⚠️Node.js version 18 or higher is required.
Verified SafeView Analysis
The server uses a login flow that scrapes HTML and extracts an authentication cookie and team ID from OurGroceries.com. These credentials (authCookie and teamId) are stored locally in a configuration file, with attempts to set restrictive file permissions (0600 on Unix-like systems) for security. While this improves local security, the stored credentials could be compromised if the local machine is breached. The dependency on HTML scraping for login makes it potentially brittle if OurGroceries.com changes its website structure. No 'eval' or obvious malicious patterns were found in the provided code.
Updated: 2025-11-28GitHub→
0
0
Low Cost
Rimshasultan11 icon

gemini-cli-mcp-server

by Rimshasultan11

Sec1

Provides a server component that integrates with the Gemini command-line interface, likely facilitating interactions with a backend control plane or specific Gemini services.

Review RequiredView Analysis
CRITICAL: Unable to perform a security audit due to missing source code. Without code, cannot check for dangerous functions like `eval`, potential network vulnerabilities, hardcoded secrets, or other malicious patterns. **Running this project without a full code review is extremely risky as its security posture cannot be assessed.**
Updated: 2025-12-03GitHub→
0
0
High Cost
fuzzylabs icon
Sec9

A comprehensive security validation framework for Model Context Protocol (MCP) servers, including static code analysis, dependency scanning, and MCP-specific threat detection.

Setup Requirements

  • ⚠️Requires Node.js 16+ and npm to run scripts and manage JavaScript dependencies.
  • ⚠️Requires Python 3.8+ and pip for Python-based scanning scripts and dependencies.
  • ⚠️Requires 'uv' (installed via curl script) to manage and run 'mcp-scan' tool effectively.
  • ⚠️A GitHub Token (GITHUB_TOKEN environment variable) is required for full functionality, particularly for version and vulnerability monitoring, and repository cloning.
Verified SafeView Analysis
This project is a security validation framework, not an MCP server itself. Its code demonstrates strong security practices for a scanner: leveraging temporary directories for cloning, retrieving sensitive tokens from environment variables, and utilizing established security tools like Bandit, ESLint, Semgrep, npm audit, safety, and mcp-scan. The project explicitly states it performs no live testing or runtime analysis of scanned code, significantly mitigating the risk of executing untrusted code. Some scan results in `data/servers.json` show errors with `mcp-scan` invocation, which indicates operational fragility, but not a fundamental security design flaw in the scanner itself. Overall, it is robustly designed for its stated purpose.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
scopweb icon
Sec4

Provides PDF manipulation functionalities (split, compress, info) accessible via HTTP API and as an MCP server for Claude Desktop.

Setup Requirements

  • ⚠️Requires Go 1.24+ for compiling from source.
  • ⚠️Requires Claude Desktop installed and configured for MCP functionality if using the `mcp-server` binary.
  • ⚠️PDF file paths provided to the MCP server must be absolute (not relative or user-relative), and the server process needs explicit read/write access to these paths.
  • ⚠️Temporary files are created for PDF processing operations, requiring sufficient disk space and potentially manual cleanup on server crashes.
Review RequiredView Analysis
The project includes a comprehensive security test suite (`test/security`) that identifies potential vulnerabilities like path traversal (CWE-22), command injection (CWE-78), race conditions, dangerous imports, and hardcoded secrets, and also acknowledges known CVEs in the `pdfcpu` dependency. However, critical gaps exist: 1. **Path Traversal (CWE-22):** User-provided file paths (`pdf_path`, `output_dir`, `output_path`) in both the `cmd/mcp-server` and `cmd/server` are passed directly to file system operations (e.g., `os.CreateTemp`, `os.MkdirAll`, `os.Rename`, `pdf.SplitPDFFile`, `pdf.CompressPDFWithDefaults`) without explicit, robust sanitization or validation at the application's entry points. While a simple `isSafePath` function exists in tests, it is not applied in the main server logic, creating a significant risk of arbitrary file access, reading, writing, or deletion outside intended directories. 2. **Denial of Service (DoS) - Malicious PDF input:** The `isValidPDFFile` function, which performs basic PDF header and size validation for DoS prevention, is present only in the test suite (`test/security/cves_test.go`) and is not explicitly applied to user-uploaded PDF files in `cmd/server` or user-specified `pdf_path` in `cmd/mcp-server`. This leaves the system vulnerable to resource exhaustion or crashes when processing malformed or extremely large untrusted PDF files, especially given `pdfcpu` has known DoS-related CVEs. 3. **Temporary File Handling:** Although temporary files are deferred for removal in `cmd/server`, an application crash or forceful termination could leave these files on disk, potentially leading to disk space exhaustion or information leakage. Cleanup of split parts is done in a delayed goroutine, which is not robust against immediate server termination. 4. **Dependency Risk:** The core `pdfcpu` library has known vulnerabilities, including path traversal and DoS. The lack of robust application-level input validation exacerbates these inherent risks.
Updated: 2026-01-07GitHub→
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→
PreviousPage 686 of 760Next