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
collinsoik icon

nl2tcl-mcp

by collinsoik

Sec6

Exposes Yosys synthesis and Icarus Verilog simulation tools to Claude Code for FPGA design workflows.

Setup Requirements

  • ⚠️Requires `yosys` and `iverilog` (including `vvp`) to be installed system-wide as command-line tools.
  • ⚠️Requires Python 3.10+.
Review RequiredView Analysis
The server includes a TCL validator to block dangerous commands (`exec`, `file delete`, `source`, shell pipes, etc.) when executing Yosys TCL. However, it is susceptible to path traversal vulnerabilities: 1. **Arbitrary File Write:** The `yosys_synthesize` tool's `output_json` argument allows writing to arbitrary file paths if an absolute path or `../` sequence is provided, potentially overwriting system files. 2. **Information Disclosure:** The `list_designs` and `get_design_content` tools' `directory` and `name` arguments can be manipulated with absolute paths or `../` to list or read files outside the intended project directories. No hardcoded secrets or direct network listening are apparent (uses stdio transport).
Updated: 2025-12-12GitHub→
0
0
Low Cost
razeone icon

mcp-weather

by razeone

Sec8

This server provides weather information, including alerts for US states and forecasts for specific coordinates, by interacting with an external weather API.

Setup Requirements

  • ⚠️Requires .NET SDK to build and run.
  • ⚠️Relies on external Weather.gov API, which may have usage policies or rate limits.
  • ⚠️Requires an active internet connection to fetch weather data.
Verified SafeView Analysis
The provided source code is limited to the README, which describes an architecture prioritizing input validation (via Value Objects like StateCode, Coordinates) and clear separation of concerns, generally contributing to a more secure system. No 'eval' or malicious patterns are visible. Interaction with an external 'WeatherGovService' implies network calls, which would require secure handling (e.g., TLS, input sanitization, error handling) in the actual implementation, but this is not verifiable from the provided text. Hardcoded secrets are not evident in the README.
Updated: 2025-12-01GitHub→
0
0
Low Cost
kgatilin icon

go-mcp-template

by kgatilin

Sec9

A production-ready Go template for building Model Context Protocol (MCP) servers, designed to follow official best practices and support both MCP client integration and direct command-line tool execution.

Setup Requirements

  • ⚠️Requires Go 1.23 or higher.
  • ⚠️Mandatory cleanup of example tools, resources, and prompts, and updating registration functions after cloning or using the template.
  • ⚠️Requires renaming the Go module and updating imports throughout the codebase if used as a new project.
Verified SafeView Analysis
The template demonstrates and strongly enforces security best practices including comprehensive input validation and sanitization, proper error handling, context cancellation, and the use of environment variables for secrets. It explicitly warns against common pitfalls like hardcoding secrets or unsafe SQL string concatenation. For HTTP transport, it mandates TLS, authentication, and rate limiting. The `internal/resources/files.go` includes path cleaning. The score isn't 10 because a template relies on developer adherence to its guidelines for true security, but it provides an excellent foundation and strong guidance.
Updated: 2025-11-19GitHub→
0
0
Medium Cost
denkaryo icon

cf-rawg

by denkaryo

Sec8

An AI agent for analyzing video game data using the RAWG API, deployed on Cloudflare Workers.

Setup Requirements

  • ⚠️Requires RAWG API key (Paid/Free, depending on usage limits)
  • ⚠️Requires OpenAI API Key OR Anthropic API Key (Paid, depending on LLM_PROVIDER)
  • ⚠️Requires Node.js 20+ and pnpm 10+
  • ⚠️Cloudflare Workers CPU time limit of 30 seconds requires a paid Cloudflare plan for optimal performance.
Verified SafeView Analysis
The server uses QuickJS in a sandboxed environment for `execute_calculation`, with a validator that actively checks for dangerous patterns like `eval`, `new Function()`, `process`, and network access (`fetch`). This significantly mitigates risks associated with arbitrary code execution. Client-side evaluation in the UI's 'Evaluation Panel' uses `new Function()`, but this is confined to the user's browser for debug purposes and does not pose a server-side vulnerability. All sensitive API keys are correctly managed via environment variables.
Updated: 2025-11-28GitHub→
0
0
Low Cost
FYTJ icon
Sec3

A server that enables remote debugging capabilities by exposing LLDB functionalities over a TCP-based protocol.

Setup Requirements

  • ⚠️Requires macOS with Xcode or Command Line Tools installed.
  • ⚠️Requires Python 3.12.
  • ⚠️Requires careful configuration of Python and LLDB framework paths (PYTHONPATH, DYLD_FRAMEWORK_PATH, DYLD_LIBRARY_PATH) for 'import lldb' to succeed.
Review RequiredView Analysis
The server exposes powerful LLDB debugging primitives (e.g., lldb.command, lldb.evaluate, lldb.launch, lldb.attach, lldb.readMemory, lldb.writeMemory) over an unauthenticated TCP connection. While default listening is on 127.0.0.1, configurable host/port allows broader network exposure. There are no explicit authentication or fine-grained authorization mechanisms beyond LLDB_MCP_ALLOW_LAUNCH and LLDB_MCP_ALLOW_ATTACH environment variables, which only cover specific process operations and not the arbitrary command/evaluation features. This means any client connecting to the server can execute arbitrary lldb commands, evaluate expressions, and manipulate processes on the host machine, posing a significant privilege escalation and system compromise risk if deployed in an untrusted environment or made network-accessible.
Updated: 2025-12-03GitHub→
0
0
Low Cost
Sec7

Provides a token-efficient pentesting system for Claude Code by executing commands directly in a Kali Linux Docker container.

Setup Requirements

  • ⚠️Docker must be installed and running.
  • ⚠️Requires manual copying and renaming of 'Dockerfile-kali-simple' and 'docker-compose-kali.yml' to 'Dockerfile' and 'docker-compose.yml' respectively.
  • ⚠️Requires local file system access for Claude skills directory (/mnt/skills/user/).
  • ⚠️Requires elevated privileges to interact with the Docker daemon for container management and command execution.
Verified SafeView Analysis
The system design for direct 'docker exec' command execution minimizes network exposure related to a server interface. The primary security risk is the potential misuse of the powerful pentesting tools included in the Kali Linux container. Strict adherence to ethical and legal guidelines for pentesting is crucial, as explicitly stated in the 'Legal Notice'.
Updated: 2025-11-17GitHub→
0
0
Medium Cost
cyverse-de icon

formation-mcp

by cyverse-de

Sec9

Connects Claude Code (an AI assistant) to the CyVerse Discovery Environment to enable natural language management of scientific applications, analyses, and data.

Setup Requirements

  • ⚠️Requires a CyVerse Discovery Environment account and credentials (username/password or JWT token).
  • ⚠️Requires configuration in `~/.claude.json` or `~/.formation-mcp.yaml` with CyVerse API base URL and authentication details.
  • ⚠️If building from source, Go 1.25.3 or later is required.
Verified SafeView Analysis
The server handles authentication externally (via token or username/password) and uses HTTPS for API communication. It avoids `eval`-like functions. The `open_in_browser` functionality uses system commands (`open`, `xdg-open`, `cmd /c start`) which, while standard for URL opening, inherently rely on the host OS's handling and could be a very minor theoretical vector if an extremely malformed URL were passed and mishandled by the OS (though current usage passes raw URL directly). Overall, the code appears robust and follows good security practices for a Go application.
Updated: 2025-11-20GitHub→
0
0
Medium Cost
AnnaSuSu icon

arxiv-mcp

by AnnaSuSu

Sec8

Enables LLMs to search, download, and read scientific papers from arXiv, providing direct access to scientific literature for AI assistants.

Setup Requirements

  • ⚠️Requires `uv` to be installed for recommended execution (`uvx`).
  • ⚠️Python 3.10+ is required.
  • ⚠️`pymupdf` (a dependency) may have native system library requirements, though `uv` typically handles these dependencies well.
Verified SafeView Analysis
The server uses the `arxiv` library to fetch paper metadata and URLs, and `urllib.request.urlretrieve` to download PDFs. PDF text extraction is handled by `pymupdf` (fitz). Potential security considerations include vulnerabilities in `pymupdf` when processing malformed PDFs (a common risk with any PDF parser) and the `download_paper` tool's `target_dir` parameter. While this parameter is for a specific tool and intended functionality, it could allow a malicious client to attempt to write files to arbitrary locations if not properly validated or sandboxed by the client-side system. The server's internal storage (`get_paper` tool) uses a controlled directory. No direct 'eval' calls, obfuscation, or hardcoded secrets were found in the provided source code. File path sanitization (`paper_id.replace('/', '_')`) is applied for local storage management.
Updated: 2026-01-04GitHub→
0
0
Medium Cost
apopovic77 icon

mcp-server

by apopovic77

Sec4

Aggregates multiple microservice APIs (Storage, O'Neal, Artrack, CodePilot, AI, Content, Tarot) under a single FastAPI interface, providing a unified toolset for various domain-specific operations, including AI-driven content, human-in-the-loop interactions, and general API orchestration.

Setup Requirements

  • ⚠️Requires multiple external API keys for full functionality (e.g., ARKTURIAN_API_KEY, ONEAL_STORAGE_API_KEY, ARTRACK_API_KEY, TELEGRAM_API_KEY, CODEPILOT_API_TOKEN, AI_API_KEY).
  • ⚠️Python dependencies (uvicorn, fastapi, httpx, etc.) must be installed, preferably in a virtual environment as implied by the `start.sh` script looking for `venv/bin/uvicorn`.
  • ⚠️Disables SSL certificate verification (`verify=False`) in specific media fetching functions, which is a significant security vulnerability and should be addressed before deployment in any sensitive environment.
Review RequiredView Analysis
The server uses a highly permissive CORS configuration (allow_origins=['*']), which could be a risk for public deployments if not properly secured with additional authentication/authorization. More critically, several HTTP client calls disable SSL certificate verification (`verify=False`) when fetching media (`storage_media_as_data_url`, `oneal_storage_media_as_data_url`), opening up to man-in-the-middle attacks. A hardcoded 'oneal_demo_token' is present as a default API key for the O'Neal API. Most other sensitive API keys are correctly loaded from environment variables, and the server explicitly checks for the presence of `ARKTURIAN_API_KEY` and `ONEAL_STORAGE_API_KEY` at startup.
Updated: 2026-01-02GitHub→
0
0
Low Cost
betterhyq icon

sse-mcp-servers

by betterhyq

Sec8

This project provides server implementations for the Model Context Protocol (MCP), enabling external agents to interact with defined tools and services, exemplified by an 'add two numbers' function.

Setup Requirements

  • ⚠️Requires Node.js runtime (version 24.x or higher is indicated by `start:huaweiyun:node` and `tsconfig.json`).
  • ⚠️The Python server specifically requires Python 3.10.15.
  • ⚠️Uses pnpm for package management; `npm` or `yarn` might not work without adjustments.
  • ⚠️Specific ports (4000 for Node.js, 4100 for Python) need to be open and accessible.
Verified SafeView Analysis
The server implementations utilize strong schema validation for incoming parameters (Zod in Node.js, Pydantic Field in Python), which is crucial for mitigating injection and other input-related vulnerabilities. There are no explicit uses of 'eval' or arbitrary command execution based on user input within the provided code. The use of `execa` for spawning child processes is present (via `fastmcp` dependency) but typically for controlled internal operations. A deployment instruction in the README involving `sudo -S` is a high-privilege operation and should be handled with care in a production environment, but this is a deployment configuration risk, not a direct code vulnerability.
Updated: 2025-12-05GitHub→
0
0
Medium Cost

eth_trading_server

by keefey-yang

Sec5

Automated or semi-automated trading of Ethereum and other cryptocurrencies on a server.

Setup Requirements

  • ⚠️Rust toolchain required
  • ⚠️Access to Ethereum node (e.g., Infura, Alchemy, or self-hosted) required
  • ⚠️Cryptocurrency exchange API keys may be required
Review RequiredView Analysis
Source code not provided for analysis; unable to assess specific vulnerabilities like 'eval' or obfuscation. Network risks are unknown without code review. Given it's a trading server, significant financial risk is inherent if not properly secured and audited.
Updated: 2025-11-18GitHub→
0
0
Low Cost
BERDataLakehouse icon

datalake-mcp-server-client

by BERDataLakehouse

Sec9

A Python client library for programmatic interaction with the BERDL Datalake MCP Server, enabling operations like health checks, database/table listing, schema retrieval, and data querying for Delta Lake tables.

Setup Requirements

  • ⚠️Requires the 'datalake-mcp-server' repository to be cloned and present in the parent directory (`../datalake-mcp-server`) relative to this client repository for client generation.
  • ⚠️The client generation process explicitly uses Python 3.13.
  • ⚠️Requires the 'uv' package manager to be installed for setting up the virtual environment and installing dependencies during client generation.
Verified SafeView Analysis
The provided code is for a client library. The generation process (via `run.sh` and `generate_spec_from_local.py`) involves dynamically importing the `create_application` function from the *server's* local repository (`../datalake-mcp-server`) to generate the OpenAPI specification. This implies a trust relationship with the server's source code during the client build step. The generated client code itself uses standard Python practices and the `httpx` library, which is well-regarded for HTTP requests. No 'eval', obfuscation, hardcoded secrets, or unusual network risks are evident within the client library's runtime code. The documentation for `table_select_request` explicitly states that the server's backend builds queries safely, preventing SQL injection.
Updated: 2025-12-28GitHub→
PreviousPage 376 of 760Next