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
t3ta icon

coduck

by t3ta

Sec8

Orchestrates Codex jobs in isolated Git worktrees, integrated with Claude Code via the Model Context Protocol (MCP) server for automated code generation, review, and deployment.

Setup Requirements

  • ⚠️Requires Node.js 18+
  • ⚠️Requires Codex CLI (`codex`) to be installed and accessible on PATH (or configured via `CODEX_CLI_PATH`)
  • ⚠️Requires Git to be installed and accessible on PATH (or configured via `GIT_PATH`)
  • ⚠️Manual configuration required in `~/.claude.json` with absolute paths for MCP server integration
  • ⚠️No Docker or containerization setup provided; manual Node.js/Git environment management is needed
Verified SafeView Analysis
The system uses `execFile`/`spawn` for Git and Codex CLI commands, which is inherently safer against shell injection than `exec`. A critical security measure, `validateRepoUrl`, mitigates SSRF by restricting external Git repository URLs to a configurable whitelist (GitHub and GitLab by default) and enforcing absolute local paths for 'no-worktree' mode. This protects the worker from fetching from malicious external URLs or making unintended requests to internal network services. No obvious hardcoded secrets, 'eval' calls, or code obfuscation were found. The 'no-worktree' mode, while intentional, allows the worker to operate directly on a specified absolute path (often `process.cwd()`), meaning a compromised orchestrator or an untrusted job creator could potentially cause unintended file system modifications outside of isolated worktrees. However, this is mitigated by validation on the `repo_url` for 'no-worktree' jobs (must be absolute path) and the design choice to not automatically clean up these directories.
Updated: 2025-12-12GitHub→
0
0
Low Cost
joecwales-outlawmindai icon

mcp-servers

by joecwales-outlawmindai

Sec1

Provides server implementations primarily for Minecraft-related development and modding activities.

Review RequiredView Analysis
Source code was not provided for analysis beyond the README title. Therefore, a comprehensive security audit could not be performed for 'eval', obfuscation, network risks, hardcoded secrets, or malicious patterns. The score reflects an inability to verify safety due to missing information.
Updated: 2025-12-03GitHub→
0
0
Medium Cost
cfahlgren1 icon

hf-dataset-mcp

by cfahlgren1

Sec9

Access and query Hugging Face datasets programmatically for AI and machine learning workflows.

Setup Requirements

  • ⚠️Requires Node.js runtime environment.
  • ⚠️Hugging Face API token (HF_TOKEN) is required for private or gated datasets.
Verified SafeView Analysis
The server acts as a proxy to the Hugging Face Hub and Dataset Viewer APIs. It uses environment variables (`HF_TOKEN`) for authentication, which is a secure practice. Input validation is performed using Zod schemas for all tool arguments. There are no direct usages of `eval` or `child_process.exec` (or similar dangerous functions) in the provided source code that would indicate arbitrary code execution vulnerabilities. The 'SQL-like' WHERE conditions for filtering are passed to an upstream Hugging Face API, relying on that service for secure interpretation rather than executing SQL directly within this server.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
AamnaAnsari icon

mcp-server

by AamnaAnsari

Sec3

Provides a custom server for Minecraft clients to connect and interact with, likely offering custom gameplay, features, or modifications.

Review RequiredView Analysis
Cannot perform a security audit as the source code was not provided. Without access to the code, it's impossible to check for malicious patterns, hardcoded secrets, 'eval' usage, or network vulnerabilities. Therefore, a low score is assigned due to unverified risk.
Updated: 2025-12-03GitHub→
0
0
Low Cost
bruvik icon

omnifocus-mcp

by bruvik

Sec8

Provides a Model Context Protocol (MCP) server to allow AI assistants (like Claude Code) to manage tasks in OmniFocus on macOS via AppleScript automation.

Setup Requirements

  • ⚠️Requires macOS with OmniFocus installed and running.
  • ⚠️Requires Python 3.11+.
  • ⚠️Initial setup involves creating a Python virtual environment and installing dependencies.
Verified SafeView Analysis
The server primarily uses `subprocess.run` to execute AppleScript commands (`osascript`). While the Python wrapper correctly passes arguments as a list to prevent shell injection, the security ultimately relies on the robustness of the AppleScripts and OmniFocus against potentially malicious input. Since the server is designed to run locally and interact with a trusted application, the risk is mitigated. No hardcoded secrets or arbitrary code execution (`eval`, `exec`) on user input were found in the Python codebase.
Updated: 2026-01-02GitHub→
0
0
Medium Cost
asmdrk icon

mcp-spotty

by asmdrk

Sec6

An MCP server providing tools to interact with the Spotify API, allowing an AI agent to fetch currently playing songs or search for song details.

Setup Requirements

  • ⚠️Requires Spotify API credentials (client ID and secret) to be obtained from the Spotify Developer Dashboard and set as environment variables.
  • ⚠️A manual OAuth flow must be performed once by running `python3 src/get_token.py` to acquire and save the Spotify access token to 'token.json'. This involves opening a browser for user login and authorization.
  • ⚠️The Spotify application's redirect URIs must be configured to match `http://127.0.0.1:3000/callback` (for token acquisition) and `http://127.0.0.1:3001/mcp` (for server operation).
Verified SafeView Analysis
Spotify API credentials (client ID and secret) are correctly loaded from environment variables. However, the Spotify OAuth token is stored locally in 'token.json', which is a security risk if the server is deployed without proper token management (e.g., encryption, secrets manager, or a more robust refresh token flow). Debug-level logging by default could expose sensitive information. Hardcoded 'localhost' redirect URIs are suitable for local development but would need careful configuration and HTTPS for production deployment.
Updated: 2025-11-27GitHub→
0
0
Medium Cost
wireweave icon

mcp-server

by wireweave

Sec9

Enables AI assistants to generate, validate, render, and manage wireframes using the Wireweave DSL by providing a tool-based interface through the Model Context Protocol.

Setup Requirements

  • ⚠️Requires a Wireweave API Key from dashboard.wireweave.org (Paid).
  • ⚠️API Key must be set as `WIREWEAVE_API_KEY` environment variable.
  • ⚠️Designed for integration with Claude Desktop, requiring specific JSON configuration (`claude_desktop_config.json`).
Verified SafeView Analysis
The MCP server acts as a thin client, forwarding requests to an external Wireweave API. It uses environment variables for sensitive data like API keys, sanitizes logs to prevent accidental exposure of secrets, and robustly constructs API requests by handling path and query parameters. The security of the overall system heavily relies on the upstream Wireweave API Server, which is beyond the scope of this audit. No direct 'eval' or other malicious code patterns, obfuscation, or hardcoded sensitive secrets were found in the provided code.
Updated: 2026-01-19GitHub→
0
0
High Cost
vosamoilenko icon

mcp-youtube-transcript

by vosamoilenko

Sec8

Provides tools for AI assistants to fetch, search, and analyze YouTube video transcripts and retrieve channel video lists.

Setup Requirements

  • ⚠️Requires Node.js >= 18.0.0
  • ⚠️Requires Python 3
  • ⚠️Requires 'youtube_transcript_api' Python package (pip install youtube-transcript-api)
Verified SafeView Analysis
The server uses 'child_process.execFile' to run a Python script for transcript fetching. While generally safer than 'exec' due to arguments being passed separately, it still involves executing an external process. Input validation is performed for video/channel IDs, mitigating direct command injection risk for the Python script arguments. No 'eval' or obvious obfuscation was found. No hardcoded secrets were identified.
Updated: 2026-01-17GitHub→
0
0
Low Cost
payincom icon

402ok-mcp

by payincom

Sec8

Provides a Model Context Protocol (MCP) server middleware to integrate HTTP 402 Payment Required for AI tools, supporting multi-network blockchain payments with a focus on XLayer/OKX.

Setup Requirements

  • ⚠️Requires OKX API Key, Secret Key, and Passphrase with x402 permissions for XLayer payments if using the OKX facilitator.
  • ⚠️Requires configuration of a recipient wallet address for payments.
  • ⚠️Requires the `URL` environment variable to be set for the server's external URL if not running on `http://localhost:3000` to correctly construct payment resource URIs.
  • ⚠️This is a library/middleware; users must write their own application (e.g., using Express) to host the MCP server functionality.
Verified SafeView Analysis
The project uses standard cryptographic practices (HMAC SHA256) for OKX API authentication and relies on environment variables for sensitive credentials (API keys, secret keys, passphrases). The design separates payment verification/settlement to external facilitators, reducing direct blockchain interaction risk for the server. However, `makeOKXRequest` logs full request headers (which may contain API keys) and body to console, which could pose an information leakage risk in a production environment if logs are not securely managed. The JSON parsing of base64-encoded payment metadata is a standard practice but should be handled robustly against malformed inputs.
Updated: 2025-12-05GitHub→
0
0
Low Cost
SaiVSrini icon

mcpfinder

by SaiVSrini

Sec8

A personal tool router that answers natural language queries to recommend the most relevant developer tools and MCP servers.

Setup Requirements

  • ⚠️Requires OpenAI API Key (Paid) for optimal performance, otherwise falls back to heuristic scoring.
  • ⚠️Requires a populated SQLite database file (`mcpfinder.sqlite`), which must be generated from `db_with_embeddings.csv` by running `mcp_suggester/load_mcp_csv_to_sqlite.py`.
Verified SafeView Analysis
The project adheres to good practices by retrieving API keys from environment variables and using parameterized queries for SQLite interactions, mitigating common injection risks. The data loading from CSV to SQLite includes JSON parsing with error handling for embedded vectors. The `api_server.py` component defaults to binding on `0.0.0.0` (all network interfaces), which should be secured if exposed to untrusted networks, but this is an optional server and not the default `command` type usage with Cursor.
Updated: 2025-12-07GitHub→
0
0
Low Cost
ifiecas icon

spotify-mcp

by ifiecas

Sec5

Connects Microsoft Copilot Studio AI agents to the Spotify Web API to enable music search, artist information, track details, and audio analysis.

Setup Requirements

  • ⚠️Requires Python 3.11+ to run.
  • ⚠️Requires a Spotify Developer Account to obtain Client ID and Secret.
  • ⚠️Requires a secure, manually generated `LOCAL_TOKEN` environment variable for authentication.
  • ⚠️Requires an Azure Account for cloud deployment and Microsoft Copilot Studio for AI agent integration.
Verified SafeView Analysis
The server uses a simple Bearer token for authentication with a single, shared secret (`LOCAL_TOKEN`). This is explicitly noted in the README as being for development/demo purposes and is not suitable for production environments due to lack of advanced security features like OAuth, user-specific access control, token expiration, rate limiting, and secure secret management (e.g., Azure Key Vault). If the `LOCAL_TOKEN` is compromised, the server is fully accessible. However, the source code does not contain direct malicious patterns, arbitrary code execution (like `eval`), or hardcoded secrets (it relies on environment variables).
Updated: 2025-11-20GitHub→
0
0
Low Cost
Intra-Pay icon

mcp-server

by Intra-Pay

Sec9

A Model Context Protocol (MCP) server exposing Brazilian Pix payment (cash-in/cash-out) and webhook operations from the Intra Pay API to AI agents and IDEs.

Setup Requirements

  • ⚠️Requires Node.js 20+ to run.
  • ⚠️Requires an Intra Pay account with API access keys and IP allowlisting configured on their dashboard.
  • ⚠️Requires an .env file with INTRAPAY_BASE_URL, INTRAPAY_CLIENT_KEY, INTRAPAY_CLIENT_SECRET, INTRAPAY_ENV, and PORT configured.
Verified SafeView Analysis
The server properly handles sensitive API keys and secrets by requiring them via environment variables (INTRAPAY_CLIENT_KEY, INTRAPAY_CLIENT_SECRET, INTRAPAY_WEBHOOK_SECRET), rather than hardcoding them. It implements a token caching mechanism to minimize authentication calls. Network requests to the external Intra Pay API include retry logic with exponential backoff and comprehensive error normalization. Logging is implemented with caution, explicitly avoiding the logging of secrets. The README advises enabling IP allowlisting on the Intra Pay dashboard, indicating good security awareness. No 'eval' or similar dangerous dynamic code execution patterns were identified.
Updated: 2025-11-26GitHub→
PreviousPage 316 of 760Next