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
High Cost
macjunkins icon

rapid-mcp-commands

by macjunkins

Sec9

Provides shared YAML command definitions for Rapid MCP Server implementations to perform various AI-assisted development tasks, including GitHub operations, documentation generation, and project analysis.

Setup Requirements

  • ⚠️Requires GitHub CLI (`gh`) installed and authenticated with appropriate permissions (e.g., 'Issues'/'Pull requests' write permissions for milestone creation).
  • ⚠️Requires Git CLI installed and configured.
  • ⚠️Many commands are tailored for Flutter/Dart projects, implicitly requiring `flutter` and `dart` CLIs for full functionality.
  • ⚠️GitHub CLI's lack of native milestone commands for 'gh milestone create' means `gh api` calls are used, which is a specific implementation detail.
Verified SafeView Analysis
The repository contains command definitions in Markdown format, which primarily describe interactions with Git and GitHub CLI. The workflows explicitly include 'Preview & Get Approval' steps before executing potentially destructive commands (`git push`, `gh pr create`, `gh issue close`, `gh api`). There is no 'eval' or direct malicious code present in the definitions. Security depends heavily on the execution environment of the Rapid MCP Server (not provided in this repository) and user oversight of command previews.
Updated: 2025-11-22GitHub→
0
0
Medium Cost
xenoxavier icon
Sec3

Provides programmatic access to analyze TradingView Pine Script indicators via the Model Context Protocol (MCP).

Setup Requirements

  • ⚠️Requires Node.js (>=18) if run locally or Docker if containerized.
  • ⚠️Expects Pine Script indicator files to be present in the server's current working directory or a mounted volume that makes them accessible.
  • ⚠️Designed to work with an MCP-compatible client like Claude Desktop, requiring specific configuration for interaction.
Review RequiredView Analysis
CRITICAL: The `analyze_indicator` and `extract_functions` tools are vulnerable to path traversal. The `indicatorName` argument is directly used in `readIndicatorFile` without validation against a whitelist of allowed files or sanitization (e.g., preventing `../` sequences). This allows an attacker to read arbitrary files from the server's working directory or parent directories (e.g., `../../package.json`, `../../Dockerfile`, or potentially other sensitive configuration files on the host system if Docker volume mounting isn't perfectly restrictive). Although the Docker volume is mounted as read-only, this still poses a significant information disclosure risk. Network risks are low due to stdio transport, and no obvious hardcoded secrets or 'eval' are present.
Updated: 2025-11-25GitHub→
0
0
Low Cost
david-pizzi-cg icon

github-mcp-demo

by david-pizzi-cg

Sec9

Demonstrates a human-guided AI DevOps workflow using GitHub MCP Server and VS Code Copilot for issue tracking, code fixing, and pull request management.

Setup Requirements

  • ⚠️Requires VS Code with GitHub Copilot extension authenticated.
  • ⚠️Requires GitHub MCP Server to be installed and running (an external dependency).
  • ⚠️Requires a Git repository connected to GitHub with appropriate permissions for issues and pull requests.
Verified SafeView Analysis
The provided client-side JavaScript (`script.js`) for the World Clock application is safe, with no `eval`, direct external API calls (it simulates data), or hardcoded secrets. The overall security of the demo system depends on the GitHub MCP Server implementation and the permissions granted to GitHub Copilot, which are external components to this specific codebase.
Updated: 2025-11-22GitHub→
0
0
Low Cost

mcp-remote-vault-demo

by Great-Stone

Sec9

A system demo where Model Context Protocol (MCP) servers manage dynamic user-specific credentials using HashiCorp Vault.

Setup Requirements

  • ⚠️Requires Docker and Docker Compose for service orchestration.
  • ⚠️Requires Python 3 and curl for executing initialization scripts.
  • ⚠️Keycloak requires approximately 30 seconds to start before running its initialization script, followed by the Vault initialization script in sequence.
Verified SafeView Analysis
The project uses well-established security tools (Vault, Keycloak) for authentication and secret management. Services run locally via Docker Compose, limiting external exposure. The use of a 'root-token' for Vault initialization is standard for local demos but should never be used in production.
Updated: 2025-11-17GitHub→
0
0
Low Cost
zero-to-prod icon

mcp-template

by zero-to-prod

Sec8

This repository serves as a template for creating custom Model Context Protocol (MCP) servers in PHP, allowing developers to quickly scaffold and deploy tool-based services.

Setup Requirements

  • ⚠️Requires `php configure.php` execution after cloning to customize the template.
  • ⚠️Requires PHP 8.4 or higher.
  • ⚠️Docker is the recommended method for development and deployment.
Verified SafeView Analysis
The `configure.php` script uses `shell_exec` for system interactions (e.g., git config, grep), which is inherently risky if user input were directly passed. However, this script is designed for one-time developer setup and is not part of the runtime server. The core server runtime (`public/index.php`) does not show direct `eval` or `shell_exec` on untrusted input. Environment variables (`APP_DEBUG`, `MCP_DEBUG`, `APP_VERSION`) are used for configuration, which is good practice. File-based session storage (`storage/mcp-sessions`) requires appropriate file permissions. No obvious hardcoded secrets or malicious patterns were found in the provided runtime source code.
Updated: 2025-12-11GitHub→
0
0
Medium Cost
omandotkom icon

oraclemcp

by omandotkom

Sec6

Enables LLMs to interact with Oracle databases for schema inspection and read-only query execution.

Setup Requirements

  • ⚠️Requires an existing Oracle Database instance for connection.
  • ⚠️Requires Go (1.18+) installed to build the executable.
  • ⚠️Requires setting three specific environment variables (`ORACLE_USER`, `ORACLE_PASSWORD`, `ORACLE_CONNECT_STRING`) for database connection.
Verified SafeView Analysis
The `sql-select` tool directly executes arbitrary `SELECT` or `WITH` SQL queries provided by the LLM. While this is its intended purpose, it means any LLM (or compromised input from an LLM) can query *any* data accessible by the configured `ORACLE_USER`. This poses a significant data exfiltration risk and potential for resource exhaustion (even if result rows are truncated, the query itself can be expensive). Error messages might expose internal database details. The `list-tables` and `get-table-schema` tools use parameterized queries or hardcoded SQL and are safer. Configuration is via environment variables, preventing hardcoded secrets. No 'eval' or similar dangerous functions were found.
Updated: 2026-01-19GitHub→
0
0
Low Cost
yfzhou0904 icon

chatgpt-handoff-mcp

by yfzhou0904

Sec8

A minimal MCP server for seamless handoff of prompts from Claude Code to ChatGPT by copying them to the system clipboard.

Setup Requirements

  • ⚠️Linux users require 'xclip' or 'xsel' to be installed for clipboard functionality.
  • ⚠️Requires manual configuration in Claude Code's settings.json file (~/.config/claude-code/settings.json).
  • ⚠️If using HTTP transport mode, the server must be manually started and kept running in a separate process.
Verified SafeView Analysis
The server uses `exec.Command` for cross-platform clipboard operations. While the prompt content is generally passed via stdin to `pbcopy`, `xclip`, or `xsel`, and securely via a PowerShell here-string on Windows, this pattern always carries a theoretical, albeit low, risk of command injection or unforeseen interpretation of special characters by the external utilities if the input is malicious. However, no 'eval' or direct command-line argument injection using user input was found. There are no hardcoded secrets, and network exposure is limited to a local HTTP server if enabled.
Updated: 2025-11-26GitHub→
0
0
Low Cost
psimsa icon

oig_cloud_mcp

by psimsa

Sec8

Acts as a Model Context Protocol (MCP) server for OIG Cloud, providing an authenticated and observable tool-driven interface to the OIG Cloud API.

Setup Requirements

  • ⚠️Requires Python 3.12+.
  • ⚠️Depends on 'oig-cloud-client' from a direct Git repository, which might require Git to be installed and can be less stable than a PyPI package.
  • ⚠️Requires 'whitelist.txt' to be present for any user authentication to succeed, with user emails listed in it.
  • ⚠️For secure operation, the server should always be deployed behind HTTPS, as credentials are sent via HTTP headers (Base64-encoded or plaintext).
Verified SafeView Analysis
Implements whitelist and rate limiting for authentication (in-memory, suitable for single-process only). Uses SHA256 for credential hashing. Provides dedicated fail2ban logging for authentication failures. Basic Auth and custom header credentials are sent via HTTP headers, which implicitly requires HTTPS for secure transmission. No 'eval' or malicious patterns found. The primary security limitation is the in-memory nature of the whitelist and rate limiter, which is suboptimal for distributed production deployments.
Updated: 2025-12-03GitHub→
0
0
Low Cost
srinivasan-govindaraj icon

MCPSERVE

by srinivasan-govindaraj

Sec1

A server backend, likely related to the Minecraft Protocol (MCP), intended for game hosting or application services.

Review RequiredView Analysis
CRITICAL: No source code was provided for analysis beyond the README title. Therefore, no security audit could be performed. Running any server without inspecting its source code for vulnerabilities (like 'eval', obfuscation, network risks, or hardcoded secrets) is extremely dangerous and highly discouraged. It is impossible to assess its safety, and it poses a severe security risk due to the complete lack of transparency.
Updated: 2025-12-05GitHub→
0
0
Low Cost
jardhel icon

seu-claude

by jardhel

Sec8

Provides a local Model Context Protocol (MCP) server for Claude Code, enabling proactive semantic indexing of entire codebases using AST-based chunking, cross-reference tracking, and efficient local vector search to enhance Claude's understanding and retrieval capabilities.

Setup Requirements

  • ⚠️Requires Node.js version 20 or greater.
  • ⚠️Initial setup involves downloading Tree-sitter language grammars, typically handled automatically by a `postinstall` script or manually via `npm run download-grammars`.
  • ⚠️The embedding model (~30-70MB) will download on first use or can be pre-downloaded via `npm run download-model`.
  • ⚠️Requires the `git` CLI installed for git-aware features and for the automated setup script to detect the project root.
Verified SafeView Analysis
The server uses `execSync` for internal system operations (like Git commands and Node.js version checks), which is generally safe when inputs are controlled and not directly user-provided. Input validation (`validateFilePath`, `validateSearchQuery`) is implemented to prevent common path traversal and injection attacks on file paths and search queries. The embedding engine downloads models from HuggingFace, a standard external dependency for AI models. No hardcoded secrets were found. The primary risk is the inherent nature of running arbitrary `npx` commands or misconfiguring system paths, which is mitigated by input validation for tool arguments.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
MindPort-GmbH icon

MCP-tools-for-VR-Builder

by MindPort-GmbH

Sec8

Enables AI assistants to programmatically create and modify VR Builder training processes within the Unity editor.

Setup Requirements

  • ⚠️Requires Unity 6000.0.x or higher.
  • ⚠️Requires VR Builder Core 5.5.0 or higher package.
  • ⚠️Requires at least one Unity MCP framework (CoplayDev or IvanMurzak) to be installed.
  • ⚠️When using com.ivanmurzak.unity.mcp, JSON input field names must be camelCase.
Verified SafeView Analysis
The Python tool `create_vr_builder_process` constructs a structured JSON payload to send commands to a Unity-based MCP server. There are no explicit `eval` or direct arbitrary code execution patterns visible in the provided Python code. The primary security consideration would be the robustness of the Unity-side implementation of `VRBuilderProcessService` against crafted inputs, which is not provided. Given it operates within a Unity development environment, typical remote server risks are mitigated.
Updated: 2025-12-05GitHub→
0
0
Medium Cost
Runscope icon

mcp-bzm-apitest

by Runscope

Sec9

The BlazeMeter API Test MCP Server allows AI agents to manage teams, buckets, tests, schedules, steps, environments, and analyze results within the BlazeMeter API Monitoring platform.

Setup Requirements

  • ⚠️Requires a BlazeMeter API Monitoring Access Token.
  • ⚠️Requires compliance with BlazeMeter API Monitoring AI Consent settings.
  • ⚠️Python 3.11+ is required for installation from source code.
Verified SafeView Analysis
The server employs good security practices, including the use of `defusedxml` to prevent XML External Entity (XXE) attacks and `nh3` for HTML sanitization to mitigate Cross-Site Scripting (XSS) vulnerabilities. API tokens are designed to be handled via environment variables or secure files, avoiding hardcoding. Input validation is applied for different body types (JSON, XML, HTML, text).
Updated: 2025-11-27GitHub→
PreviousPage 634 of 760Next