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
akousha icon
Sec8

An MCP server that exposes Oracle Primavera Data Service API tools for project management data analysis and reporting to LLMs and other MCP-compatible clients.

Setup Requirements

  • ⚠️Requires Node.js v18+ (v20+ recommended).
  • ⚠️Requires specific Primavera Data Service credentials configured as environment variables in a `.env` file for each tool.
  • ⚠️Designed for integration with MCP-compatible clients like Postman Desktop App, Claude Desktop, or GitHub Copilot Chat, not as a standalone web application.
Verified SafeView Analysis
The server correctly uses environment variables for all API credentials, preventing hardcoding of secrets. All external API calls are made over HTTPS, securing data in transit. Dynamic tool loading uses a statically defined path list, mitigating arbitrary code execution risks. A dependency (`pac-resolver` for proxy auto-configuration) uses code generation for legitimate purposes, which is a known pattern but always carries an inherent, albeit contained, risk. Direct exposure of `error.message` in API error responses could potentially leak minor internal details, but generally, the codebase follows good security practices for a generated server.
Updated: 2025-11-19GitHub→
0
0
Medium Cost

ssh-mcp-server

by ricklamers

Sec6

Enables AI agents to securely execute SSH commands on remote servers, managing persistent connections and multiple server configurations for tasks like system monitoring and deployment.

Setup Requirements

  • ⚠️Requires Node.js runtime environment.
  • ⚠️The Claude for Desktop configuration must specify the absolute path to `build/index.js`.
  • ⚠️SSH configuration (server details, credentials) must be provided as a JSON string via the `SSH_MCP_CONFIG` environment variable, potentially requiring complex shell commands for multi-line or file-based configurations.
Verified SafeView Analysis
The server executes arbitrary bash commands provided by the AI agent without explicit mention of internal sanitization or sandboxing, which poses a significant command injection risk if the AI generates malicious input. It handles sensitive SSH credentials (passwords, private keys, base64-encoded keys), which must be securely managed by the user to prevent exposure. While the README includes security considerations, the inherent functionality requires careful handling and validation by the user/calling agent to remain secure.
Updated: 2025-11-17GitHub→
0
0
Medium Cost
Sec7

Provides AI assistants (e.g., Claude for Desktop) with read, write, and delete access to a specified local file system directory via the MCP protocol.

Setup Requirements

  • ⚠️Docker must be installed on your system.
  • ⚠️Requires manual configuration of the volume mount path in 'docker-compose.yml' or the 'docker run' command to point to your desired local directory.
  • ⚠️Requires manual configuration of Claude for Desktop or other AI tool's MCP server settings.
Verified SafeView Analysis
The server grants full read, write, and delete capabilities to the specified mounted local directory. While contained within Docker, an unconstrained or exploited AI could potentially delete or modify important files within that mounted volume. Proper path sanitization in the 'server.py' (not provided for audit) is crucial to prevent path traversal attacks. No direct network exposure is indicated, as access is via 'docker exec'. The risk is primarily related to the scope of file system access granted to the AI.
Updated: 2025-11-19GitHub→
0
0
Medium Cost
Vishwasa2004 icon

mcp-regex-server

by Vishwasa2004

Sec5

This server provides a standardized interface (MCP) for performing regular expression searches within specified files, returning matching lines.

Setup Requirements

  • ⚠️Requires a Go development environment (Go 1.16+ typically) to build and run.
  • ⚠️Designed to communicate via standard input/output (stdin/stdout) using JSON, not a network port. It expects an external orchestrator to provide input and consume output.
  • ⚠️No built-in input validation or sanitization for file paths or regex patterns, which are critical for security.
Review RequiredView Analysis
The server allows searching arbitrary file paths (`file_path` argument) using a user-provided regex pattern (`pattern` argument). This introduces two significant risks if deployed in an untrusted environment or with untrusted input: 1. Local File Inclusion (LFI): An attacker could specify paths to sensitive system files (e.g., /etc/passwd) to extract their content. The current implementation only reads, not writes, files. 2. Regular Expression Denial of Service (ReDoS): Maliciously crafted complex regex patterns can consume excessive CPU resources, leading to a denial of service. There is no built-in input validation or sanitization for file paths or regex patterns.
Updated: 2026-01-19GitHub→
0
0
Low Cost
Yeahx1000 icon

mcp-weather

by Yeahx1000

Sec9

Serves weather information via the Model Context Protocol (MCP) as a tool for AI agents.

Setup Requirements

  • ⚠️Requires Claude Desktop installed to interact with the server as intended.
  • ⚠️Requires the `NWS_API_BASE` and `USER_AGENT` environment variables to be set for successful interaction with the National Weather Service (NWS) API.
  • ⚠️The `server/tsconfig.json` file contains `"noEmit": true` in its `compilerOptions`. This setting prevents TypeScript from compiling the source code into JavaScript, which would cause the `npm run build` command to fail and consequently `npm run start` would not function as `build/index.js` would not be created. This option must be changed to `"noEmit": false` or removed for the server to build and run correctly.
Verified SafeView Analysis
The server employs good security practices by using `dotenv` for environment variable management and `zod` for robust input validation on all tool arguments (`state`, `latitude`, `longitude`), which helps prevent common injection issues. External API requests are made using values configured via environment variables (`NWS_API_BASE`, `USER_AGENT`), mitigating hardcoded secret risks. Basic error handling is in place for network requests. No 'eval', obfuscation, or other overtly malicious patterns were detected in the provided source code. A potential, albeit low, configuration risk exists if `NWS_API_BASE` or `USER_AGENT` are maliciously set in the environment, but this is an environmental concern rather than a code vulnerability.
Updated: 2026-01-19GitHub→
0
0
Low Cost
LuizMeier icon

mcp-ddi

by LuizMeier

Sec3

This project provides an MCP (Multi-Cloud Platform) server that integrates with Infoblox DDI to manage DNS zones, records, and grid members, offering a unified interface for network automation and operations.

Setup Requirements

  • ⚠️Requires `WAPI_URL`, `WAPI_USER`, and `WAPI_PASS` environment variables, typically provided via a `.env` file.
  • ⚠️The Infoblox WAPI client explicitly disables SSL verification (`verify=False`), which is a critical security risk and should be addressed for production deployments.
  • ⚠️Requires `uv` (a Python package manager and runner) or a similar `uvicorn`/`fastapi` setup to run the server.
Review RequiredView Analysis
The `infoblox_client.py` explicitly disables SSL certificate verification for all Infoblox WAPI calls by using `httpx.AsyncClient(verify=False)`. This creates a critical security vulnerability, making the system susceptible to Man-in-the-Middle attacks. While environment variables are used for credentials, this SSL bypass severely undermines transport security. No 'eval' or obvious obfuscation detected.
Updated: 2025-11-25GitHub→
0
0
Medium Cost
Atomic-Germ icon

mcp-optimist

by Atomic-Germ

Sec7

Provides comprehensive static code analysis and optimization suggestions for JavaScript/TypeScript codebases.

Setup Requirements

  • ⚠️Requires Node.js 18+ and npm/pnpm.
  • ⚠️Requires a local Ollama server running if utilizing the 'consult_ollama' tool (e.g., via the provided 'ask_kimi' scripts), which acts as an intermediary for external AI models.
  • ⚠️Initial setup requires `npm install` and `npm run build` to compile the TypeScript source to JavaScript.
Verified SafeView Analysis
The core server performs static code analysis locally, with a stated design principle of 'Sandboxed Analysis: No code execution during analysis' and 'No Network Access: All analysis performed locally'. However, the utility scripts (`tools/ask_kimi.js`, `tools/ask_kimi_then_qwen.js`) utilize `child_process.execSync` and `spawn` to invoke internal tools and external LLMs (via the `consult_ollama` tool). While these calls are currently controlled to execute trusted local scripts/tools, dynamic code generation and execution (`fs.writeFileSync` then `node <temp_file>`) in `tools/ask_kimi_then_qwen.js` for LLM interaction is a potential vector for code injection if the LLM output is not properly sanitized before embedding it into executable code. No obvious hardcoded secrets or arbitrary network risks were found in the core server logic.
Updated: 2025-12-02GitHub→
0
0
High Cost
vespo92 icon
Sec6

Provides AI assistants with persistent memory and context by storing and retrieving diverse file types (code, documents, photos, CAD) in a local-first ChromaDB vector store, enhanced with batch processing, EXIF extraction, watch folders, and duplicate detection.

Setup Requirements

  • ⚠️Requires Bun runtime for execution
  • ⚠️Requires Docker to run ChromaDB locally
  • ⚠️Requires ChromaDB vector database to be running and accessible
Review RequiredView Analysis
The server performs extensive file system operations (read, write, scan, delete) based on paths provided via AI prompts. Without robust input sanitization or strict access controls, a compromised AI or malicious prompt injection could lead to directory traversal, unauthorized file access, modification, or deletion on the host system. The potential to connect to remote ChromaDB instances introduces a risk if these endpoints are untrusted or insecure. No obvious hardcoded secrets or 'eval' usage found.
Updated: 2025-11-22GitHub→
0
0
Low Cost

xerxes-mcp-server

by metrotech-sk

Sec6

A Python-based server application designed for network communication, configured for Docker deployment and dependency management with uv.

Setup Requirements

  • ⚠️Docker required for standard deployment via compose.yml
  • ⚠️Python environment setup using uv (uv.lock) for local development or direct execution
  • ⚠️Requires specific network port availability on the host system to function correctly
Review RequiredView Analysis
Source code for the 'main.py' and 'src' directory is not provided for a detailed security audit. As a server application, it will inherently expose network ports, which carries an inherent security risk. No signs of obfuscation or direct 'eval' usage are discernible from the file list alone.
Updated: 2025-11-18GitHub→
0
0
Low Cost
veelenga icon

jot-mcp

by veelenga

Sec9

A lightweight MCP server for maintaining coding context across sessions by logging and retrieving 'jots' about development activities.

Setup Requirements

  • ⚠️Requires Node.js >=18.0.0
  • ⚠️Requires git for optimal context auto-detection
  • ⚠️Relies on a local SQLite database for storage
Verified SafeView Analysis
The server communicates over standard I/O (stdio) as an MCP plugin, limiting direct network exposure. It uses `execSync` for git operations, but the commands are fixed and not directly composed from untrusted user input, mitigating command injection risks. SQLite operations utilize prepared statements, preventing SQL injection. No hardcoded secrets or obvious malicious patterns were found. As a local tool, its attack surface is inherently lower.
Updated: 2026-01-15GitHub→
0
0
Low Cost
koudaiii icon
Sec7

This project enables the deployment and management of a Model Context Protocol (MCP) server for the PHONE APPLI API via Azure API Management, allowing AI agents to interact with its functionalities.

Setup Requirements

  • ⚠️Requires Python 3.11 or higher.
  • ⚠️Requires `uv` (Python package manager), `Azure CLI`, and `yq` to be installed globally.
  • ⚠️Deployment to older Azure API Management tiers (Basic/Standard/Premium) requires participation in the 'AI Gateway Early' update group.
  • ⚠️Requires an active Azure subscription with appropriate permissions.
Verified SafeView Analysis
The project utilizes secure practices like `yaml.safe_load` and Azure's `DefaultAzureCredential` for authentication. Infrastructure is defined with Bicep and Azure Verified Modules (AVM), indicating a focus on well-architected cloud deployments. The documentation provides clear guidance on general security best practices for the deployed API Management instance, including prompt injection, authentication, input validation, rate limiting, and the principle of least privilege. However, a discrepancy exists in the `src/import_api.py` script: its `generate_api_policy` function's comment states it generates XML for 'validates X-Pa-Api-Key header', but the actual XML returned is a generic base policy (`<base />`) with no specific validation or forwarding of the `X-Pa-Api-Key` header to the backend. While Azure API Management typically enforces `Ocp-Apim-Subscription-Key` validation at a higher level, proper forwarding and validation of the backend-specific `X-Pa-Api-Key` header might require manual policy configuration after deployment if this script's generated policy is relied upon. This is a functional flaw in the script for API-level policy generation, which could lead to an insecure configuration for the backend API if not manually corrected.
Updated: 2025-11-28GitHub→
0
0
Low Cost
Nehareddy17 icon
Sec9

Provides AI tools for HR leave management, email notifications, and a personal to-do list, designed to integrate as agents within the Claude Desktop environment.

Setup Requirements

  • ⚠️Requires the Claude Desktop application to function as intended.
  • ⚠️Email functionality (in `email_agent.py`) requires `SENDER_EMAIL` and `SENDER_PASSWORD` environment variables to be configured.
  • ⚠️Multiple MCP servers (Leave Management, Email Notification, To-Do List) are provided as separate Python files; each needs to be individually installed into Claude Desktop via `uv run mcp install <filename.py>`.
Verified SafeView Analysis
The server uses in-memory data for leave and to-do lists, avoiding external database vulnerabilities. The email agent securely loads credentials from environment variables using `dotenv` and utilizes TLS for `smtplib` connections, preventing hardcoded secrets and securing network communication. There are no instances of `eval`, code obfuscation, or other immediately apparent malicious patterns. The primary security consideration is the secure management of the `SENDER_EMAIL` account credentials outside of the codebase.
Updated: 2025-11-28GitHub→
PreviousPage 548 of 760Next