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(8554)

35
5
Medium Cost
pyvista icon
Sec2

The server provides a Model Context Protocol (MCP) interface to PyVista for 3D visualization and mesh processing, offering tools to create, manipulate, and export 3D models.

Setup Requirements

  • ⚠️Requires Python 3.12 or newer.
  • ⚠️Dependencies include 'pyvista[all]' which may have complex installation requirements for its visualization backends.
  • ⚠️Vulnerable to directory traversal attacks through file path arguments.
Review RequiredView Analysis
The server's tools accept file paths (filename, output_filename, other_filename) directly from user input via the MCP without any path sanitization or validation. This makes the server vulnerable to directory traversal attacks, potentially allowing an attacker to read, write, or overwrite arbitrary files outside the intended working directory on the server's filesystem.
Updated: 2026-01-12GitHub→
35
1
Medium Cost
yasg1988 icon

mcp-rosreestr

by yasg1988

Sec9

MCP Server for retrieving cadastral data (coordinates, addresses, property information) from Rosreestr based on cadastral numbers.

Setup Requirements

  • ⚠️Requires `ROSREESTR_API_TOKEN` environment variable to be set for API access.
  • ⚠️If operating outside Russia, `ROSREESTR_API_URL` must point to an API proxy with a Russian IP, or the `rosreestr2coord` library (used for direct access) will not function correctly.
  • ⚠️The `.mcp.json` configuration requires the full, absolute path to `server.py`.
Verified SafeView Analysis
The server correctly loads API tokens from environment variables, preventing hardcoding. It relies on external APIs (ipapi.co for IP checks, and a Rosreestr API proxy or direct rosreestr2coord library for data retrieval), which inherently involves third-party dependencies and network requests. No 'eval' or similar dangerous patterns are observed.
Updated: 2025-11-25GitHub→
35
4
Low Cost
lgndluke icon
Sec8

A FastMCP server that integrates with the REI3 Tickets application, enabling MCP clients to manage tickets, worklogs, and retrieve ticket information.

Setup Requirements

  • ⚠️Python 3.13.5 is a specific version requirement for manual installation.
  • ⚠️Requires a designated user in REI3 with 'Tickets API role' and an 'API Profile' set up in the REI3 instance.
  • ⚠️The FastMCP disk storage backend is currently blocking new release builds, making manual or Docker installation the primary methods.
  • ⚠️Extensive configuration required in `config.ini` for REI3 API access and potentially OIDC Proxy settings, all of which are critical for functionality and security.
Verified SafeView Analysis
The server relies heavily on a `config.ini` file for sensitive credentials, including REI3 API username/password, and potentially OIDC client secrets and encryption keys. The security of the server is directly tied to the proper securing of this configuration file. No hardcoded secrets were found in the source code. It uses `httpx` for secure asynchronous HTTP requests and can be configured with SSL. OIDC proxy functionality includes encryption for client storage.
Updated: 2025-12-11GitHub→
35
5
Low Cost
joelverhagen icon

mcp-insights

by joelverhagen

Sec9

Automatically collects, analyzes, and reports on the public Model Context Protocol server registry, generating trend data and statistics.

Setup Requirements

  • ⚠️Requires Node.js for SVG chart rendering.
  • ⚠️Requires PowerShell for script execution.
Verified SafeView Analysis
The project functions as a client-side data collection and reporting tool, making outgoing network requests to a public registry endpoint. It processes data locally using PowerShell and Node.js. No 'eval' or similar dynamic code execution is evident in the provided snippets, nor are there signs of hardcoded secrets. It does not expose any services or process untrusted user input directly, making it relatively safe for its stated purpose as a data analysis and reporting client.
Updated: 2026-01-19GitHub→
35
1
Medium Cost
feedback-loop-ai icon

mcp-ory-kratos

by feedback-loop-ai

Sec9

MCP server for AI agents to manage Ory Kratos identities, sessions, and authentication flows, supporting developers in Claude Code, GitHub Copilot, or Gemini CLI workflows.

Setup Requirements

  • ⚠️Requires a running Ory Kratos instance with Admin API access.
  • ⚠️Requires Node.js 18+ or Bun 1.x installed.
  • ⚠️Authentication to Kratos Admin API (API key or custom headers) might be required, otherwise KRATOS_AUTH_TYPE=none must be configured.
  • ⚠️An MCP-compatible client (Claude Code, GitHub Copilot, or Gemini CLI) is needed to interact with the server.
Verified SafeView Analysis
The server acts as a proxy to the Ory Kratos Admin API. It loads sensitive credentials (API keys, custom headers) from environment variables, which is a standard and secure practice. Logging explicitly avoids sensitive data like credentials or PII traits. The security posture is highly dependent on the secure configuration and operational environment of the underlying Kratos instance and the network where this server runs.
Updated: 2026-01-19GitHub→
35
3
Medium Cost
JustinBeckwith icon

pylon-mcp

by JustinBeckwith

Sec9

An MCP server enabling AI agents to interact with and manage the Pylon customer support platform, handling accounts, contacts, issues, tags, and teams.

Setup Requirements

  • ⚠️Requires Node.js 24+.
  • ⚠️Requires a Pylon API token with Admin access.
  • ⚠️Requires pnpm as the package manager for installation.
Verified SafeView Analysis
The server securely loads the Pylon API token from environment variables (PYLON_API_TOKEN), avoiding hardcoded secrets. The codebase is clear, well-structured, and not obfuscated, making it easy to audit. It utilizes the StdioServerTransport, meaning it communicates via standard input/output, which limits direct external network attack surface from the MCP server itself. Input validation for API parameters using `zod` and internal filtering (`cleanFilter`, `validateTimeRange`) are implemented to prevent malformed requests and potential injection. Outbound network requests are exclusively directed to the official Pylon API.
Updated: 2026-01-19GitHub→
35
6
Medium Cost
dokku-MCP icon

dokku-mcp

by dokku-MCP

Sec9

Exposes Dokku's management capabilities through the Model Context Protocol (MCP), enabling Large Language Models (LLMs) to interact with and manage a Dokku instance.

Setup Requirements

  • ⚠️Early Development: Breaking changes are expected, and it is not recommended for production use.
  • ⚠️Requires Go 1.25+ for building from source.
  • ⚠️Requires Docker and Docker Compose for local development environment.
  • ⚠️Requires configured SSH access to a Dokku instance, including SSH key management.
  • ⚠️Verbose log output from Dokku commands can lead to higher LLM token consumption.
Verified SafeView Analysis
The project demonstrates a strong commitment to security. It includes robust input validation, a command blacklist (with plans for an allow-list), and sensitive log redaction to prevent command injection and information leakage. Secure SSH handling, including path traversal prevention and key file access checks, is implemented. Comprehensive CI testing with security tools (gosec, nancy, staticcheck) and a strict code quality policy (blocking `interface{}`, `any`, `reflect`, `unsafe`) further enhance its security posture. While the default CORS policy for SSE is `*`, it is well-documented and configurable for stricter environments, and token-based authentication is still required.
Updated: 2026-01-13GitHub→
35
8
High Cost
CorgiBoyG icon

mcp-server-juejin

by CorgiBoyG

Sec3

AI-powered service for publishing articles to JueJin community.

Setup Requirements

  • ⚠️Requires a JueJin account and an active login Cookie, which must be manually extracted from the browser.
  • ⚠️The JueJin Cookie is session-based and will expire, requiring periodic updates.
  • ⚠️The project utilizes Spring AI 1.0.0-M6, which is a milestone (non-General Availability) release, potentially introducing stability issues or future breaking changes.
  • ⚠️Requires JDK 17+ and Maven 3.6+.
Review RequiredView Analysis
The provided `application.yml` example and instructions explicitly encourage hardcoding a sensitive JueJin login cookie directly into the configuration file. This practice poses a critical risk of credential leakage if the configuration is committed to version control or shared insecurely. While the application itself doesn't contain malicious code like 'eval', this credential management vulnerability is severe.
Updated: 2025-11-22GitHub→
35
5
Medium Cost
peterbud icon

nitro-mcp-server

by peterbud

Sec4

This project serves as a Model Context Protocol (MCP) server demonstrating streamable HTTP transport with pluggable authentication providers (Auth0, Microsoft Entra ID) and schema-validated tools/resources.

Setup Requirements

  • ⚠️Requires Node.js v20+ and pnpm.
  • ⚠️Authentication requires configuring environment variables for Auth0 or Microsoft Entra ID (e.g., `NITRO_MCP_SERVER_AUTH_PROVIDERS_AUTH0_CLIENT_ID`).
  • ⚠️For production, the default file system storage for OAuth data (`registrationStore`, `authCodeStore`) must be replaced with a secure, production-grade database or distributed cache to ensure security and scalability.
Review RequiredView Analysis
CRITICAL: The server relies on local file system storage (fs driver) for `registrationStore` and `authCodeStore` to manage OAuth client registrations, authorization codes, and states. This is fundamentally insecure for production environments as it's vulnerable to local file system attacks and does not support distributed deployments or high availability. The 'Todo' section explicitly mentions a missing cleanup task for expired authorization codes, which is a significant vulnerability for resource exhaustion and potential misuse of stale codes. The `/auth/register` endpoint acts as a DCR proxy without inherent rate limiting, which is noted in the README as a point requiring external protection to prevent abuse.
Updated: 2025-11-28GitHub→
35
2
Medium Cost
fmktech icon

mcp-kg-skills

by fmktech

Sec7

Manages a knowledge graph of reusable Python functions (skills), documentation, and environment variables for dynamic script composition and execution by an LLM.

Setup Requirements

  • ⚠️Python 3.12 or higher required.
  • ⚠️uv (fast Python package installer) required.
  • ⚠️Neo4j database required (Docker recommended).
Verified SafeView Analysis
The 'execute' tool allows arbitrary Python code execution provided by the LLM. While output is sanitized (secrets replaced with '<REDACTED>') and secret environment variables are stored with restricted file permissions (0600), a sophisticated or exploited LLM could still potentially craft code to exfiltrate secrets if it manages to infer variable names. The 'QueryTool' is strictly read-only, preventing graph modification operations.
Updated: 2025-11-26GitHub→
35
119
Low Cost
sirkirby icon
Sec6

Programmatic management and automation of UniFi Network Controllers, enabling external systems (like LLMs or custom scripts) to interact with UniFi devices, clients, and network configurations.

Setup Requirements

  • ⚠️Requires access to a UniFi Network Controller (v7.x+ recommended).
  • ⚠️Requires setting critical environment variables (UNIFI_HOST, UNIFI_USERNAME, UNIFI_PASSWORD).
  • ⚠️Default `UNIFI_VERIFY_SSL=false` introduces security risks if not explicitly set to `true` and proper SSL certificates are not validated.
Review RequiredView Analysis
The default `verify_ssl=False` in `UniFiSettings` and its explicit mention as `UNIFI_VERIFY_SSL="false"` in examples is a significant security risk, making connections vulnerable to Man-in-the-Middle (MITM) attacks if not explicitly configured to `True` with proper certificate validation in production environments. Additionally, `aiohttp.CookieJar(unsafe=True)` is used in the `ConnectionManager`, which relaxes cookie security policies and could potentially expose the session to risks under certain conditions (e.g., XSS vulnerabilities in the UniFi web interface). While the project implements granular permissions (`permission_category`, `permission_action`), requires explicit confirmation (`confirm=True`) for destructive actions, and uses robust input validation with JSON schemas, these two critical network security concerns lower the overall score. It is crucial to ensure this server runs in a trusted, isolated environment and that `UNIFI_VERIFY_SSL` is correctly configured for production.
Updated: 2025-12-19GitHub→
35
7
Medium Cost
RocketPy-Team icon

Infinity-API

by RocketPy-Team

Sec8

Performs rocket simulations, stores input data, and provides an API for managing rocket components and flights.

Setup Requirements

  • ⚠️Requires Python 3.12 or above
  • ⚠️Requires MongoDB-Atlas instance
  • ⚠️Requires MONGODB_CONNECTION_STRING environment variable
Verified SafeView Analysis
The application uses Pydantic for input validation, environment variables for secrets (MONGODB_CONNECTION_STRING, UPTRACE_DSN), and structured logging for auditability. It uses 'dill' for serializing RocketPy objects for download, which carries an inherent risk if arbitrary deserialization from untrusted sources were allowed (which it is not directly exposed in this API). The `fastmcp` integration uses an experimental OpenAPI parser, which might introduce unforeseen vulnerabilities. Overall, good practices are followed for a server handling complex object serialization.
Updated: 2026-01-11GitHub→
PreviousPage 135 of 713Next