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
u9401066 icon

medical-calc-mcp

by u9401066

Sec6

Provides a Model Context Protocol (MCP) server that offers a comprehensive suite of 90+ validated medical calculators for AI agents, facilitating diagnostic, prognostic, and treatment decisions by exposing them as discoverable and executable tools.

Setup Requirements

  • ⚠️Default security features (rate limiting, API key authentication) are DISABLED by default. Explicitly enable them via environment variables (`SECURITY_AUTH_ENABLED`, `SECURITY_API_KEYS`, `SECURITY_RATE_LIMIT_ENABLED`) for secure remote deployment.
  • ⚠️Requires Python 3.11+.
  • ⚠️For HTTP/SSE transport modes, `uvicorn` is required, which is usually installed with the project's dependencies.
Review RequiredView Analysis
The project includes a robust `SecurityMiddleware` for rate limiting and API key authentication. However, these critical security features are **disabled by default**. Running the server in network-exposed modes (`--mode sse` or `--mode http`, which defaults to binding on `0.0.0.0`) without explicitly enabling authentication and rate limiting (`SECURITY_AUTH_ENABLED=true`, `SECURITY_API_KEYS=your-key`, `SECURITY_RATE_LIMIT_ENABLED=true`) poses a significant risk of unauthorized access and abuse. On the positive side, logging is designed to be PHI-free, and API key comparisons use constant-time operations.
Updated: 2026-01-08GitHub→
0
0
Medium Cost
stayce icon
Sec9

Provides an MCP interface for AI agents to access, search, and browse the WHO International Classification of Functioning, Disability and Health (ICF) data.

Setup Requirements

  • ⚠️Requires WHO ICD-API credentials (free registration at https://icd.who.int/icdapi)
  • ⚠️Requires Python 3.11+
  • ⚠️Local installation (`pip install -e .`) is needed after cloning the repository.
Verified SafeView Analysis
The server securely handles API credentials via environment variables, preventing hardcoding. It uses `httpx` for asynchronous HTTP requests to the legitimate WHO API. No `eval`, `exec`, or direct shell command usage was found. The FastMCP server uses STDIO transport, which is generally safe for local agent communication and does not inherently expose public network ports.
Updated: 2026-01-16GitHub→
0
0
Low Cost
JohnnyB90 icon
Sec5

Provides a desktop application for managing connections to MCP servers.

Review RequiredView Analysis
Source code was not provided for analysis beyond the README. As a desktop application managing server connections, it inherently has the potential to handle sensitive credentials or connection details. Without access to the actual code, it is impossible to audit for specific risks like 'eval' usage, obfuscation, hardcoded secrets, or malicious network patterns. The score reflects a neutral stance due to the lack of code visibility.
Updated: 2025-12-09GitHub→
0
0
Low Cost
ossdhaval icon
Sec8

Serves as a Model Context Protocol (MCP) adapter for an Employee Management backend API, exposing employee operations and data as MCP tools and resources.

Setup Requirements

  • ⚠️Requires a Java Runtime Environment (JRE) to execute.
  • ⚠️Requires the project to be built into a JAR file (e.g., `target/mcp-backend-server-1.0.0.jar`).
  • ⚠️Requires an external Employee Management backend API to be running and accessible via the `BACKEND_API_URL`.
Verified SafeView Analysis
The server uses environment variables for backend API URL, authentication tokens, and API keys, which is good practice to avoid hardcoded secrets. There are no obvious 'eval' or direct system command executions. Input validation for resource IDs relies on `Integer.parseInt`, which is generally safe when used for in-memory filtering, but could be problematic if directly used in database queries without further sanitization (not the case here). Error messages from backend API calls may expose some internal details, which is a minor information leakage risk.
Updated: 2025-11-25GitHub→
0
0
Low Cost
jjiayan icon

mcp-server-test

by jjiayan

Sec1

Unable to determine the specific use case due to the complete absence of provided source code. The repository name 'mcp-server-test' suggests it might be a test server related to the Minecraft Protocol (MCP).

Setup Requirements

  • ⚠️Source code is completely missing for analysis, preventing proper understanding and setup guidance.
Review RequiredView Analysis
A critical security audit cannot be performed due to the complete absence of source code. Without the ability to analyze the code for 'eval', obfuscation, network risks, hardcoded secrets, or malicious patterns, the project is considered high-risk, and its safety cannot be verified. A score of 1 reflects this complete lack of visibility.
Updated: 2025-11-27GitHub→
0
0
High Cost
tensorspace-ai icon

refua-mcp

by tensorspace-ai

Sec8

Provides an MCP server for protein folding, affinity prediction, and antibody/peptide design using Refua Boltz2 and BoltzGen.

Setup Requirements

  • ⚠️Requires significant computational resources, especially GPU (CUDA) for optimal performance.
  • ⚠️Requires downloading large model and molecule assets using `refua.download_assets()` prior to first use.
  • ⚠️Requires Python version 3.11, 3.12, or 3.13.
Verified SafeView Analysis
The server uses `Path.expanduser()` for resolving output paths, which could potentially allow writing to arbitrary file system locations if the `output_path` arguments are not sanitized by the calling client. However, this is generally considered acceptable for self-hosted, client-controlled MCP environments. No direct 'eval' or obvious hardcoded secrets were found. Relies on external dependencies ('refua') for core functionality, introducing dependency-related risks.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
Fridemn icon
Sec3

A plugin-based FastAPI server implementing the Model Context Protocol (MCP) for dynamic integration and management of AI tools, featuring hot reloading and API key authentication.

Setup Requirements

  • ⚠️Requires OpenAI API Key (Paid) and OPENAI_MODEL if the internal LLMClient functionality is used.
  • ⚠️Server runs unauthenticated by default if AUTOMATA_ACCESS_TOKEN is not configured, which is a major security risk.
  • ⚠️Requires `uv` (recommended in README) or `pip` for dependency installation for plugins.
  • ⚠️Python 3.10+ is required.
  • ⚠️The `ALLOWED_ORIGINS` and `ALLOWED_METHODS` environment variables must be explicitly set for CORS configuration, otherwise server startup will fail.
Review RequiredView Analysis
The real-time log viewer at `/api/logs` and `/api/logs/ws` is publicly accessible without authentication, posing a critical information disclosure risk as server logs can contain sensitive operational details. The API is unauthenticated by default if the `AUTOMATA_ACCESS_TOKEN` environment variable is not set, allowing unauthorized access to server tools. The server dynamically installs Python dependencies specified in tool `config.yaml` files; while package names are validated, this process involves executing external commands and could be a vector for supply chain attacks if tool configurations are compromised. The CORS configuration can be set to allow all origins (`*`), which is explicitly warned against as a security risk, although this is configurable by the user.
Updated: 2025-12-16GitHub→
0
0
Low Cost
jonmmease icon

jons-mcp-reminders

by jonmmease

Sec9

Manages macOS Reminders by allowing AI assistants to create, read, update, and delete reminders and lists via EventKit.

Setup Requirements

  • ⚠️Requires macOS 14.0+ (Sonoma or later).
  • ⚠️Requires Python 3.10+.
  • ⚠️Requires explicit Reminders access permission granted by the user in System Settings > Privacy & Security > Reminders.
  • ⚠️Uses 'uv' for dependency management and running, which needs to be installed first.
Verified SafeView Analysis
The server primarily interacts with the macOS EventKit framework, requiring explicit user permission for Reminders access on first run. All operations are local to the machine, with no external network calls or data exfiltration mechanisms identified in the provided source code. No use of 'eval' or other dangerous dynamic code execution patterns. EventKit interactions are serialized for thread-safety. Location data for reminders is handled locally within the OS framework. Considered very safe given its stated purpose and OS-level permission requirements.
Updated: 2025-12-14GitHub→
0
0
Medium Cost

hands-on-mcp-server

by damir-manapov

Sec8

A creative Model Context Protocol (MCP) server for task management, providing tools, resources, and prompts via an in-memory database.

Setup Requirements

  • ⚠️Requires pnpm package manager.
  • ⚠️When using the MCP Inspector, the server must be run from its built output (`node dist/index.js`) rather than `pnpm dev` to avoid interfering with JSON-RPC communication.
Verified SafeView Analysis
The server uses an in-memory database, reducing risks associated with persistent storage vulnerabilities. It runs locally as a Node.js process. Potential security concerns are limited to input validation for internal data manipulation, common in any application. No obvious use of 'eval' or obfuscation is indicated. It is generally safe for its intended local development and testing purposes.
Updated: 2025-11-16GitHub→
0
0
Low Cost
muness icon
Sec8

Manages Xero accounting tasks including creating invoices, bills, expenses, and expense claims, with file attachments and PKCE authentication.

Setup Requirements

  • ⚠️Requires Xero App Setup: Must create a 'Mobile or desktop app' in the Xero Developer Portal with a specific redirect URI (`http://localhost:3000/callback`).
  • ⚠️Requires `XERO_CLIENT_ID` environment variable to be set.
  • ⚠️Initial use requires interactive browser authentication to Xero.
  • ⚠️Requires Node.js version 18 or higher.
Verified SafeView Analysis
The server correctly uses PKCE for OAuth, avoiding client secret exposure for desktop apps. Tokens are stored locally in the user's home directory (`~/.xero-mcp/token.json`), which relies on host file system security. File attachment functions (e.g., `readFileSync(filePath)`) take a user-provided `filePath`. While common for local tools, in a less trusted environment, this could pose a risk if malicious file paths (e.g., directory traversal) are injected without proper sanitization. No 'eval' or obvious malicious code patterns were found. Dependencies are reputable.
Updated: 2026-01-05GitHub→
0
0
Medium Cost
refself icon
Sec8

A Model Context Protocol (MCP) server providing access to Yahoo Finance data via 9 distinct tools, designed for deployment on Cloudflare Workers.

Setup Requirements

  • ⚠️Requires a Cloudflare Workers account for deployment to production.
  • ⚠️Relies on Yahoo Finance's unofficial (cookie+crumb) API which can be unstable or change without notice.
  • ⚠️Usage requires an MCP-compatible client like Claude Desktop or MCP Inspector.
Verified SafeView Analysis
The server primarily acts as an API proxy for Yahoo Finance, implementing a cookie and crumb authentication mechanism to access potentially unofficial APIs. Input is validated using Zod schemas for tool arguments, mitigating common injection risks. No 'eval' or other direct arbitrary code execution vectors are apparent in the provided source. The reliance on undocumented Yahoo Finance APIs, while common for this type of service, inherently carries risks of API changes or unexpected behavior, but this is a fragility risk rather than a direct code security vulnerability.
Updated: 2025-12-03GitHub→
0
0
Low Cost
jacewalker icon
Sec8

Remote Model Context Protocol (MCP) server for deploying calculator tools on Cloudflare Workers without authentication, intended for demonstration and easy integration with MCP clients like Cloudflare AI Playground.

Setup Requirements

  • ⚠️Requires a Cloudflare account for deployment.
  • ⚠️Requires Node.js and npm for local development and deployment.
  • ⚠️The server is 'authless' by design, making its tools publicly accessible. This should be considered for any non-demo deployments.
Verified SafeView Analysis
The server is explicitly designed to be "authless" as per its name and README, making its MCP endpoints publicly accessible without authentication. This is suitable for a demo/example, but would require adding authentication for production use cases involving sensitive operations. The code itself for the calculator tools performs simple arithmetic and uses Zod for input schema validation, minimizing injection or logic manipulation risks within the tool functions.
Updated: 2025-11-28GitHub→
PreviousPage 306 of 760Next