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)

0
0
Medium Cost
gisetia icon

mcp-agent-base

by gisetia

Sec9

A minimal FastAPI service exposing an OpenAI-compatible /chat/completions endpoint backed by Anthropic Claude with MCP tool calls and SSE streaming.

Setup Requirements

  • ⚠️Requires an Anthropic API Key (paid service) unless running in simulation mode (`SIMULATE=true`).
  • ⚠️Requires an MCP server to be reachable at `MCP_SERVER_URL` for tool discovery and invocation, unless simulation or empty MCP mock is enabled.
  • ⚠️Requires Python 3.10+.
Verified SafeView Analysis
Secrets (API keys, URLs) are handled via environment variables, avoiding hardcoding. The service implements retry mechanisms for network calls to both the LLM provider and the MCP server, improving resilience. No 'eval' or other direct arbitrary code execution patterns were found. Security is partly dependent on the trustworthiness of the external MCP server and the tools it exposes.
Updated: 2026-01-19GitHub→
0
0
Low Cost
djoreilly icon

mcp-auth-go-sdk

by djoreilly

Sec8

Tests OAuth support for the Model Context Protocol (MCP) Go SDK using Keycloak and MCP Inspector, providing an example MCP server with authenticated tools.

Setup Requirements

  • ⚠️Requires a running Keycloak instance, which needs to be configured with a specific realm, client, scopes, and users via a provided Python script and manual UI steps (Web Origins, Valid Redirect URIs).
  • ⚠️Requires `npx @modelcontextprotocol/inspector@0.16.7` as specific older version is needed due to a known bug in newer versions.
  • ⚠️The Keycloak URL and server audience are hardcoded in the Go source, requiring recompilation for changes.
Verified SafeView Analysis
Implements standard OAuth 2.0 Bearer token authentication with JWT validation using Keycloak as the OIDC provider. It fetches and automatically refreshes JWKS for cryptographic key validation, which is good practice. The server binds to localhost, limiting direct external exposure. No obvious malicious patterns, 'eval' usage, or hardcoded sensitive secrets are present for its intended purpose as an example server. Production deployments would typically require additional hardening such as rate limiting (which the code explicitly notes as a potential need).
Updated: 2026-01-08GitHub→
0
0
Low Cost
RobertCrupa icon

Clearcom-MCP-Server

by RobertCrupa

Sec2

Provides an AI agent with an API to manage ClearCom MCP server connections, roles, and channel assignments.

Setup Requirements

  • ⚠️Requires Python 3.12 or higher.
  • ⚠️Requires the 'uv' package manager for installation and execution.
  • ⚠️Hardcoded ClearCom device IP (http://10.50.16.99) and credentials ('admin'/'admin') in `src/main.py`, which must be changed in the source code to work with a different device or secure credentials.
Review RequiredView Analysis
CRITICAL: The `src/main.py` file hardcodes the `DeviceClient` base_url, username, and password (`admin:admin`). This is a severe security vulnerability as it exposes sensitive access credentials directly in the source code and prevents dynamic configuration for different environments. These values should be loaded from environment variables or a secure configuration mechanism.
Updated: 2025-11-21GitHub→
0
0
Medium Cost
manohar9694 icon

monkdb-mcp

by manohar9694

Sec9

Enables LLMs and AI agents to securely interact with MonkDB for data querying, description, and health checks using a standardized Model Context Protocol (MCP).

Setup Requirements

  • ⚠️Requires a running MonkDB instance accessible from the server's host.
  • ⚠️Requires granting only minimum necessary privileges to the database user configured for the MCP server.
  • ⚠️Python 3.13+ for the Python version, or Node.js 20+ and NPM 10.9+ for the TypeScript version.
Verified SafeView Analysis
The server explicitly blocks non-SELECT queries in the `run_select_query` tool, a critical measure against SQL injection for write/delete/update operations. Configuration relies on environment variables (MONKDB_HOST, MONKDB_USER, MONKDB_PASSWORD, MONKDB_API_PORT), preventing hardcoded secrets. Logging is implemented for server operations. A crucial caveat, highlighted in the README, is the user's responsibility to configure the database user with the 'minimum necessary privileges' for the MCP server, avoiding default or administrative users. This external configuration is paramount for the overall security posture.
Updated: 2025-12-15GitHub→
0
0
Low Cost
Vani2130 icon

mcp_ctl

by Vani2130

Sec7

Manages and simplifies the deployment and operation of various Model Context Protocol (MCP) servers across different platforms using a command-line interface.

Setup Requirements

  • ⚠️Requires Node.js (v12 or higher) and npm for installation and operation.
  • ⚠️Requires Docker to be installed on the system for managing the 'github' MCP server package.
  • ⚠️Requires 'uvx' (a Python package installer, often used for Python virtual environments) for managing the 'semgrep' MCP server package.
Verified SafeView Analysis
The tool stores sensitive information like API tokens (e.g., GitHub, Unleash) in a local JSON configuration file (`claude_desktop_config.json`). While this is typical for CLI tools, users should ensure proper local file system security. The Figma API key is passed directly as a command-line argument to the spawned process, which is generally less secure than using environment variables, as command-line arguments can sometimes be visible in process listings. The `spawn` command is used for executing server processes, but the commands and arguments are constructed from predefined package configurations and validated user inputs, mitigating risks of arbitrary command injection.
Updated: 2026-01-19GitHub→
0
0
Low Cost
g1ddy icon
Sec9

Enables AI models and development tools to interact with Raindrop.io bookmarks and collections using natural language via the Model Context Protocol.

Setup Requirements

  • ⚠️Requires .NET 10 SDK (preview) for the recommended DNX setup, or .NET 8 SDK for development/global tool installation.
  • ⚠️A Raindrop.io API token is mandatory and must be securely configured via environment variables (`Raindrop__ApiToken`) or .NET user secrets.
  • ⚠️Client-side configuration (e.g., in VS Code's `settings.json` or `mcp.json`) is required to connect to the MCP server.
Verified SafeView Analysis
The project emphasizes secure handling of the Raindrop.io API token via environment variables or .NET user secrets, explicitly guiding users away from hardcoding. No 'eval' or obfuscation detected. Network communication is with the official Raindrop.io API. The `setup.sh` script includes checksum verification for downloaded packages, indicating a focus on supply chain security. The `AllowedHosts: *` in `appsettings.json` is a minor consideration, but given the server is designed for local stdio communication with an MCP client, it is not a direct web exposure risk.
Updated: 2026-01-19GitHub→
0
0
Low Cost
OpenAF icon

mini-a

by OpenAF

Sec8

A goal-oriented autonomous agent for orchestrating LLMs, shell commands, and MCP servers to achieve user-defined objectives.

Setup Requirements

  • ⚠️Requires OpenAF to be installed and available in PATH.
  • ⚠️`OAF_MODEL` environment variable (or `model=` argument) is mandatory for LLM configuration.
  • ⚠️Specific environment variables are needed for certain LLM providers (e.g., AWS credentials, Gemini JSON prompt flags).
  • ⚠️External tools like Docker or Ollama might be required for specific sandboxing or local model configurations.
Verified SafeView Analysis
Mini-A is designed for powerful autonomous execution, including shell commands and filesystem modifications. It has robust built-in safety features: shell access and write operations are disabled by default (`useshell=false`, `readwrite=false`), dangerous commands are banned by default (e.g., `rm`, `sudo`, `curl`), and interactive confirmation (`checkall=true`) is available. Model API keys are stored encrypted. The system's power necessitates careful configuration, but defaults are secure. Client-side evaluation for charts includes basic pattern filtering.
Updated: 2026-01-17GitHub→
0
0
Medium Cost
agentic-forge icon

mcp-weather

by agentic-forge

Sec9

Provides current weather, forecast, air quality, and geocoding services by integrating with the Open-Meteo API.

Setup Requirements

  • ⚠️Requires Python 3.12+ (Python 3.13+ is explicitly tested/recommended)
  • ⚠️Requires `uv` for dependency management and execution (`uv sync`, `uv run`)
  • ⚠️Relies on external Open-Meteo APIs (requires internet access)
Verified SafeView Analysis
The server does not handle sensitive user data or require API keys. It uses `httpx` for external API calls and has no obvious use of `eval`, `exec`, or direct shell command execution of user input. CORS is set to `*` for HTTP transport, which is acceptable for serving public data but could be tightened if restricted access is ever required. `detect-secrets` is included in development dependencies, indicating awareness of secret management.
Updated: 2026-01-12GitHub→
0
0
Medium Cost
mamarche icon

chuckai

by mamarche

Sec7

A serverless AI-powered chatbot that demonstrates the Model Context Protocol (MCP) using Azure Functions to discover and invoke tools for interacting with a Chuck Norris joke database.

Setup Requirements

  • ⚠️Requires .NET 10 SDK
  • ⚠️Requires Azure Functions Core Tools v4
  • ⚠️Requires Azure SQL Database or SQL Server (with manual script execution)
  • ⚠️Requires an Azure AI Foundry account with an OpenAI deployment (paid service)
Verified SafeView Analysis
The project configures CORS with `*` for local development in `ChuckAI.Database.Api/local.settings.json`, which is a security risk in production environments and should be restricted to specific origins. Placeholder values for API keys and connection strings (`your-azure-openai-api-key`, `your-username`, `your-password`) are correctly used in `local.settings.json` examples, indicating that sensitive information should not be hardcoded or committed to source control. No obvious 'eval' or malicious patterns were found.
Updated: 2025-12-02GitHub→
0
0
Medium Cost
greatgitsby icon

ynab-mcp

by greatgitsby

Sec9

Exposes YNAB (You Need A Budget) financial data to LLMs via the Model Context Protocol (MCP) for querying budget information.

Setup Requirements

  • ⚠️Requires YNAB_API_TOKEN environment variable, obtainable from YNAB developer settings.
  • ⚠️Requires Python 3.12 or higher.
  • ⚠️Requires the 'uv' package manager for dependency management and execution.
Verified SafeView Analysis
The server securely handles the YNAB API token by requiring it via an environment variable (YNAB_API_TOKEN) and using it for Bearer authentication with the YNAB API via the httpx library. There are no hardcoded secrets, 'eval' usage, or obvious malicious patterns. Input parameters for resources/tools are validated or used in API calls, reducing direct injection risks. Output is formatted into human-readable text, which is generally safer for LLM consumption than raw JSON.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
gaikwadsantosh icon

RemoteMCP

by gaikwadsantosh

Sec8

AI-powered financial assistant for tracking expenses and food card actions through natural language interaction.

Setup Requirements

  • ⚠️Requires GOOGLE_API_KEY (Paid service for Google Gemini API).
  • ⚠️Requires 'uv' for dependency management if following README setup instructions.
  • ⚠️Multiple services need to be run concurrently: at least one FastMCP server (ExpenseTracker or FoodCardTracker) and an AI-enabled client/backend (FastAPI or LangChain based).
Verified SafeView Analysis
The server uses parameterized SQL queries to prevent injection vulnerabilities. API keys (GOOGLE_API_KEY) are correctly fetched from environment variables. No 'eval' or obvious malicious patterns were found. The use of '0.0.0.0' for server binding is standard for development/containerized environments but requires proper network isolation (firewalling) in production to prevent unintended exposure.
Updated: 2025-11-27GitHub→
0
0
Low Cost
vipulpathak113 icon
Sec8

A backend server for tracking and managing personal expenses using the Model Context Protocol (MCP) as an API.

Setup Requirements

  • ⚠️Requires Python 3.12 or newer.
Verified SafeView Analysis
The server uses parameterized queries for SQLite operations, effectively preventing SQL injection. File paths are handled safely with `os.path.join`. No explicit hardcoded secrets or dangerous functions like `eval` or `os.system` are present. Security relies on the underlying `fastmcp` framework's robustness and appropriate network configuration when exposed via HTTP. Future enhancements for user authentication and authorization would be critical for production use in a multi-user environment.
Updated: 2026-01-18GitHub→
PreviousPage 495 of 713Next