Stop Searching. Start Trusting.

The curated directory of MCP servers, vetted for security, efficiency, and quality.

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

Real-time terminal dashboard for monitoring FTE Shop AI Employee operations via Obsidian vault file watching.

Setup Requirements

  • ⚠️Requires Python 3.10 or higher.
  • ⚠️Requires an Obsidian-like vault directory (AI Employee Vault) to be configured via the VAULT_PATH environment variable.
  • ⚠️Relies on an external 'Claude Code' (claude binary) being installed and accessible in the system's PATH, as the orchestrator executes it via subprocess. This is a critical external dependency.
  • ⚠️The Gmail Watcher requires Google Cloud Project setup for Gmail API access and a `credentials.json` file for authentication (OAuth2 flow to generate `token.json`).
  • ⚠️Requires a terminal with UTF-8 and ANSI color support for optimal display.
Verified SafeView Analysis
The project emphasizes local-first operation and includes robust path validation (`_is_path_in_vault`) to prevent directory traversal attacks, ensuring all file operations remain within the configured vault directory. Content displayed in the terminal is sanitized by Textual's built-in ANSI escaping. The `orchestrator.py` component invokes an external `claude` binary with `--dangerously-skip-permissions`, which shifts trust to the security and hardening of the `claude` binary itself; potential vulnerabilities in this external dependency could pose a risk, but the orchestrator's prompt construction for `claude` appears to avoid direct command injection from arbitrary user input. No obvious hardcoded sensitive secrets or unhandled network risks (beyond legitimate Gmail API interaction) were identified within the provided source.
Updated: 2026-01-19GitHub
0
0
Low Cost
GitHub-Insight-ANZ-Lab icon

copilot-lab-mcp-server

by GitHub-Insight-ANZ-Lab

Sec9

This MCP server demonstrates the creation of custom tools and resources to integrate AI clients (like Copilot) with external APIs, specifically providing a friendly greeting and fetching data from NASA's Astronomy Picture of the Day (APOD) API.

Setup Requirements

  • ⚠️Requires a Copilot License to be enabled in your IDE.
  • ⚠️Requires Node.js to be installed on your system.
  • ⚠️A NASA API Key is highly recommended for higher rate limits (a free key is available from api.nasa.gov).
  • ⚠️The project must be built (`npm run build`) before the server can be run.
Verified SafeView Analysis
The server securely retrieves the NASA API key from environment variables, with a fallback to a demo key. The documentation explicitly warns against committing API keys and recommends using environment variables, adding `.env` to `.gitignore`, and regular key rotation. Network requests are made to a known public API (api.nasa.gov). No 'eval' or other directly malicious patterns were found. The server implementation includes basic error handling for API calls. A minor risk is the 'DEMO_KEY' fallback, but it's clearly for a tutorial context and limited.
Updated: 2025-12-01GitHub
0
0
High Cost
mschristiansen icon

bc-extra-api

by mschristiansen

Sec7

Provides a Business Central API extension for warehouse and inventory queries, designed to integrate with MCP servers and AI assistants for managing wood materials inventory, reservations, and calculations.

Setup Requirements

  • ⚠️Requires a Microsoft Dynamics 365 Business Central environment (SaaS or local Docker-based sandbox).
  • ⚠️Requires the 'DHS - Basis' Business Central extension (v1.0.0.17) by 'Aktieselskabet balance.as' as a dependency.
  • ⚠️Assumes an MCP (Microsoft Cloud Platform) server is configured to integrate with Business Central APIs to expose the endpoints.
Verified SafeView Analysis
The `app.json` manifest for the Business Central extension has `allowDebugging: true`, `allowDownloadingSource: true`, and `includeSourceInSymbolFile: true`. While standard for development, these settings can expose source code and debugging capabilities in production environments if not secured through tenant-level access controls.
Updated: 2026-01-05GitHub
0
0
Low Cost
DharaniKumarLearning icon

test-remote-mcp-server

by DharaniKumarLearning

Sec9

Provides a simple calculator server with basic arithmetic (addition) and random number generation capabilities via MCP tools.

Setup Requirements

  • ⚠️Requires Python 3.11 or higher.
  • ⚠️Requires the 'fastmcp' Python package to be installed.
Verified SafeView Analysis
The server's code is simple and does not use dangerous functions like 'eval'. It binds to '0.0.0.0' which makes it accessible from any network interface, standard for server deployments, but implies external access if deployed without network restrictions. No hardcoded secrets or malicious patterns were found.
Updated: 2026-01-17GitHub
0
0
Low Cost
JPishikawa icon

mcp-servers

by JPishikawa

Sec6

These servers provide a 'Model Context Protocol' (MCP) interface for various external services, including Slack, Kubernetes, GitHub, and Weather APIs, primarily to serve as context providers for AI Agents.

Setup Requirements

  • ⚠️Requires a Kubernetes cluster for deployment.
  • ⚠️External API keys are needed for Slack (SLACK_MCP_XOXP_TOKEN) and Weather (WEATHER_API_KEY for OpenWeatherMap or similar).
  • ⚠️Specific Kubernetes RBAC permissions (ClusterRole and ClusterRoleBinding) are required for the Kubernetes MCP server to operate.
Review RequiredView Analysis
The 'weather-mcp.yaml' contains a hardcoded 'WEATHER_API_KEY' set to 'demo-key'. While labeled as a demo key, hardcoding API keys is a significant security risk and a poor practice, potentially leading to exposure of real keys in production. The 'kubernetes-mcp.yaml' grants broad read-only access (get, list, watch) to numerous Kubernetes resources (pods, events, services, secrets, deployments, etc.) via a ClusterRole. While intended for observability, this constitutes a wide attack surface if the server itself is compromised.
Updated: 2025-11-27GitHub
0
0
Medium Cost
klkhlt icon

tekmetric-mcp

by klkhlt

Sec9

The Tekmetric MCP Server allows users to query their Tekmetric shop management data (customers, vehicles, repair orders, appointments, etc.) using natural language through an AI assistant.

Setup Requirements

  • ⚠️Requires Tekmetric API credentials (Client ID and Client Secret) which must be requested from Tekmetric and can take 2-3 weeks for approval.
  • ⚠️For building from source, Go 1.23+ is required.
  • ⚠️API results are typically limited to 25-100 records per query, requiring careful filtering for broad requests.
Verified SafeView Analysis
The server is explicitly designed for read-only access to Tekmetric data, minimizing accidental modification risks. It relies on OAuth 2.0 for authentication with client ID and secret, which are expected to be provided securely via environment variables or configuration files (no hardcoded production secrets found). API interactions enforce HTTPS for production environments. Input parameters are validated, and rate limiting with exponential backoff is implemented for robust API communication. No 'eval' or similar dangerous dynamic code execution patterns were identified.
Updated: 2026-01-19GitHub
0
0
Low Cost
Nagavamsi178 icon

mcp-server

by Nagavamsi178

Sec9

A simple calculator API server providing basic arithmetic operations, complemented by a Streamlit web user interface.

Setup Requirements

  • ⚠️Requires Python 3.x
  • ⚠️Dependencies include fastapi, uvicorn, pydantic, streamlit, and requests
  • ⚠️Two separate processes need to be run concurrently (FastAPI server and Streamlit UI)
Verified SafeView Analysis
The application runs locally on `127.0.0.1:8000` by default, which is generally safe. Input validation for division by zero is implemented. No 'eval' or other highly dangerous patterns are present. If deployed publicly, standard API security practices (e.g., authentication, rate limiting, more robust input sanitization) would be necessary, but this is beyond the scope of a simple calculator service.
Updated: 2025-11-25GitHub
0
0
Medium Cost
appsmartzaiml icon

my-mcp-server

by appsmartzaiml

Sec8

Provides a Model Context Protocol (MCP) interface for AI models to search and discover live radio stations and podcasts from the Radio FM service.

Setup Requirements

  • ⚠️Requires Node.js runtime and TypeScript compiler (tsc) for building.
  • ⚠️The external Radio FM API base URL (`RADIOFM_API_BASE`) is hardcoded in `src/index.ts`.
Verified SafeView Analysis
The server uses `cors()` with `Access-Control-Allow-Origin: *` which is common for public APIs and MCP servers, but should be noted. The `RADIOFM_API_BASE` is hardcoded within the source file; changes to this external API URL would require code modification and redeployment. No usage of `eval` or other obvious malicious patterns was found. Input validation for the `query` parameter is present, and `axios` handles parameter encoding, mitigating direct injection risks in the external API call. The output formatting is plain text, preventing XSS in the response content.
Updated: 2026-01-19GitHub
0
0
Low Cost
serge2 icon

emcp

by serge2

Sec6

Provides a lightweight framework for building MCP (Model Context Protocol) services over HTTP/JSON-RPC in Erlang.

Setup Requirements

  • ⚠️Requires Erlang/OTP environment to be installed.
  • ⚠️Requires `rebar3` build tool for dependency management and compilation.
  • ⚠️Requires secure management of API keys by the implementing application as demonstrated in the configuration example.
Verified SafeView Analysis
The framework allows application developers to define custom tool/resource handler functions. The provided example for `resources_read` demonstrates the use of `os:cmd/1` to execute shell commands. This capability, while flexible, introduces a risk of command injection if user-supplied input is passed unsanitized to `os:cmd/1` by the application developer. Secure management of API keys by the implementing application is also crucial.
Updated: 2026-01-18GitHub
0
0
Medium Cost
dogkeeper886 icon

ruckus1-mcp

by dogkeeper886

Sec9

Facilitates automated management and querying of RUCKUS One network infrastructure (venues, APs, WiFi networks, security profiles, roles) by AI assistants via the Model Context Protocol.

Setup Requirements

  • ⚠️Requires valid RUCKUS One API credentials (Tenant ID, Client ID, Client Secret) configured as environment variables.
  • ⚠️An MCP client (e.g., Claude Desktop/CLI, Cline) is necessary to interact with the server, as it does not expose HTTP endpoints.
  • ⚠️Many 'create', 'update', and 'delete' operations are asynchronous, requiring polling with configurable retries, which means responses for these operations will include activity IDs and status details, not immediate final results.
Verified SafeView Analysis
The server uses environment variables (`RUCKUS_TENANT_ID`, `RUCKUS_CLIENT_ID`, `RUCKUS_CLIENT_SECRET`) for API credentials, which is a good practice to avoid hardcoding secrets. It communicates via standard I/O (stdio) as an MCP server, eliminating direct network exposure from the server itself. Authentication tokens are cached with an expiration buffer to minimize re-authentication and potential misuse. Error handling provides structured API responses, which helps in debugging without exposing raw internal stack traces. Input validation is performed through JSON schemas for tool arguments, and some utility validation functions exist, though their comprehensive application to all incoming data isn't fully detailed in the truncated code. There are no apparent uses of `eval` or other highly dangerous functions. Overall, the design prioritizes secure credential management and minimal network footprint for the MCP server.
Updated: 2026-01-19GitHub
0
0
Medium Cost

Provides semantic PDF reading capabilities by converting PDF content to structured Markdown and extracting metadata, optimized for LLM consumption.

Setup Requirements

  • ⚠️Requires Docker for the recommended deployment, which involves mounting a volume for PDF access.
  • ⚠️The Docling library may download models on its first run, requiring an internet connection for initial setup.
  • ⚠️Requires Python 3.10 or newer.
Verified SafeView Analysis
The `read_pdf_structure` and `get_pdf_metadata` tools take a `path` argument, allowing the server to access files on the host filesystem (or within its Docker container). While the recommended Docker setup mitigates this risk by explicitly mounting a PDF-containing directory to `/data`, running the server directly via `pip` or `uv` without proper sandboxing could allow a malicious client to trigger arbitrary file reads by the server process. There are no direct `eval` calls, hardcoded secrets, or obvious malicious network patterns. The `HF_HUB_DISABLE_SYMLINKS` environment variable is explicitly set as a security measure.
Updated: 2025-11-26GitHub
0
0
Low Cost
nazihkhelifa icon

mcp-server-templates

by nazihkhelifa

Sec1

Unable to determine the specific use case as the source code for the `mcp-server-templates` repository was not provided for analysis.

Setup Requirements

  • ⚠️Source code not provided, making it impossible to identify specific setup requirements or friction points.
Review RequiredView Analysis
The source code for the `mcp-server-templates` repository was not provided for analysis. Without access to the code, it is impossible to audit for security risks such as `eval` usage, obfuscation, network vulnerabilities, hardcoded secrets, or malicious patterns. Therefore, a score of 1 is assigned, and it is considered critically unsafe to run without a thorough code review. Any server where the source code cannot be inspected for security is inherently risky.
Updated: 2025-11-24GitHub
PreviousPage 390 of 713Next