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
Low Cost
bobtherdsman icon

RDSMCP

by bobtherdsman

Sec8

Assess SQL Server instances for migration compatibility to AWS RDS.

Setup Requirements

  • ⚠️Requires Microsoft ODBC Driver 18 for SQL Server (Windows-specific, external download).
  • ⚠️Requires specific SQL Server permissions (VIEW SERVER STATE, VIEW ANY DEFINITION, access to system databases, sp_MSforeachdb).
  • ⚠️Requires Python 3.8 or higher.
Verified SafeView Analysis
The tool connects to specified SQL Server instances, requiring network access. It uses `Trusted_Connection=yes` or explicit credentials. The connection string uses `Encrypt=yes;TrustServerCertificate=yes`, where `TrustServerCertificate=yes` bypasses certificate validation, potentially allowing MITM attacks if not used in a secure, trusted environment. The core SQL query utilizes `sp_MSforeachdb`, which can be a SQL injection risk if the inner queries were dynamically constructed from untrusted user input; however, in this implementation, the inner queries are fixed and use `?` only for database names derived internally from `sys.databases`, mitigating this specific risk. No hardcoded credentials or `eval` statements were found.
Updated: 2025-12-02GitHub→
0
0
Medium Cost
reouno icon

gemini-mcp

by reouno

Sec9

An MCP (Model Context Protocol) server that provides a standardized interface for accessing Google Gemini AI models for text generation.

Setup Requirements

  • ⚠️Requires a Google Gemini API Key (paid service, obtained from AI Studio).
  • ⚠️Initial deployment to Google Cloud Run requires significant manual GCP project setup (creating project, linking billing, gcloud CLI authentication).
  • ⚠️Automated deployment via GitHub Actions requires setting up multiple GitHub Secrets with values derived from GCP resources.
Verified SafeView Analysis
The server correctly uses environment variables for sensitive API keys and validates input with Zod schemas, mitigating common injection risks. Deployment to Google Cloud Run leverages Workload Identity Federation for secure GitHub Actions integration, limiting permissions to the specific repository. No 'eval' or direct malicious patterns were found. The use of 'any' casts for Google Gen AI SDK responses is a minor type safety concern but not a security vulnerability.
Updated: 2025-11-19GitHub→
0
0
Low Cost
olahiselius icon

PigelloMockAPI

by olahiselius

Sec8

This Model Context Protocol (MCP) server integrates with a Pigello Mock API to manage property information, cases, tenants, and components, primarily for AI assistant interaction via the Model Context Protocol.

Setup Requirements

  • ⚠️Requires the Pigello Mock API (a separate .NET project) to be running on 'http://localhost:5059' (or 'https://localhost:7293' for HTTPS) before starting the MCP server.
  • ⚠️Manual JSON configuration is required in VS Code or Codespaces (under 'mcpServers') to integrate this MCP server with GitHub Copilot.
  • ⚠️This is an internal prototype; production readiness would require further hardening beyond the mock setup.
Verified SafeView Analysis
The server design as a proxy to a mock API is generally safe for development/prototyping. For production, careful configuration of CORS is necessary to restrict origins. The base URL for the mock API is configurable via environment variables, which is good practice. No 'eval', obfuscation, or obvious hardcoded sensitive secrets were found in the provided code snippets.
Updated: 2025-11-19GitHub→
0
0
Low Cost
WonkyBilly icon
Sec9

Provides real-time air temperature data for Singapore as a Model Context Protocol (MCP) tool.

Verified SafeView Analysis
The server makes a `fetch` request to `https://api-open.data.gov.sg/v2/real-time/api/air-temperature`. While direct external API calls are a potential network risk, the URL is hardcoded and appears to be a legitimate government service. No `eval`, hardcoded secrets, or unusual malicious patterns were found. Uses `process.env.PORT` for configuration, which is good practice.
Updated: 2026-01-18GitHub→
0
0
Medium Cost
u9401066 icon
Sec8

Integrates PubMed literature search capabilities into AI agents, particularly for Microsoft Copilot Studio, enabling comprehensive scientific research and information retrieval within Microsoft 365 applications.

Setup Requirements

  • ⚠️Requires an NCBI Email for API access (free but essential for NCBI's E-utilities policy).
  • ⚠️For Microsoft Copilot Studio integration, a publicly accessible HTTPS URL with a valid SSL certificate is required (often achieved via Nginx reverse proxy or temporary tunnels like ngrok).
  • ⚠️Python 3.8 or higher is required to run the server.
Verified SafeView Analysis
The server uses environment variables for sensitive credentials (NCBI API Key) and supports deployment with Nginx for HTTPS termination, rate limiting, and security headers. The internal HTTP API (`/api/*` endpoints) for MCP-to-MCP communication uses `allow_origins=['*']`, which is a common pattern for trusted internal integrations or services behind a proxy. However, this requires careful configuration of the ingress layer (e.g., Nginx) in production environments to prevent unintended external exposure. The server generally binds its internal HTTP API to `127.0.0.1` by default, reducing direct external exposure.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
Zutavern icon
Sec8

Enables AI assistants to interact with the Belbo Booking API for managing appointments, customers, services, and other business operations.

Setup Requirements

  • ⚠️Requires Node.js 18 or higher to run.
  • ⚠️Requires a Belbo account with API access enabled and an API token.
  • ⚠️Configuration needs to be provided via environment variables (BELBO_BUSINESS, BELBO_TOKEN) or dynamically through the 'belbo_configure' tool.
Verified SafeView Analysis
The server correctly uses HTTPS for all API communication and explicitly avoids logging API tokens to console output. API tokens are passed as query parameters, which is a common pattern for the Belbo API but generally less secure than 'Bearer' tokens in headers as they can persist in some server logs or proxy caches. The server itself does not introduce arbitrary code execution risks like 'eval'. Input validation for tool arguments is expected to be handled by the MCP SDK based on the defined 'inputSchema', and the internal Belbo client performs checks for configuration existence.
Updated: 2025-12-14GitHub→
0
0
Medium Cost
f114112140-star icon

MCP-Server

by f114112140-star

Sec3

A server to integrate Google Gemini AI with Unity, allowing scene generation based on two camera inputs and outputting a JSON array of scene objects.

Setup Requirements

  • ⚠️Requires manual installation of dependencies listed in `requirement.txt`.
  • ⚠️The Google Gemini API key is hardcoded in `mcp_server.py` and must be manually replaced within the source code.
  • ⚠️The AI prompt for scene generation is hardcoded and requires modifying `mcp_server.py` to change.
Review RequiredView Analysis
The Google API key is hardcoded directly into `mcp_server.py`, posing a severe security risk as it can be easily exposed. The `CORSMiddleware` is configured to allow all origins (`allow_origins=["*"]`), which is generally unsafe for production environments as it can lead to Cross-Site Request Forgery (CSRF) vulnerabilities.
Updated: 2025-11-25GitHub→
0
0
Low Cost
mlgill icon
Sec9

Provides an MCP server to send Pushover notifications from MCP-compatible tools like Cursor, offering customizable alerts.

Setup Requirements

  • ⚠️Requires a Pushover account with a registered application (App Token) and User Key.
  • ⚠️Requires Python 3.10+ and the `uv` package manager installed for direct Python execution.
  • ⚠️When using Docker Compose, requires a `.env` file with `PUSHOVER_TOKEN` and `PUSHOVER_USER_KEY`.
Verified SafeView Analysis
The server correctly loads API credentials from environment variables or a configuration file, avoiding hardcoded secrets. It uses `httpx` for network requests and `FastMCP` for server functionality, both reputable libraries. Input validation (e.g., message length, priority range) is performed. When run in SSE (web service) mode, standard web service security practices (e.g., firewall, access control) should be considered if exposed publicly, though it defaults to `127.0.0.1`. No `eval` or obfuscation is present.
Updated: 2026-01-16GitHub→
0
0
Low Cost
Jing-yilin icon
Sec8

Provides Model Context Protocol (MCP) access to Twitter data and write actions through the TwitterAPI.io service for LLM clients like Claude.

Setup Requirements

  • ⚠️Requires a `TWITTERAPI_API_KEY` from TwitterAPI.io (a paid service with free trial credits).
  • ⚠️Node.js version 18.0.0 or higher is required.
  • ⚠️Write actions (`login_user`, `create_tweet`) explicitly require a high-quality residential proxy.
Verified SafeView Analysis
The server securely handles API keys via environment variables and stores sensitive login cookies only in-memory. It uses HTTPS for all API requests and supports enterprise proxies. A moderate risk exists with client-provided `save_dir` arguments for file writes, as a malicious client could potentially attempt to write to arbitrary file paths on the local system if not properly restricted by the client-side sandbox; however, the content written is controlled (cleaned JSON data). No 'eval' or obvious obfuscation is present.
Updated: 2026-01-10GitHub→
0
0
Medium Cost
JustAnotherDevv icon

Arbitrum-Stylus-MCP

by JustAnotherDevv

Sec8

A privacy-preserving quadratic voting system leveraging Noir's zero-knowledge proofs (ZKPs) and Arbitrum Stylus smart contracts to verify voter eligibility, prevent double-voting, and calculate quadratic voting power with complete ballot secrecy.

Setup Requirements

  • ⚠️Requires `nsv` (Noir Stylus Verifier CLI) tool to be installed.
  • ⚠️Requires a specific Rust toolchain (e.g., `1.83.0` with `wasm32-unknown-unknown` target) for Stylus contract compilation.
  • ⚠️Requires `pnpm` for managing JavaScript dependencies.
Verified SafeView Analysis
The project adheres to standard practices for ZKP-based decentralized applications using Noir and Arbitrum Stylus. There is no presence of 'eval', obfuscation, or hardcoded sensitive secrets within the provided source code for deployment. Key management for `--private-key` during contract deployment is an operational security concern, not a code vulnerability. The core security relies on the correctness of the Noir circuit logic and the cryptographic primitives provided by the underlying Noir/Stylus frameworks.
Updated: 2025-11-28GitHub→
0
0
Medium Cost
anortham icon

sherpa

by anortham

Sec9

Guides AI agents through systematic software development workflows, promoting best practices and habit formation via positive reinforcement.

Setup Requirements

  • ⚠️Requires Bun runtime (v1.0.0+) to be installed and in PATH.
  • ⚠️Requires a one-time setup step (`bun run setup`) to initialize user configuration and copy default workflows to `~/.sherpa/`.
  • ⚠️When configuring in Claude, the `sherpa-server.ts` path must be an absolute file path.
Verified SafeView Analysis
The server primarily operates locally, interacting via standard I/O (stdio) and persisting state to the user's home directory (`~/.sherpa/`). Input arguments are validated for length and type, and workflow YAML files are parsed, not executed. File operations for state persistence (`user-profile.json`, `progress-tracker.json`, `workflow-state.json`) use atomic writes (temp file + rename) and include robust error handling with retry mechanisms and graceful degradation. There are no obvious hardcoded secrets or direct network listening services exposed. The risk of `eval` or arbitrary code execution from workflow files is mitigated by parsing YAML rather than executing code. Overall, it demonstrates good security practices for a local agent-guidance tool.
Updated: 2025-11-25GitHub→
0
0
Medium Cost
brownrl icon

eco_mcp

by brownrl

Sec8

Provides AI agents with access to the European Commission's Component Library (ECL) documentation, offering search, structured data, and code examples for frontend development.

Setup Requirements

  • ⚠️Requires a local SQLite database (`ecl-database.sqlite`) to be present and populated. This database is built by running the `crawl.js` script.
  • ⚠️Requires execution of the `download-ecl-assets.sh` script to fetch frontend assets (CSS, JS, icons) for local development if building pages from templates.
  • ⚠️Requires Node.js (version >=18 recommended based on `@modelcontextprotocol/sdk` dependencies).
Verified SafeView Analysis
The server-side Node.js code (`index.js`, `crawl.js`) uses parameterized SQL queries, mitigating SQL injection risks. It fetches data from known, official European Commission domains via HTTPS. No 'eval' or direct execution of arbitrary user-provided code is observed. The 'start_here' tool returns a shell script (`download-ecl-assets.sh`) as text content, which the user is then instructed to run manually; the server itself does not execute this script, placing the responsibility of reviewing and running the script on the user. The `ecl-ec.js` file is a minified client-side library and its direct impact on server security is minimal for this MCP.
Updated: 2025-11-27GitHub→
PreviousPage 444 of 713Next