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
High Cost
Satyampant icon
Sec8

An autonomous multi-agent AI equity trading system for diverse investment strategies.

Setup Requirements

  • ⚠️Requires Groq API Key (free tier available, but usage limits apply; paid tier recommended for sustained use).
  • ⚠️Requires Polygon.io API Key (free tier provides End-Of-Day data, paid/real-time tiers offer more current data).
  • ⚠️Requires either Brave Search API Key OR Serper API Key for the researcher agent's web search capabilities.
  • ⚠️Requires Pushover API Key and User Key for push notifications.
  • ⚠️Requires Python 3.12+ and Node.js (for npx commands used by some MCP servers).
  • ⚠️Requires the `uv` package manager for installation and running scripts.
Verified SafeView Analysis
The system utilizes `uvx` and `npx` to dynamically fetch and execute external MCP server binaries from remote repositories (e.g., GitHub, npm). While this is part of the MCP framework, it introduces a dependency supply chain risk if external sources are compromised. Secrets (API keys) are properly externalized via environment variables, and the system uses a local SQLite database for persistence.
Updated: 2025-11-30GitHub→
0
0
High Cost
carglezfer icon

MaxKB

by carglezfer

Sec3

An enterprise-grade agent platform for building AI applications, offering RAG, workflow orchestration, and integration with various large language models and knowledge bases.

Setup Requirements

  • ⚠️Requires Docker for deployment.
  • ⚠️Requires PostgreSQL/pgvector for database and vector store.
  • ⚠️Requires configuration of LLM and embedding models, potentially involving API keys for third-party services (e.g., OpenAI, AWS Bedrock, Tencent Cloud, etc.) or local model deployment.
  • ⚠️Default admin credentials (username: admin, password: MaxKB@123..) are insecure and must be changed immediately after deployment.
Review RequiredView Analysis
Critical vulnerabilities identified: The backend uses `exec_code` for user-defined tools, a highly dangerous function that is extremely difficult to secure against malicious code injection, even with attempted sandboxing. The default admin password 'MaxKB@123..' is hardcoded in the README, posing a severe risk if not immediately changed. Potential SQL injection vectors exist in `common/db/search.py` due to 'native' SQL query construction without clear input sanitization. Dynamic `baseURL` from `window.MaxKB?.prefix` in frontend requests, if not strictly controlled on the server, could introduce risks. While there is extensive use of permission decorators, the complexity of fine-grained access control can sometimes lead to bypasses if not implemented perfectly.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
zanderthuo icon

MCP_SERVER_PRAC

by zanderthuo

Sec8

The MCP (Multi-Agent Communication Protocol) server provides a robust framework for building and interacting with AI-powered agent services. It supports various transports (SSE, HTTP, Stdio, WebSocket), incorporates authentication and transport security, and offers functionalities for resource management, tool execution, prompt elicitation, and AI sampling. It serves as a foundational layer for developing complex, intelligent agent systems.

Setup Requirements

  • ⚠️Requires Python 3.12+.
  • ⚠️Potential dependency on external AI models (e.g., OpenAI API Key for `OpenAISamplingHandler`, which is a paid service).
  • ⚠️Requires networking/port availability (e.g., `http://localhost:8080`).
  • ⚠️Some CLI commands (`mcp dev`, `mcp run`) may leverage `uv` (a fast Python package installer/resolver), potentially implying a dependency on `uv` being installed and configured in the environment.
Verified SafeView Analysis
The project extensively uses well-vetted libraries like Uvicorn, httpx, websockets, Authlib, and Pydantic, which significantly enhances security. It implements robust authentication (OAuth2, JWT) and transport security mechanisms (trusted hosts, allowed origins). A potential concern is the use of `eval` within the `jaraco.functools.except_` decorator. While typically controlled by the developer using the decorator and not directly exposed to untrusted external input within the application layer, `eval` always carries inherent risks if misused or if input sanitization fails elsewhere. Overall, the architecture shows a strong focus on security best practices.
Updated: 2025-11-24GitHub→
0
0
Medium Cost
DiscourseGraphs icon

discourse-graph-mcp

by DiscourseGraphs

Sec8

Exposes structured discourse graphs to AI assistants for exploration, search, and traversal of research knowledge, including dynamic schema adaptation and inline image display.

Setup Requirements

  • ⚠️Requires a local JSON discourse graph file specified by the DATA_PATH environment variable.
  • ⚠️Image fetching and base64 encoding for inline display can be slow and consume high token counts for image-rich nodes.
  • ⚠️This is a Proof-of-Concept, not optimized for production with limited error handling and no authentication/access control.
Verified SafeView Analysis
The server loads data from a local JSON file (`DATA_PATH`) and fetches images from publicly accessible Firebase URLs. The `fetchImageAsBase64` function, while designed for public URLs, could pose a Server-Side Request Forgery (SSRF) risk if the `DATA_PATH` file itself were compromised with malicious, internal network URLs. However, given it's a Proof-of-Concept, intended for a single static, presumably trusted JSON data source, and operates via standard I/O (stdio) rather than a network port exposed to the internet, the immediate external attack surface is minimal. No 'eval' or obvious malicious patterns found in the source code. The primary risk lies with the integrity of the input JSON data file.
Updated: 2026-01-16GitHub→
0
0
High Cost
leegonzales icon

MCPServers

by leegonzales

Sec9

Generate, animate, extend, and transition AI-powered videos using Google Veo 3.1 via the Model Context Protocol.

Setup Requirements

  • ⚠️Requires a Google Gemini API Key (GEMINI_API_KEY environment variable) obtained from Google AI Studio (potentially incurs cost for video generation).
  • ⚠️Requires Node.js version 18 or higher to run.
  • ⚠️Generated video files require local disk space (`~/Documents/veo_generated`).
Verified SafeView Analysis
The server correctly retrieves the `GEMINI_API_KEY` from environment variables, preventing hardcoded credentials. File system operations (read, write, delete) are strictly confined to a dedicated user-specific output directory (`~/Documents/veo_generated`), and output filenames use `randomUUID` to prevent path traversal vulnerabilities. Input validation for tool parameters is handled robustly using Zod schemas. The server utilizes standard I/O for communication (StdioServerTransport), avoiding direct network port exposure, and outgoing API calls to Google are made securely with an API key in headers.
Updated: 2026-01-08GitHub→
0
0
Low Cost
SylphxAI icon

mcp-server-sdk

by SylphxAI

Sec9

Pure functional MCP (Model Context Protocol) server SDK for building AI-callable tools, resources, and prompts.

Setup Requirements

  • ⚠️Primarily optimized and built for Bun, although Node.js compatibility is maintained through `node:stream` and general web standards (Fetch API, gust).
Verified SafeView Analysis
The server uses `@sylphx/vex` for robust, type-safe schema validation on all tool and prompt inputs, mitigating common injection vectors. JSON-RPC messages are parsed and validated by `Rpc.parseMessage`. The HTTP transport allows configurable CORS, including a wildcard ('*') which, while flexible, should be used with caution in production. No direct `eval` calls or hardcoded sensitive credentials were found. Standard network server vulnerabilities (e.g., large payload DoS) are inherent to HTTP transport but are not specific to this SDK's logic.
Updated: 2025-12-05GitHub→
0
0
Low Cost
Bytelope icon
Sec9

Provides tools for AI assistants to search and retrieve details about Swedish IT consultant jobs.

Setup Requirements

  • ⚠️Requires `API_SECRET` environment variable for self-hosting.
Verified SafeView Analysis
The server correctly handles API secrets via environment variables (API_SECRET) and uses Zod for robust input validation, mitigating common injection risks. There is no evidence of 'eval' or obfuscation. It interacts with a single, defined external API endpoint (https://consultant.dev/api). Permissive CORS headers are present, which is typical for a public tool, but not a critical vulnerability.
Updated: 2025-12-12GitHub→
0
0
Medium Cost
Nn9987 icon
Sec10

The mcp-docs-server provides a Model Context Protocol (MCP) server for efficient search and retrieval of MCP documentation.

Setup Requirements

  • ⚠️Requires Node.js 18.0.0 or higher.
  • ⚠️Requires an active internet connection for initial documentation indexing and subsequent document retrieval.
Verified SafeView Analysis
The server demonstrates strong security practices. It uses Zod for input validation and critically restricts all external HTTP fetches to a hardcoded allow-list (only 'https://modelcontextprotocol.io/'). This effectively prevents Server-Side Request Forgery (SSRF) and other arbitrary file/URL access vulnerabilities. There is no usage of 'eval', obfuscation, or hardcoded secrets in the provided source code. The application communicates over standard I/O (stdio) when run, which is inherently secure in a local child-process context.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
MissionSquad icon

mcp-thorchain

by MissionSquad

Sec9

Provides an MCP server to access THORChain blockchain data for AI assistants, including transaction details, address history, pool statistics, network stats, and vault addresses.

Setup Requirements

  • ⚠️Requires Node.js >= 20.0.0
  • ⚠️Manual configuration of Claude Desktop JSON file with an absolute path is required for integration.
Verified SafeView Analysis
Input validation is rigorously enforced using Zod schemas. The server makes API calls to public THORChain endpoints (Midgard, Thornode) and includes provider rotation for redundancy. No hardcoded sensitive secrets or 'eval' usage were found in the provided source code. Direct calls to external APIs inherently carry a minor risk from those APIs, but the project itself appears well-secured.
Updated: 2025-11-22GitHub→
0
0
Low Cost
kaushaldhingra128-boop icon

test-remote-mcp-server

by kaushaldhingra128-boop

Sec1

Unable to identify the specific use case for this 'MCP Server' as the source code was not provided in the prompt.

Setup Requirements

  • ⚠️Source code not provided, cannot analyze requirements or friction points.
Review RequiredView Analysis
Source code for 'test-remote-mcp-server' was not provided in the prompt, making it impossible to perform a security audit for 'eval', obfuscation, network risks, hardcoded secrets, or malicious patterns. Due to the complete lack of visibility, the lowest possible security score is assigned, and it is marked as unsafe to run.
Updated: 2025-11-25GitHub→
0
0
Medium Cost
civicteam icon
Sec9

An MCP server for interacting with the CardPointe Gateway payment processing API, enabling transaction, inquiry, profile, reporting, and BIN lookup operations.

Setup Requirements

  • ⚠️Requires CardPointe Gateway API Credentials (Merchant ID, Username, Password, Site Identifier) obtained from Fiserv/CardPointe Portal.
  • ⚠️Requires Node.js version >= 20.0.0.
  • ⚠️Defaults to read-only mode; 'READONLY=false' must be set to enable write operations like authorizations, captures, refunds, voids, and profile creation/updates/deletions.
Verified SafeView Analysis
The server correctly handles sensitive credentials by requiring them as environment variables (CARDPOINTE_USERNAME, CARDPOINTE_PASSWORD, CARDPOINTE_MERCHANT_ID). All API communication uses HTTPS. A robust 'read-only' mode is implemented and enabled by default, blocking all write operations and significantly enhancing safety for production deployments. No 'eval' or obvious obfuscation detected. Error handling is present to prevent exposing raw API errors directly, though further sanitization might be considered for verbose error messages.
Updated: 2026-01-07GitHub→
0
0
Medium Cost
jjones-wps icon

pyodbc-mcp-server

by jjones-wps

Sec9

Provides read-only access to Microsoft SQL Server databases for AI assistants and other clients via the Model Context Protocol (MCP), using Windows Authentication.

Setup Requirements

  • ⚠️Requires Windows operating system to connect to SQL Server using Windows Authentication.
  • ⚠️Requires ODBC Driver 17 or 18 for SQL Server to be installed.
  • ⚠️Requires a Windows domain account with SELECT permissions on the target SQL Server database.
Verified SafeView Analysis
Designed with robust security: strictly read-only (blocking INSERT, UPDATE, DELETE, etc., even in subqueries), uses Windows Authentication (no credentials stored), enforces row limiting, and communicates via stdio only (no network exposure). A documented local API token exposure was confirmed never to have been committed to git or involved actual project tokens; mitigation is complete.
Updated: 2026-01-03GitHub→
PreviousPage 486 of 760Next