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)

32
2
Low Cost
peakflames icon

BitbucketMcpServers

by peakflames

Sec9

Provides Model Context Protocol (MCP) server functionality for integrating with Bitbucket Cloud repositories to perform operations like listing pull requests and retrieving their details.

Setup Requirements

  • ⚠️Requires a Bitbucket Cloud account name configured in appsettings.json.
  • ⚠️Requires authentication credentials (either OAuth 2.0 Consumer Key/Secret or Bitbucket Username/App Password) to be provided via environment variables at startup.
  • ⚠️Requires .NET 9.0 SDK for local development, or Docker for containerized deployment.
Verified SafeView Analysis
The server explicitly uses environment variables for sensitive credentials (OAuth 2.0 consumer key/secret or Bitbucket username/app password) and warns against committing these to `appsettings.json`. It supports OAuth 2.0 which is more secure for production. Standard API server practices are followed. No direct 'eval' or obvious malicious patterns found in the provided code snippets. A score of 9 reflects good security practices, with a minor deduction as any application handling credentials always carries inherent risk and requires careful deployment.
Updated: 2026-01-16GitHub→
32
2
Medium Cost
0pens0 icon
Sec9

Provides AI-powered access to Cloud Foundry operations through specialized tools, acting as a Model Context Protocol (MCP) server.

Setup Requirements

  • ⚠️Requires access to a running Cloud Foundry foundation and valid credentials (API host, username, password).
  • ⚠️Requires Maven 3.9+ and Java 21 for local building and development.
  • ⚠️Default organization and space can be configured for default context, or provided per tool call.
Verified SafeView Analysis
The server's source code adheres to good practices, utilizing Spring's externalized configuration for sensitive credentials (environment variables or VCAP services), preventing hardcoded secrets in committed files. Interactions with Cloud Foundry are performed through the official Java client library, which is generally secure. The placeholder generation for application cloning involves creating temporary files and writing minimal, buildpack-specific code, but this is programmatically controlled and not exposed to arbitrary user input for command execution. No direct 'eval' or similar dangerous patterns were found. Proper secure deployment (e.g., using HTTPS, managing CF roles) is assumed for maximum security.
Updated: 2025-12-07GitHub→
32
4
High Cost
Cadasto icon
Sec8

The openEHR Assistant MCP Server helps AI assistants integrate with openEHR resources, terminology services, and CKM APIs to assist healthcare informaticians with tasks such as archetype exploration, semantic explanation, language translation, syntax correction, and design reviews.

Setup Requirements

  • ⚠️Requires Docker and Docker Compose for local setup, as PHP 8.4 with specific extensions is containerized.
  • ⚠️Development workflows require executing PHP/Composer commands directly inside the Docker container.
  • ⚠️Local development might encounter SSL certificate issues with upstream APIs, potentially requiring `HTTP_SSL_VERIFY=false` (not recommended for production use).
Verified SafeView Analysis
The codebase avoids obvious 'eval' or direct execution of untrusted input. `SimpleXMLElement` is used to parse a local, trusted XML file (`openehr_terminology.xml`), minimizing XXE risk. Dynamic regex construction for search patterns uses `preg_quote` to prevent regex injection. Network calls use Guzzle, with SSL verification configurable via the `HTTP_SSL_VERIFY` environment variable (setting this to 'false' in production would be a risk, but it is a configurable choice). No hardcoded secrets are apparent; sensitive configurations are handled via environment variables. Overall, the implementation appears to follow good security practices within the analyzed scope.
Updated: 2026-01-07GitHub→
32
1
High Cost
FajarArrizki icon

mcp-technical-analysis

by FajarArrizki

Sec8

A comprehensive Model Context Protocol (MCP) server that bridges AI assistants with professional cryptocurrency market analysis capabilities, real-time market data, technical analysis, and Hyperliquid trading execution.

Setup Requirements

  • ⚠️Requires secure management of `AGENT_WALLET_PRIVATE_KEY` and `MAIN_WALLET_ADDRESS` environment variables for live trading (real money).
  • ⚠️Requires `MEM0_API_KEY` and `MEM0_USER_ID` environment variables for AI memory features (Mem0 is an external platform).
  • ⚠️Geographic restrictions may apply for Binance and Hyperliquid access, potentially requiring VPN or specific DNS configurations.
  • ⚠️Testnet trading is recommended for initial use as mainnet trading involves real funds and is irreversible.
Verified SafeView Analysis
The project demonstrates strong security practices for a financial trading agent, including explicit `confirmExecution: true` for mainnet trades, asset whitelisting, position size limits, and Zod schema validation for inputs. Environment variables are used for sensitive keys like `AGENT_WALLET_PRIVATE_KEY`. Network communication is designed for local (`localhost`) access via HTTP/SSE, minimizing direct external exposure. The use of `cross-spawn` and `tsx` to execute scripts is noted, but the primary interactions are with trusted APIs. Real-money trading always carries inherent risks, but the system has implemented safeguards.
Updated: 2025-12-05GitHub→
31
3
Low Cost
NasAndNora icon

obsidian-http-mcp

by NasAndNora

Sec8

Facilitates AI agents, such as Claude Code, to manage Obsidian notes by providing an HTTP-native Model Context Protocol (MCP) server, bypassing stdio transport bugs.

Setup Requirements

  • ⚠️Requires Obsidian with the 'Local REST API' plugin enabled, with 'Non encrypted (HTTP) API' enabled and 'Binding Host' set to '0.0.0.0' for Docker/WSL2 scenarios.
  • ⚠️For cross-platform usage (e.g., AI on WSL2, server on Windows), the server must be installed and run on the same system as Obsidian, and the AI client must connect to the server's specific IP address (e.g., Windows bridge IP) rather than localhost.
  • ⚠️For any production deployment or exposure beyond a trusted local network, a reverse proxy with authentication, rate limiting, and HTTPS/TLS is CRITICAL, as these security features are not built into the server itself.
Verified SafeView Analysis
The server implements path traversal prevention, ReDoS protection (query length limit), PORT validation, type safety, and a request size limit. Soft delete is enabled by default, moving files to a trash directory. Crucially, the documentation explicitly states the server is designed for trusted networks (localhost, LAN, VPN) and does NOT include built-in authentication, rate limiting, or HTTPS. It binds to `0.0.0.0` for cross-platform compatibility, which requires a reverse proxy with authentication, rate limiting, and TLS for production or internet exposure. The strong emphasis on user responsibility for external security measures is a positive, but the lack of built-in measures limits its standalone security score.
Updated: 2025-11-19GitHub→
31
1
Low Cost
MagicTurtle-s icon

asana-mcp-railway

by MagicTurtle-s

Sec9

This server acts as a Model Context Protocol (MCP) server for Asana, enabling AI agents (like Claude Code/Desktop) to manage tasks and projects in Asana through a comprehensive set of 42 tools.

Setup Requirements

  • ⚠️Requires registration and configuration of an Asana OAuth App (Client ID, Client Secret, Redirect URI) in the Asana Developer Console.
  • ⚠️Critical environment variables (ASANA_CLIENT_ID, ASANA_CLIENT_SECRET, ASANA_REDIRECT_URI) must be set before running.
  • ⚠️For production deployments, integrating with a persistent storage solution like Redis is recommended for token management, as the default implementation uses in-memory storage (tokens are lost on server restart).
Verified SafeView Analysis
The project demonstrates strong security practices for OAuth 2.0, including PKCE for authorization code flow and loading all secrets from environment variables. It also implements robust session management with asyncio locks, state machines, and circuit breakers to prevent re-authentication loops and handle concurrent requests. CORS is set to `allow_origins=["*"]` in development, but the documentation explicitly advises restricting this for production deployments. In-memory token storage is used by default, with clear recommendations for Redis in production for persistence.
Updated: 2025-11-23GitHub→
31
1
Medium Cost
sumitparakh icon

ai-collections

by sumitparakh

Sec9

Provides a comprehensive collection of resources and proof-of-concept implementations for building and understanding Model Context Protocol (MCP) servers, integrating LLMs with external tools and data.

Setup Requirements

  • ⚠️Requires API keys for various AI services (e.g., OpenAI, Anthropic, vector databases) which can incur significant costs depending on usage.
  • ⚠️Requires specific language runtimes (Python 3.8+, Node.js 16+, Rust 1.70+) and their respective package managers.
Verified SafeView Analysis
The project documentation strongly emphasizes critical security best practices, including never committing API keys (mentioned multiple times), API key management, input validation, output filtering, rate limiting, privacy considerations, and secure data handling. No malicious patterns or 'eval' calls are visible in the truncated source code provided, suggesting a strong focus on secure development. However, as it's a collection of POCs, the security of actual implementations would require individual audits.
Updated: 2025-11-22GitHub→
31
1
Low Cost
samiribrh icon

tableau-mcp

by samiribrh

Sec8

A Model Context Protocol (MCP) server enabling Claude Desktop to interact with Tableau Server, allowing natural language operations like uploading datasets, checking data sources, and converting Excel files to Tableau Hyper format.

Setup Requirements

  • ⚠️Requires Claude Desktop App for full integration.
  • ⚠️Requires a local Ollama instance running with a supported model (e.g., 'llama3.1:8b') for AI capabilities.
  • ⚠️Requires Tableau Server with a configured Personal Access Token (PAT).
Verified SafeView Analysis
The server correctly uses environment variables (`.env`) for sensitive Tableau Personal Access Token (PAT) credentials, avoiding hardcoded secrets. It is designed for local desktop app integration, which inherently reduces network exposure risks. No 'eval' or obfuscation is present. File path handling for uploads, while attempting to resolve paths within a default directory, could theoretically allow access to other files within that directory if the LLM generates an unexpected path. However, the tool definition strongly hints the LLM to provide 'filename only', mitigating this risk for its intended use case.
Updated: 2025-11-26GitHub→
31
1
Medium Cost
anand-kamble icon

mcp-instagram

by anand-kamble

Sec9

Provides an MCP (Model Context Protocol) server for integrating with Instagram, enabling AI clients to interact with Instagram functionalities like viewing profiles, posts, stories, and performing engagement actions.

Setup Requirements

  • ⚠️Requires Node.js 18+ or 20+ to be installed.
  • ⚠️Instagram account credentials (IG_USERNAME and IG_PASSWORD) must be provided via environment variables or explicitly in the MCP client configuration.
  • ⚠️If Two-Factor Authentication (2FA) is enabled on the Instagram account, the `instagram_complete_2fa` tool must be used after initial login to complete the authentication flow.
  • ⚠️Relies on an unofficial Instagram API, which carries inherent risks of account restrictions or API changes breaking functionality.
Verified SafeView Analysis
The server correctly loads Instagram credentials (username, password) from environment variables (IG_USERNAME, IG_PASSWORD), preventing hardcoded secrets. Session data for `instagram-private-api` is persisted locally in `data/session.json` within the project directory, which is standard for local session management but means the user is responsible for securing this file. There are no obvious signs of arbitrary code execution (e.g., `eval` or `child_process.exec` on user input) or network-exposed vulnerabilities beyond its stdio interface designed for local client communication. The use of an unofficial Instagram API is explicitly disclosed as a risk to account status, but this is inherent to the chosen underlying library, not a direct vulnerability in the server's implementation.
Updated: 2025-11-24GitHub→
31
1
Low Cost
murigugitonga icon

mcp_server_ts

by murigugitonga

Sec8

A Node.js Model Context Protocol (MCP) server designed to expose defined tools, currently featuring a placeholder 'create-user' capability, for interaction with external models or clients.

Setup Requirements

  • ⚠️Requires Node.js runtime (typically >=18 as indicated by dependencies' engine requirements).
  • ⚠️Relies on TypeScript, requiring 'typescript' and 'ts-node' for direct execution ('npm run server:dev') or a prior build step ('npm run server:build').
  • ⚠️Users need familiarity with the Model Context Protocol (MCP) to develop clients or effectively interact with the server's tools.
Verified SafeView Analysis
The server leverages the @modelcontextprotocol/sdk and uses Zod for robust input schema validation, which is a strong security practice. There are no direct 'eval' calls or obvious obfuscation. The 'create-user' tool's implementation is currently an empty placeholder, preventing a deeper analysis of data persistence security. A notable point is the 'DANGEROUSLY_OMIT_AUTH=true' flag used in the 'server:inspect' script, which explicitly disables authentication for inspection purposes. While clearly labeled for development/debugging, this flag represents a potential operational risk if inadvertently enabled in a production environment. The use of 'dotenv' suggests awareness for managing secrets, although no 'process.env' usage is visible in the provided 'server.ts' snippet.
Updated: 2025-12-13GitHub→
31
2
High Cost
ThibautMelen icon

claude-insane-guide

by ThibautMelen

Sec7

Orchestrates complex multi-dialog workflows using sequential chaining for adaptable linear processes. It is recommended for advanced Claude Code patterns, specifically for mastering the orchestration of intricate dialogues.

Setup Requirements

  • ⚠️Requires `npm` and network access to fetch the `@modelcontextprotocol/sequential-thinking` package via `npx`.
  • ⚠️As a Model Context Protocol (MCP) server, it will likely consume a significant portion of the context window (potentially 50k+ tokens at startup), impacting overall token efficiency and potentially increasing costs for prolonged usage, as per general MCP server characteristics discussed in the guide.
Verified SafeView Analysis
No specific security audit details are provided in the source for this particular MCP server. It is assumed to be safe as it's a recommended tool within the Claude Code ecosystem, likely from official or trusted partners. However, general best practices for vetting third-party dependencies should always be applied.
Updated: 2025-11-21GitHub→
31
1
Medium Cost

push-chain-mcp-server

by kshitij-hash

Sec7

A unified Model Context Protocol (MCP) server providing AI assistants with comprehensive access to Push Chain documentation and SDK APIs.

Setup Requirements

  • ⚠️Requires executing a shell script (`setup.sh`), implying a Unix-like environment (Linux/macOS or WSL on Windows).
  • ⚠️Requires IDE-specific configuration detailed in `SETUP.md` for integration with AI assistants like Claude Code, Cursor, or Windsurf.
  • ⚠️Optional but recommended GitHub Personal Access Token is needed for full functionality, particularly for updating SDK and documentation data.
Verified SafeView Analysis
The server's primary risk vectors are the `setup.sh` script and the SDK/docs auto-update mechanisms (`sdk-updater.js`, `generate-docs-data.js`, `generate-sdk-data.js`), which fetch data directly from GitHub. While this is common for developer tools, a compromise of the upstream Push Chain repositories could introduce malicious code. An optional GitHub token for data fetching also adds a credential management concern. For an internal developer-focused tool, these risks are manageable but warrant caution.
Updated: 2025-11-18GitHub→
PreviousPage 197 of 760Next