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(9120)

36
6
Medium Cost
M3l3r0 icon

MCP-buddy

by M3l3r0

Sec9

A local desktop or web application to manage and interact with multiple MCP (Model Context Protocol) servers, offering optional AI orchestration and enhancement for responses.

Setup Requirements

  • ⚠️AI enhancement and orchestration features require an API key from a supported LLM provider (e.g., OpenAI, Anthropic, Snowflake Cortex), which may incur costs.
  • ⚠️Requires access to and configuration of at least one MCP server to be fully functional.
  • ⚠️For developers, initial configuration can be loaded from `public/config.local.json`; for other users, configuration is done via the UI and saved in browser localStorage.
Verified SafeView Analysis
The application is designed to run 100% locally, with user configurations (including sensitive API keys and tokens) stored either in the browser's localStorage or a git-ignored `public/config.local.json` file. It explicitly warns against committing sensitive data and provides a `check-secrets.sh` script. CORS is enabled for local communication, and OAuth tokens are cached with expiration. No direct `eval` calls or obfuscation were found. Network risks are minimal as it's intended for localhost use.
Updated: 2026-01-19GitHub
36
8
High Cost
MadnessEngineering icon

Omnispindle

by MadnessEngineering

Sec3

Omnispindle acts as a coordination layer providing standardized Model Context Protocol (MCP) tools for AI agents to manage todos, capture lessons, and facilitate cross-project coordination within the Madness Interactive ecosystem.

Setup Requirements

  • ⚠️Requires Python 3.13 for optimal performance and specified deployments.
  • ⚠️MongoDB is required for 'hybrid' and 'local' operation modes (Docker Compose includes it).
  • ⚠️Auth0 authentication is required; the system attempts browser-based login automatically on first use, or requires manual `AUTH0_TOKEN`, `MCP_USER_EMAIL`, or `MCP_USER_ID` environment variables.
  • ⚠️Requires `mosquitto-clients` package (for `mosquitto_pub` command) for MQTT status publishing functionality.
Review RequiredView Analysis
CRITICAL: The `bring_your_own` tool (in `src/Omnispindle/tools.py`) allows arbitrary code execution (Python, JavaScript, Bash) via `subprocess.run` and `importlib.util.module_from_spec` (equivalent to `eval`). While its docstring claims it is 'DISABLED for security reasons,' the code for execution is present and it is enabled in the default 'full' tool loadout when running in local mode. This is a severe security risk. Additionally, Auth0 configuration defaults (domain, client ID, audience) are hardcoded in `src/Omnispindle/auth_utils.py` and `src/Omnispindle/token_exchange.py`, which the README explicitly warns against deploying as-is. The `mqtt_publish` function uses `subprocess.run` directly with input strings, posing a potential command injection risk if not properly sanitized.
Updated: 2026-01-17GitHub
36
7
Low Cost
XenoXilus icon

outlook-mcp

by XenoXilus

Sec9

Enables AI assistants to interact with Microsoft Outlook for email, calendar, and SharePoint operations through the Microsoft Graph API.

Setup Requirements

  • ⚠️Requires manual setup of an Azure Active Directory application to obtain Client ID and Tenant ID.
  • ⚠️Initial authentication requires user interaction via a browser for OAuth 2.0 consent.
Verified SafeView Analysis
The server employs robust security practices including OAuth 2.0 with PKCE for secure delegated authentication, ensuring no client secrets are stored. Tokens are encrypted and stored locally, leveraging the OS keychain if available, or encrypted file storage as a fallback. Critical configuration values (Client ID, Tenant ID) are explicitly handled via environment variables, preventing hardcoding. Input and output content are actively sanitized using DOMPurify and custom malicious pattern detection to mitigate XSS and other injection vulnerabilities. Furthermore, HTTP connections to the Microsoft Graph API utilize TLSv1.2 with strong ciphers and configured connection pooling, enhancing network security and reliability. There is active validation of file paths to prevent traversal attacks. No instances of 'eval' or obvious obfuscation were found.
Updated: 2026-01-18GitHub
36
8
High Cost

Provides up-to-date Node.js API documentation and release schedule information as a service via the Model Context Protocol.

Setup Requirements

  • ⚠️Requires Node.js version >=22.0.0.
  • ⚠️Requires internet access for initial data fetching from nodejs.org and github.com (cached thereafter).
  • ⚠️Specific client-side configuration (e.g., for Claude Desktop or Cursor AI) is needed to integrate the MCP server.
Verified SafeView Analysis
The server primarily fetches data from trusted, official Node.js documentation sources (nodejs.org, raw.githubusercontent.com) and uses an in-memory cache to reduce external calls. Explicit security linting rules (via eslint-plugin-security) are configured to prevent common vulnerabilities like arbitrary file system access, unsafe regex, child process execution, and eval with expressions. While object injection warnings are present in `src/tools/index.ts`, analysis shows the keys used are internally defined and not user-controlled, mitigating this specific risk. No hardcoded secrets or other malicious patterns were identified in the provided source code.
Updated: 2026-01-19GitHub
36
8
Medium Cost
Sec9

Integrates Simplenote with Claude Desktop as a memory backend or content source via the Model Context Protocol (MCP), enabling AI interaction with user notes.

Setup Requirements

  • ⚠️Requires Simplenote account credentials (email and password).
  • ⚠️For non-Docker installs, Python 3.10+ is required.
  • ⚠️Running MCP evaluations (optional) requires an OpenAI API key (paid) and Node.js dependencies.
Verified SafeView Analysis
The project demonstrates a high commitment to security best practices, including multi-stage Docker builds, non-root user execution, read-only filesystems, and built-in health checks. CI/CD pipelines incorporate automated security scanning (Bandit, pip-audit, Trivy, Cosign, SBOM generation) and `scripts/security.py` validates inputs against common vulnerabilities. Environment variables are used for sensitive credentials, avoiding hardcoding. No 'eval' or similar dangerous patterns are apparent for user input.
Updated: 2026-01-19GitHub
36
3
Medium Cost
Sec7

A specialized Model Context Protocol (MCP) server for MiniMax AI, providing web search and image analysis tools specifically tailored for coding development workflows.

Setup Requirements

  • ⚠️Requires a MiniMax API Key (a paid service).
  • ⚠️Requires the `uv` Python package manager to be installed.
  • ⚠️The `MINIMAX_API_HOST` environment variable must be regionally aligned with your `MINIMAX_API_KEY` to avoid 'invalid api key' errors.
  • ⚠️Windows users integrating with Claude Desktop must enable 'Developer Mode'.
  • ⚠️If 'uvx' command is not in your system's PATH, you may need to specify its absolute path in the MCP client configuration.
Verified SafeView Analysis
The `process_image_url` function can download images from arbitrary HTTP/HTTPS URLs or read from local file paths. If the server processes untrusted input for `image_source`, this could be a vector for Server-Side Request Forgery (SSRF) or resource exhaustion attacks, particularly if deployed in a multi-user or cloud environment. While the image content isn't directly executed, fetching arbitrary external data poses an indirect risk. No `eval` or direct code execution vulnerabilities are apparent, and API keys are handled securely via environment variables.
Updated: 2025-11-20GitHub
36
9
Low Cost
CorgiBoyG icon

mcp-server-weixin

by CorgiBoyG

Sec9

Provides a service for AI systems to send templated messages to WeChat public account users.

Setup Requirements

  • ⚠️Requires WeChat Public Account AppID, AppSecret, TemplateID, User OpenID, and Original ID.
  • ⚠️JDK 17+ and Maven 3.6+ required for local development/build.
  • ⚠️Mandatory configuration in `src/main/resources/application.yml` for WeChat API parameters.
Verified SafeView Analysis
The application follows good practices for handling sensitive information by externalizing configurations to `application.yml` for WeChat API credentials. It explicitly warns users against committing `AppSecret` to code repositories. Access tokens are properly cached with a 2-hour expiry. A hardcoded example access token exists in a test file, but it's for testing and immediately overwritten by a real token fetch, posing minimal risk. No 'eval' or malicious patterns were found. The Docker push script uses a local config file for credentials, which is good practice for CI/CD.
Updated: 2025-11-22GitHub
36
35
Medium Cost
Sec4

Integrates InfraNodus knowledge graph and text network analysis capabilities into LLM workflows and AI assistants for generating knowledge graphs, detecting content gaps, identifying topics, and performing SEO analysis.

Setup Requirements

  • ⚠️Requires a (potentially paid) InfraNodus API Key to avoid rate limits and access full functionality.
  • ⚠️OAuth client registrations are stored in-memory and will not persist across server restarts, impacting client session stability.
  • ⚠️The HTTP server uses an OAuth2 authorization flow that may require a deeper understanding of OAuth for manual setup.
Review RequiredView Analysis
The server's JWT access tokens contain the InfraNodus API key directly in their unencrypted payload. While the token is signed, any compromise of the access token immediately exposes the API key, allowing unauthorized access to the InfraNodus API. OAuth client registrations are stored in-memory and will not persist across server restarts, which means clients would need to re-register after server restarts if relying on the registration endpoint. Extensive logging of request and response bodies may expose sensitive information in logs if not properly managed.
Updated: 2025-12-31GitHub
36
7
Medium Cost

mcp-bybit-server

by dlwjdtn535

Sec8

Provides an MCP interface for interacting with the Bybit cryptocurrency exchange API to fetch market data, manage accounts, and place orders.

Setup Requirements

  • ⚠️Requires a Bybit account and API keys with specific permissions (Read, Trade, Wallet).
  • ⚠️Requires 'uv' (a Python package installer/runner) or Docker to be installed and configured.
  • ⚠️Environment variables ACCESS_KEY and SECRET_KEY must be set.
Verified SafeView Analysis
Requires careful handling of Bybit API keys, including enabling IP restrictions and limiting permissions (Read, Trade, Wallet) to minimize risk. The README provides clear security warnings and best practices for API key management.
Updated: 2025-11-17GitHub
36
7
Medium Cost
binalyze icon

air-mcp

by binalyze

Sec9

A Node.js server implementing Model Context Protocol (MCP) for Binalyze AIR, enabling natural language interaction with AIR's digital forensics and incident response capabilities.

Setup Requirements

  • ⚠️Requires `AIR_HOST` environment variable to be set (URL of Binalyze AIR API).
  • ⚠️Requires `AIR_API_TOKEN` environment variable to be set (API token for Binalyze AIR, obtained from the console).
  • ⚠️Requires Node.js runtime (version 16 or higher).
Verified SafeView Analysis
The server uses environment variables for sensitive configurations like `AIR_API_TOKEN` and `AIR_HOST`. It employs `zod` for robust input validation on all tool arguments, significantly reducing risks from malformed inputs. Standard `axios` library is used for external API interactions. Error handling is present for API calls. No obvious malicious patterns or unsafe code execution (`eval`) were found.
Updated: 2025-12-02GitHub
36
5
High Cost

This server acts as a Model Context Protocol (MCP) gateway, integrating various AI capabilities (image recognition, TTS, image/video generation, chat summarization, personality analysis) and WeChat-specific functions (song requests, emoji extraction, group management) for a WeChat robot.

Setup Requirements

  • ⚠️Requires a MySQL database for configuration storage and message history, with tenant databases created dynamically based on 'RobotCode'.
  • ⚠️Relies on external AI service providers (e.g., OpenAI, Doubao, Jimeng, GLM, Hunyuan) for AI capabilities, which will incur API usage costs.
  • ⚠️Assumes the existence of a separate 'WeChat client' component that this server communicates with via HTTP for sending messages.
Review RequiredView Analysis
CRITICAL vulnerability identified: The `buildDSNForRobot` function constructs a MySQL DSN using `robotCode` directly as the database name. If `robotCode` can be controlled or influenced by an attacker, this allows for database name injection, potentially enabling access to arbitrary databases on the MySQL server or causing denial of service by repeatedly attempting to connect to non-existent databases. Additionally, the server makes external HTTP requests to various AI service providers (e.g., OpenAI, Doubao, Jimeng, GLM, Hunyuan) and a music API (`api.cenguigui.cn`). While parameters are typically encoded, the reliability and security of these third-party services are external dependencies. AI API keys and other sensitive settings are stored in the database, requiring robust database security. No 'eval' or obvious obfuscation detected.
Updated: 2026-01-17GitHub
36
3
Medium Cost

Power-BI-MCP-Server

by michaelmckinleyconsulting

Sec7

Provides server-side functionality to interact with or serve data related to Power BI and the Microsoft Certification Program (MCP).

Setup Requirements

  • ⚠️Requires Node.js and npm (or yarn) installed locally.
  • ⚠️Requires `npm install` to set up project dependencies.
  • ⚠️Likely requires environment variables or configuration for Power BI/MCP API credentials or database connections.
Verified SafeView Analysis
Cannot audit source code for specific vulnerabilities or 'eval' usage without access to files in `src` or `package.json` dependencies. As a server, it inherently exposes network ports, which requires proper security configuration for production deployment.
Updated: 2025-11-18GitHub
PreviousPage 133 of 760Next