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
Medium Cost
chrisguillory icon

granola-mcp

by chrisguillory

Sec7

Provides programmatic access to Granola meeting notes, transcripts, and metadata for AI assistants and automation.

Setup Requirements

  • ⚠️Requires Granola desktop application installed and authenticated on the same machine.
  • ⚠️Requires `uv` Python package manager to be installed for execution.
  • ⚠️Requires Python 3.11 or higher.
  • ⚠️Authentication file location (`~/Library/Application Support/Granola/supabase.json`) is specific to macOS, limiting cross-platform compatibility without modification.
Verified SafeView Analysis
The server accesses a WorkOS OAuth token from a local Granola app support file (~/Library/Application Support/Granola/supabase.json). This design, while intended for a local MCP, means the server requires local access to sensitive credentials. If the local machine or the MCP server itself is compromised, the Granola account linked to the token could be at risk. The server uses Pydantic for strict API response validation, `httpx` with timeouts, and temporary directories for downloads, which are good practices. There's a minor theoretical risk of path traversal if a crafted 'filename' parameter in download tools isn't fully sanitized by `pathlib.Path`, but this is less severe for a locally run MCP.
Updated: 2026-01-08GitHub→
0
0
Medium Cost
hnizdiljan icon

Cookidoo-MCP-Server

by hnizdiljan

Sec2

Provides a RESTful API server to manage custom recipes and collections on the Cookidoo platform for Thermomix devices, allowing control via AI assistants like Claude in Cursor.

Setup Requirements

  • ⚠️Requires .NET 8 SDK to run the backend server.
  • ⚠️Requires Node.js 18+ for the MCP client.
  • ⚠️Requires a valid Cookidoo account (with subscription recommended for full features).
  • ⚠️Requires a Cursor editor for AI assistant integration.
Review RequiredView Analysis
CRITICAL: The `test-real-cookidoo.js` file contains hardcoded real user credentials (email and password) which are exposed in the source code. Additionally, the OAuth2 client ID and secret for Cookidoo (`kupferwerk-client-nwot` and `Ls50ON1woySqs1dCdJge`) are hardcoded in the `OAUTH2_IMPLEMENTATION.md` and used by the .NET backend, which is a significant vulnerability. A development JWT secret key is also hardcoded. While the server aims not to store user credentials permanently, these hardcoded values represent severe security flaws.
Updated: 2025-11-22GitHub→
0
0
Medium Cost
imjac0b icon
Sec9

Provides AI assistants with programmatic access to Iconify's vast collection of vector icons for various frameworks and design tools.

Setup Requirements

  • ⚠️Requires Bun runtime for local development and build processes.
  • ⚠️Requires Node.js >= 18.0.0.
Verified SafeView Analysis
The server primarily acts as a proxy to the official Iconify API. It does not perform any dynamic code execution (e.g., eval), nor does it store or handle sensitive user data. All data returned is a direct stringification of the Iconify API response. The main security considerations would be the reliability and security of the upstream Iconify API itself, but the server implementation introduces no apparent direct vulnerabilities.
Updated: 2025-11-22GitHub→
0
0
Medium Cost
kalleeh icon
Sec9

Generate and edit images using Amazon Bedrock models like Nova Canvas, Stable Diffusion 3.5 Large, and various Stability AI services through a Model Context Protocol (MCP) server.

Setup Requirements

  • ⚠️Requires `uv` package manager for Python environment setup and installation, not standard `pip`.
  • ⚠️Requires an AWS account with Amazon Bedrock enabled and access specifically requested for the Nova Canvas, Stable Diffusion 3.5 Large, and various Stability AI models in the target AWS Region.
  • ⚠️Requires AWS IAM permissions (`bedrock:InvokeModel`) for all specific image generation models you intend to use.
  • ⚠️Model availability varies by AWS Region; users must select a region where their desired models are supported.
Verified SafeView Analysis
The server uses `boto3` for AWS API interactions, which handles authentication securely via AWS profiles or environment variables. Image processing and mask creation are done using the `Pillow` library, and base64 encoding/decoding is standard. File system operations for saving/reading images (e.g., `os.makedirs`, `os.path.exists`) are constrained within a `workspace_dir` provided by the MCP client, mitigating broad file system risks. No direct `eval` or other highly dangerous patterns were observed. The primary security consideration relies on the trustworthiness of the MCP client to provide safe `workspace_dir` and input file paths.
Updated: 2025-12-11GitHub→
0
0
Medium Cost
HDieter6789 icon
Sec3

Provides a Micro-Context Protocol (MCP) server and HTTP API for automating Power BI operations, including REST API interactions and local PBIX/PBIT file transformations.

Setup Requirements

  • ⚠️Requires Azure AD application registration and Service Principal setup with appropriate Power BI permissions (for 'sp' authentication mode).
  • ⚠️Requires the 'pbi-tools' command-line utility to be installed and accessible on the server's PATH or specified via PBI_TOOLS_PATH.
  • ⚠️Requires a secret API_KEY environment variable for authenticating API requests.
Review RequiredView Analysis
CRITICAL: The server uses 'child_process.spawn' with 'shell: true' to execute 'pbi-tools'. User-controlled inputs for file paths (e.g., 'filePath', 'outDir', 'projectDir', 'outPath') are passed directly to these commands. This creates a severe command injection vulnerability if a malicious path containing shell commands is provided, potentially allowing arbitrary code execution on the host system. Additionally, the default CORS_ORIGINS is '*' which is risky for public deployments, and API key authentication uses a single shared key, which requires careful management.
Updated: 2025-12-11GitHub→
0
0
High Cost
tinatuazon icon
Sec9

Provides AI-powered query capabilities for a professional digital twin profile via the Model Context Protocol (MCP) for integration with AI tools like GitHub Copilot, allowing interactive access to background, skills, and career goals.

Setup Requirements

  • ⚠️Requires Groq API Key (Paid service, though often has a free trial)
  • ⚠️Requires Upstash Vector Database (Paid service, offers a free tier)
  • ⚠️Requires Node.js runtime environment (version >=18 for mcp-server, >=20 for Next.js app)
  • ⚠️Depends on 'data/digitaltwin.json' for profile content; full functionality relies on this file being present and correctly structured.
Verified SafeView Analysis
The server explicitly relies on environment variables for API keys (Groq, Upstash), preventing hardcoding of secrets. Input validation and truncation are implemented before feeding user queries to the LLM. LLM system prompts include strict instructions to limit responses to provided context, mitigating prompt injection risks. The `profile-loader.ts` reads from a local JSON, which is safe as it's not user-controlled. No `eval` or direct dynamic code execution is apparent. Network requests to external AI/vector services include timeouts and retries, enhancing stability. Overall, good security practices are in place for this type of application.
Updated: 2025-12-11GitHub→
0
0
Medium Cost
pyaekyaw-dev icon

fattureincloud-mcp

by pyaekyaw-dev

Sec8

Manages Italian electronic invoices by integrating with the Fatture in Cloud API, providing tools for creating, sending, tracking, and analyzing invoices through a conversational interface.

Setup Requirements

  • ⚠️Requires a Fatture in Cloud account and API credentials (FIC_ACCESS_TOKEN, FIC_COMPANY_ID), which may involve a paid service.
  • ⚠️Requires Python 3.10 or later.
  • ⚠️Requires an active internet connection for Fatture in Cloud API integration.
Verified SafeView Analysis
The server uses environment variables (`os.getenv`) for sensitive information like API access tokens, which is a good practice. It does not contain direct usage of `eval` or obvious obfuscation. Input validation is largely deferred to the `fattureincloud-python-sdk`. A generic `except` block for all tool calls could mask specific errors but doesn't introduce direct security vulnerabilities from the server side. It communicates via standard I/O (stdio), which is generally safe when executed locally or in a trusted environment. Overall, the code appears to be a straightforward wrapper around a well-known API.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
nhajje icon
Sec9

Provides Claude with access to Hajjefy time tracking analytics and insights for comprehensive overview, user, team, billable, customer, capacity, daily hours, and TAM analysis.

Setup Requirements

  • ⚠️Requires a Hajjefy API Token (implies a paid Hajjefy service subscription).
  • ⚠️Node.js version 18+ is recommended for optimal compatibility.
  • ⚠️Requires careful configuration in Claude Desktop using absolute paths to the built `index.js` file, as highlighted in the installation guide.
Verified SafeView Analysis
The server's source code shows good security practices. It loads the `HAJJEFY_API_TOKEN` from environment variables, preventing hardcoding. The `axios` client includes error interceptors for authentication and access issues. Sensitive Salesforce credentials are noted as being required for the 'main Tempo Dashboard' (presumably the Hajjefy backend), and the MCP server accesses Salesforce data via Hajjefy's Netlify functions (`/.netlify/functions/salesforce-account`), which abstracts direct credential handling from the local server. No `eval` or intentional obfuscation was found. Test scripts include placeholder tokens, but these are clearly separated from the main application logic.
Updated: 2026-01-05GitHub→
0
0
Medium Cost
cloudsteak icon

dora-agents

by cloudsteak

Sec1

Acts as a central server (MCP) for managing and orchestrating internal agent microservices.

Setup Requirements

  • ⚠️Docker required
  • ⚠️Python environment setup required
Review RequiredView Analysis
Source code for security analysis (beyond README.md) was not provided. Thus, it's impossible to verify the absence of 'eval', obfuscation, network risks, hardcoded secrets, or malicious patterns. The score reflects this complete lack of visibility.
Updated: 2025-12-03GitHub→
0
0
Medium Cost
Abhuday2709 icon

MCP-SERVER

by Abhuday2709

Sec8

An AI chatbot server integrating Google Gemini with Gmail via Model Context Protocol for intelligent email interaction.

Setup Requirements

  • ⚠️Requires Google Cloud Project setup for OAuth2 credentials and Gmail API enablement.
  • ⚠️Requires a running Redis instance (local or cloud like Upstash).
  • ⚠️Requires a Google Gemini API key.
Verified SafeView Analysis
The server follows good security practices by using environment variables for sensitive data, HTTP-only cookies for JWTs, and Redis for storing OAuth tokens. The MCP client spawns a fixed `node` process, which is safe. CORS is configured correctly to prevent cross-site scripting. The AI prompt engineering attempts to obtain structured JSON, with error handling for parsing. However, explicit Google refresh token handling is not fully detailed in the provided code snippets (though tokens are stored), and rate limiting, while recommended in the README, is not implemented in the main `app.js`.
Updated: 2025-11-23GitHub→
0
0
Medium Cost
peacockery-studio icon

outlook-mcp

by peacockery-studio

Sec8

Connects Claude with Microsoft Outlook to manage emails and calendar events via the Microsoft Graph API.

Setup Requirements

  • ⚠️Requires Azure App Registration: Users must register an application in the Azure Portal, configure permissions (Mail.Read, Mail.Send, Calendars.ReadWrite, Contacts.Read), and obtain client ID/secret.
  • ⚠️Node.js version: Requires Node.js 18.0.0 or higher.
  • ⚠️Separate Authentication Server: The OAuth authentication process requires running a separate local server (`npm run auth-server`) on port 3333 to handle authentication callbacks from Microsoft. This server must be active during the initial authentication step.
Verified SafeView Analysis
The server correctly uses environment variables (MS_CLIENT_ID, MS_CLIENT_SECRET, OUTLOOK_CLIENT_ID, OUTLOOK_CLIENT_SECRET) for sensitive credentials, avoiding hardcoded secrets in the main application logic. Tokens are stored locally in the user's home directory (`~/.outlook-mcp-tokens.json`), which is a common practice for local applications. The OAuth authentication flow uses a localhost callback, mitigating some network risks. However, utility scripts (`find-folder-ids.js`, `move-github-emails.js`, `create-notifications-rule.js`) contain hardcoded folder IDs, which, while not a direct server vulnerability, is poor practice and could lead to misconfiguration or data targeting issues if those scripts are reused blindly. The `outlook-auth-server.js` uses a simple `Date.now().toString()` for the OAuth `state` parameter, and the `oauth-server.js` includes a mandatory check for the *presence* of the state parameter but explicitly notes that full state *validation* (comparing the received state value to a stored one for CSRF protection) is the responsibility of the integrating application, as this module does not manage sessions. This means the integrating application needs to correctly implement CSRF protection. Debug logs using `console.error` in `auth/token-manager.js` may expose token details if not handled carefully in production.
Updated: 2025-12-05GitHub→
0
0
Low Cost
nikydobrev icon
Sec9

Specialized Model Context Protocol (MCP) server for Azure DevOps, providing multi-organization support and LLM-optimized responses.

Setup Requirements

  • ⚠️Requires Azure DevOps Personal Access Tokens (PATs) with appropriate permissions (Code Read, Build Read & Execute, Project and Team Read) for each organization.
  • ⚠️Requires a `config.json` file in the root directory, mapping Azure DevOps organization names to their respective PATs.
  • ⚠️Requires Node.js v18 or higher for local execution, or Docker for containerized deployment (which then requires building the Docker image).
Verified SafeView Analysis
Personal Access Tokens (PATs) are externalized to a `config.json` file, which must be secured by the user. The server itself does not expose PATs in its output or allow dynamic code execution from untrusted input. Interactions with Azure DevOps APIs are handled via a well-established SDK. The `pipelines_update_build_stage` tool is explicitly noted as not fully implemented, reducing potential risks from incomplete write operations.
Updated: 2025-12-11GitHub→
PreviousPage 493 of 760Next