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)

30
1
Medium Cost
jessaminesimple608 icon

scraper-mcp

by jessaminesimple608

Sec6

A web scraping MCP server that efficiently extracts content (HTML, Markdown, text, links) from web pages for downstream processing, particularly to reduce LLM token usage.

Setup Requirements

  • ⚠️Python 3.12 or higher required.
  • ⚠️Docker and Docker Compose are recommended for deployment.
  • ⚠️No built-in authentication for Admin API: Public exposure of admin endpoints (e.g., /api/config, /api/cache/clear) is a security risk; external authentication/access control must be implemented.
Review RequiredView Analysis
The server's administrative API endpoints (e.g., /api/config, /api/cache/clear, /api/stats) lack built-in authentication or authorization. This is a critical vulnerability as it allows any unauthenticated user to modify runtime configuration (e.g., enable proxies, disable SSL verification, change concurrency limits), clear the cache, or retrieve server statistics. While the code itself does not use 'eval' or contain hardcoded secrets, the exposed admin interface poses a significant risk if deployed publicly without external security measures.
Updated: 2026-01-19GitHub→
30
2
Medium Cost
domdomegg icon

google-drive-mcp

by domdomegg

Sec9

Facilitates AI systems to perform comprehensive file and folder management in Google Drive, including listing, searching, uploading, downloading, and managing comments and permissions, enabling workflows like content analysis, project scaffolding, and feedback synthesis.

Setup Requirements

  • ⚠️Requires setting up Google OAuth credentials (Client ID, Client Secret) in Google Cloud Console, including enabling the Google Drive API and configuring an authorized redirect URI.
  • ⚠️Requires providing Google OAuth credentials as environment variables: `GOOGLE_CLIENT_ID` and `GOOGLE_CLIENT_SECRET` for HTTP transport, OR `GOOGLE_ACCESS_TOKEN` for Stdio transport. The specific required variables depend on the `MCP_TRANSPORT` setting.
  • ⚠️The HTTP server runs on `http://localhost:3000` by default, requiring local access or configuration of `MCP_BASE_URL` if accessed remotely.
Verified SafeView Analysis
The server implements a robust OAuth proxy architecture to Google Drive API. It explicitly avoids holding tokens or state, relying on environment variables for Google OAuth credentials (`GOOGLE_CLIENT_ID`, `GOOGLE_CLIENT_SECRET`, `GOOGLE_ACCESS_TOKEN`). The `/authorize` and `/callback` endpoints securely handle redirects by encoding the client's `redirect_uri` within a base64url encoded `state` parameter, mitigating open redirect vulnerabilities. Token validation is performed using Google's `tokeninfo` endpoint and a cache, improving efficiency and preventing processing requests with expired tokens. No `eval`, code obfuscation, or obvious malicious patterns were found in the provided source. The broad `drive` scope is a user configuration choice rather than an inherent server vulnerability.
Updated: 2026-01-07GitHub→
30
1
Low Cost
kdoooh000h icon
Sec7

Provides a token-optimized API server for integrating Google Gemini CLI with applications like Claude, focusing on reducing tool schema overhead for cost efficiency.

Setup Requirements

  • ⚠️Requires Google Gemini CLI to be pre-installed and configured (via `gemini auth login` and `GOOGLE_API_KEY` env var).
  • ⚠️Enables the `--yolo` flag for Gemini CLI, which grants auto-approval for Gemini's own tool execution (e.g., `write_file`). Users should be aware of the security implications of this trust delegation to the LLM.
  • ⚠️The test files (`src/__tests__/*.test.ts`) contain inconsistencies, still referencing 'codex' and 'gpt-5-codex' despite the main application logic (`src/tools/definitions.ts`, `src/tools/handlers.ts`, `package.json`) being adapted for 'gemini'. This indicates potentially outdated tests or an incomplete transition from a 'codex-mcp-server' base, which could affect confidence in full test coverage for the Gemini implementation.
Verified SafeView Analysis
The server correctly uses `child_process.execFile` with `shell: false` in `src/utils/command.ts`, which mitigates direct shell injection vulnerabilities. User-provided prompts are passed as arguments to the `gemini` CLI. A critical consideration is the `--yolo` flag explicitly pushed to `cmdArgs` in `src/tools/handlers.ts`. This flag 'enables auto-approval for tool execution (write_file, etc.)' within the Gemini CLI. While this is a feature of the underlying CLI to allow tool use, it delegates significant trust to the Gemini LLM's ability to safely interpret and execute commands via its tools, potentially including file system operations or arbitrary command execution, if the LLM were to be jailbroken or misused. This is an inherent risk of enabling powerful AI tool-use capabilities, rather than a direct vulnerability in the server's parsing or command construction. No hardcoded secrets or obfuscation were found.
Updated: 2026-01-13GitHub→
30
1
Medium Cost
mattaspira icon
Sec8

The Google Docs MCP server enables large language models to interact with Google Docs for document creation, reading, updating, formatting, and structural manipulation.

Setup Requirements

  • ⚠️Requires manual setup of a Google Cloud Project to obtain OAuth 2.0 client credentials (client_id, client_secret, redirect_uris), which must be saved as a `credentials.json` file in the project root.
  • ⚠️Initial authentication requires user interaction to open a URL in a web browser and grant permissions to their Google Account.
  • ⚠️Integration tests may require specific credentials and could hit Google API quotas or rate limits, as noted in the project's README.
Verified SafeView Analysis
The server uses Google's OAuth2 for authentication, storing tokens and reading client credentials from a local `credentials.json` file. Input validation is applied to document IDs, indices, text content, and numerical ranges, with search queries explicitly sanitized to prevent injection vulnerabilities. The implementation of `find_and_replace` leverages the Google Docs API's `replaceAllText` for secure mass operations. No direct `eval` or blatant dynamic code execution points were identified. The OAuth callback server runs locally, minimizing network exposure. The primary security consideration is ensuring `credentials.json` is protected and not committed to source control.
Updated: 2026-01-19GitHub→
30
1
Medium Cost
jcr82 icon
Sec9

Integrates Bruno CLI with Model Context Protocol to execute API tests, validate collections, and generate reports via AI tools for automated API testing workflows.

Setup Requirements

  • ⚠️Requires Node.js 20 or higher.
  • ⚠️Bruno CLI must be installed and accessible (typically via `npm install` within the project, or globally).
  • ⚠️Requires local Bruno collections (.bru files) for API testing.
  • ⚠️An MCP client (e.g., Claude Desktop) needs to be configured with the absolute path to the server's `dist/index.js` file.
  • ⚠️If security.allowedPaths is configured in `bruno-mcp.config.json`, only collections within those specified directories can be accessed.
Verified SafeView Analysis
The server includes a dedicated security module that provides path validation (preventing directory traversal), input sanitization (against command injection), and secret masking in logs and error messages. All tool parameters are validated before execution. While the underlying Bruno CLI performs network calls, this server actively mitigates risks by sanitizing arguments. Proper configuration of 'allowedPaths' in `bruno-mcp.config.json` is crucial for restricting access to Bruno collections. No 'eval' or obfuscation found.
Updated: 2025-11-30GitHub→
30
1
Low Cost
kecbigmt icon

mm

by kecbigmt

Sec9

A command-line interface (CLI) tool for personal knowledge management, integrating GTD, Bullet Journal, and Zettelkasten methods to manage notes, tasks, and events as Git-friendly Markdown files.

Setup Requirements

  • ⚠️Requires Deno runtime (v2.x or later) to be installed.
  • ⚠️Requires Git for version control and synchronization features.
  • ⚠️Designed primarily for macOS or Linux environments.
Verified SafeView Analysis
The application is a local CLI tool written in Deno. It heavily uses `Deno.Command` for Git operations (clone, push, pull, diff) and to launch user-configured external editors (`$EDITOR`) and pagers (`$PAGER`). While `Deno.Command` allows arbitrary command execution, its usage is confined to expected CLI functionalities, interacting with user-controlled Git repositories and user-configured tools. No obvious hardcoded secrets or malicious network patterns were found beyond legitimate Git remote interactions. The security relies on Deno's sandboxing (`--allow-read --allow-write --allow-env --allow-run`) and the user's caution with external tool configurations.
Updated: 2026-01-15GitHub→
30
1
High Cost
praneethravuri icon

pitstop

by praneethravuri

Sec9

Provides comprehensive Formula 1 data including historical statistics, real-time telemetry, standings, schedules, and news via a Model Context Protocol server.

Setup Requirements

  • ⚠️Requires Python 3.13+
  • ⚠️For local deployment, requires replacing '/absolute/path/to/pitstop' with the actual repository path in client configuration.
  • ⚠️The 'get_telemetry_data' tool can return a very large number of data points, potentially leading to high token usage if not carefully filtered by the client.
Verified SafeView Analysis
The server uses standard, well-vetted libraries for network operations (httpx, feedparser) and data processing (fastf1, pandas, pydantic). Configuration is handled via environment variables and .env files, preventing hardcoded secrets. No 'eval' or other directly dangerous functions were found. The use of external APIs (OpenF1, Ergast, RSS feeds) is properly encapsulated.
Updated: 2026-01-18GitHub→
30
1
Medium Cost
mcp-z icon

server-pdf

by mcp-z

Sec8

Generate PDFs from text or layouts, render PDF pages as images, and measure text before layout, with specialized support for JSON Resume format.

Setup Requirements

  • ⚠️Emoji rendering requires `NotoColorEmoji.ttf` to be present; it's downloaded during `postinstall`. If the download fails, emojis will be skipped in PDFs.
  • ⚠️The `pdf-image` tool uses `pdf-to-png-converter`, which internally relies on native PDF rendering libraries (like Poppler or Ghostscript). While it bundles binaries, platform-specific issues or missing system dependencies can occur.
  • ⚠️Custom font loading via URL requires active network access. If the URL is unreachable or the font download fails, it falls back to a default font (Helvetica).
Verified SafeView Analysis
The server involves filesystem operations (e.g., `pdfPath` in `pdf-image`, `writeFile` for output) and network requests (e.g., `fetch` for custom fonts). The `pdf-to-png-converter` dependency might rely on native system libraries, which could pose a risk if not properly isolated or if vulnerabilities exist in those libraries. `eval` is used internally for dual ESM/CJS loading, which is generally acceptable for bootstrapping. No hardcoded secrets were identified.
Updated: 2026-01-16GitHub→
30
1
Low Cost
lornest icon

whoop-mcp

by lornest

Sec9

Provides conversational access to WHOOP fitness and recovery data through an MCP client like Claude.

Setup Requirements

  • ⚠️Requires Python 3.12+
  • ⚠️Requires manual creation and configuration of a WHOOP OAuth application on their developer dashboard, including setting a redirect URI to `http://localhost:8080/callback`.
  • ⚠️The `bootstrap.py` script starts a local web server (http://localhost:8080) for OAuth callback, which might require firewall adjustments if blocked.
Verified SafeView Analysis
The server employs robust security practices. OAuth 2.0/2.1 compliance is handled by the well-tested `authlib` library. Tokens are stored securely using OS-native keychain (macOS Keychain, Windows Credential Locker, GNOME Keyring/KWallet) or fall back to an encrypted file with strong symmetric encryption (`cryptography.fernet`) and strict file permissions. CSRF protection is implemented in the OAuth bootstrap flow. Client secrets are stored securely and never exposed in runtime environment variables. API requests are centrally handled with comprehensive error handling for authentication, rate limits, and network issues. No 'eval' or other obviously dangerous patterns were found.
Updated: 2025-12-14GitHub→
30
1
Medium Cost
hmmroger icon
Sec9

Enables AI assistants to manage Microsoft Outlook calendars and emails via the Microsoft Graph API.

Setup Requirements

  • ⚠️Requires Node.js 20.19.0 or higher.
  • ⚠️Requires manual Azure AD Application registration with specific `Calendars.ReadWrite`, `Mail.Read`, `Mail.Send`, `User.Read` permissions.
  • ⚠️Requires a one-time device code flow authentication via browser to set up initially.
Verified SafeView Analysis
The server securely handles authentication tokens using `@azure/identity` with local persistence. User-provided content for emails/events is sanitized via `DOMPurify` when converted from Markdown to HTML before being sent to Microsoft Graph, mitigating potential XSS. The client ID is not hardcoded and the README provides strong warnings and best practices for creating a dedicated Azure AD application. No 'eval' or malicious obfuscation patterns were found. Communication with the MCP client is over standard I/O (stdio), limiting direct network exposure.
Updated: 2026-01-19GitHub→
30
1
High Cost
groupdocs-parser-cloud icon

groupdocs-parser-cloud-mcp

by groupdocs-parser-cloud

Sec8

Provides an MCP server that wraps the GroupDocs.Parser Cloud API to enable AI agents to extract text, images, and barcodes from various document formats and manage cloud storage.

Setup Requirements

  • ⚠️Requires GroupDocs Cloud API credentials (CLIENT_ID, CLIENT_SECRET), which may imply a paid service.
  • ⚠️Requires Python 3.10+.
Verified SafeView Analysis
The `file_upload_local` and `file_download_local` tools allow agents to specify local filesystem paths for uploads/downloads. While useful for local agent execution, this could introduce arbitrary file read/write vulnerabilities if the MCP server is exposed to untrusted external input or deployed in an insecure network configuration without proper access controls, as `local_path` is directly used. Secrets are handled via environment variables.
Updated: 2025-12-14GitHub→
30
1
Medium Cost
rezashahnazar icon

digikala-mcp-server

by rezashahnazar

Sec9

Facilitates intelligent product discovery, search, recommendations, and detailed information retrieval on Digikala, a prominent e-commerce platform.

Setup Requirements

  • ⚠️Requires Python 3.14+ (as specified in pyproject.toml, though Python 3.10+ is mentioned in documentation, the pyproject.toml is definitive and implies a pre-release Python version or a typo)
  • ⚠️Requires `uv` package manager for dependency management and execution
Verified SafeView Analysis
The server primarily makes HTTP GET requests to public Digikala APIs. No hardcoded sensitive API keys or credentials are found within the provided source code. HTTP timeouts are configured (30 seconds) to prevent prolonged external connections. There are no 'eval' statements, obfuscation, or direct file system/shell interactions observed. Standard network risks associated with interacting with external APIs apply, but no specific vulnerabilities are apparent.
Updated: 2025-12-03GitHub→
PreviousPage 212 of 760Next