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(8554)

0
0
Low Cost
stephan-chiorean icon

bluekit-mcp-server

by stephan-chiorean

Sec8

The BlueKit MCP server provides tools for AI-assisted development, enabling the creation and management of code generation kits, structured blueprints, expert agents, system diagrams, and project walkthroughs, along with project initialization and git clone management.

Setup Requirements

  • ⚠️Requires `git` command-line tool to be installed and available in the system's PATH for clone management features.
  • ⚠️The `better-sqlite3` dependency is a native Node.js module, which may require build tools (e.g., `build-essential` on Linux, Xcode on macOS) if prebuilt binaries are not available for the specific environment.
  • ⚠️Mermaid diagram validation functionality (`bluekit_diagram_generateDiagram`) spawns a separate `npx` process (`@rtuin/mcp-mermaid-validator@latest`), which requires an internet connection to fetch the package if not cached, and may incur a slight startup delay or compatibility issues with specific Node.js environments.
Verified SafeView Analysis
The server uses `execSync` for git operations (`git clone`, `git checkout`) in `CloneTools.ts` and spawns external processes via `npx` for Mermaid validation in `MermaidValidatorClient.ts`. While `gitUrl`s are derived from local repositories during registration, rather than direct user input, and `npx` targets a specific known package, these interactions with external processes and fetching external code (git repos) introduce inherent supply-chain and execution risks. File system operations are extensive but generally confined to the project or user home directory, with path normalization applied to mitigate directory traversal. No obvious `eval` or direct arbitrary user command injection vulnerabilities were found, nor hardcoded sensitive secrets.
Updated: 2025-12-24GitHub→
0
0
Medium Cost
plantoncloud icon

mcp-server-planton

by plantoncloud

Sec9

Enables AI agents to query and manage Planton Cloud resources using user permissions via the Model Context Protocol (MCP).

Setup Requirements

  • ⚠️Requires a Planton Cloud API Key, which must be obtained from the Planton Cloud Console and dictates user permissions.
  • ⚠️Developers must use Go 1.25+ for local development to avoid version mismatch issues with project dependencies.
  • ⚠️Requires access to Planton Cloud APIs (either the hosted `apis.planton.cloud:443` or a local instance `localhost:8080`).
Verified SafeView Analysis
The server implements robust per-user API key authentication, ensuring fine-grained authorization and audit trails. API keys are sourced from environment variables (for STDIO mode) or Authorization headers (for HTTP mode) and are not hardcoded. TLS is used for production gRPC endpoints. While a global API key storage workaround is used for HTTP mode due to a library limitation, it is well-documented and mitigated by the single-threaded nature of SSE connections per client, posing a low risk in typical usage. Overall, the project demonstrates strong security practices and clear documentation.
Updated: 2025-12-14GitHub→
0
0
Medium Cost
Linkly-HQ icon

mcp-server-linkly

by Linkly-HQ

Sec9

Manages URL shortening, link analytics, and custom domains for the Linkly platform through a Model Context Protocol (MCP) server.

Setup Requirements

  • ⚠️Requires Node.js runtime environment (npm/npx).
  • ⚠️A Linkly account is required to obtain API credentials.
  • ⚠️Mandatory environment variables: LINKLY_API_KEY and LINKLY_WORKSPACE_ID must be set for self-hosting.
Verified SafeView Analysis
The server's core functionality involves proxying requests to the Linkly API. It correctly uses environment variables (LINKLY_API_KEY, LINKLY_WORKSPACE_ID) for API authentication in the self-hosted `index.js` version. For the Cloudflare Worker version (`src/index.ts`), OAuth client credentials (LINKLY_CLIENT_ID, LINKLY_CLIENT_SECRET) are defined in `worker-configuration.d.ts`, but the runtime code accesses them via the `env` object, implying secure configuration as platform secrets rather than hardcoded values. No 'eval', code obfuscation, or obvious malicious patterns were found. The primary security risk lies in the secure handling and configuration of the required API keys/OAuth credentials in the deployment environment.
Updated: 2026-01-13GitHub→
0
0
High Cost
lkm1developer icon

mcp-servers-sse

by lkm1developer

Sec3

A scalable Express.js server that acts as an API gateway, hosting multiple Model Context Protocol (MCP) servers with real-time Server-Sent Events (SSE) support, route-based isolation, and JWT authentication for integrating various external APIs and tools.

Setup Requirements

  • ⚠️Requires API keys/tokens for potentially 20+ external services (e.g., Tavily, BuiltWith, NeverBounce, RocketReach, Apollo.io, FindyMail, Ocean.io, IcyPeas, HubSpot, SmartLead, Resend, Notion, Firecrawl, Hatch), many of which are paid services.
  • ⚠️Google Docs/Sheets require a path to a service account key file, and Gmail requires an OAuth2 access token, implying complex OAuth flow setup in addition to API keys.
  • ⚠️Requires `SUPABASE_URL` and `SUPABASE_SERVICE_ROLE_KEY`, indicating a dependency on a Supabase backend for persistent storage (e.g., sessions, configurations) which needs to be set up separately.
Review RequiredView Analysis
1. Hardcoded Secret: The 'EMAIL_API_KEY' in 'servers/meerkats/adapter.js' is hardcoded ('jhfgkjghtucvfg'), posing a critical security risk. 2. Unencrypted Network Communication: The 'EMAIL_SERVICE_URL' in 'servers/meerkats/adapter.js' uses plain HTTP ('http://34.46.80.154/api/email'), which allows eavesdropping and tampering with sensitive data. 3. DNS Rebinding Protection Disabled: 'enable_dns_rebinding_protection: false' in 'server.json' is a severe vulnerability that can allow attackers to bypass same-origin policies and attack internal network resources. 4. Sensitive Data in JWT: The server stores 'apiKey' or 'accessToken' directly within the JWT payload. If the 'JWT_SECRET' (an environment variable) is compromised, an attacker can forge tokens and gain full access to all integrated external APIs for any user. 5. Google API Credentials Handling: Google Sheets/Docs require a path to a service account key file, and Gmail requires an OAuth2 access token. The secure handling, storage, and refresh mechanisms for these credentials are critical and not fully detailed, posing a potential risk.
Updated: 2026-01-05GitHub→
0
0
Low Cost
v1nvn icon
Sec10

Provides a curated and categorized list of Model Context Protocol (MCP) server implementations, enabling AI models to securely interact with local and remote resources through standardized server integrations.

Verified SafeView Analysis
This repository serves as a curated list of Model Context Protocol (MCP) server implementations. The provided 'source code' is the README.md file, which is static documentation and does not pose direct security risks. However, users are strongly advised to exercise caution and perform thorough security audits on any *individual MCP server* they choose to deploy from this list, as those servers interact with various local and remote resources and may have different security postures.
Updated: 2026-01-19GitHub→
0
0
Low Cost
zmacks icon

tiny-mcp

by zmacks

Sec6

Facilitates real-time, peer-to-peer-like message exchange between connected WebSocket clients, acting as a simple message broker.

Setup Requirements

  • ⚠️Python 3.11+ required
Verified SafeView Analysis
The server lacks built-in authentication or authorization, meaning any client can connect and send messages. While it does not show direct code injection vulnerabilities (no 'eval' or similar), deploying it publicly without an external security layer would expose it to unrestricted access. Message content is not deeply validated beyond JSON parsing, relying on client-side sanity for message structures.
Updated: 2025-12-11GitHub→
0
0
High Cost
Amaculus icon
Sec9

Enables Claude to perform deep technical SEO analysis by querying crawl data, Google Search Console (GSC) metrics, and Google Analytics 4 (GA4) data from OnCrawl, facilitating crawl-over-crawl comparisons and identification of common SEO issues.

Setup Requirements

  • ⚠️Requires Python 3.11+.
  • ⚠️Requires an OnCrawl account with API access and a generated API token (with `projects:read` scope).
  • ⚠️The MCP server configuration in Claude Desktop/Code requires using an absolute file path for the `command` attribute (e.g., `C:\path\to\venv\Scripts\python.exe`).
  • ⚠️Claude Desktop/Code must be restarted after making configuration changes for the MCP server to be recognized.
Verified SafeView Analysis
The server securely handles API authentication via environment variables, avoiding hardcoded secrets. It utilizes `httpx` for reliable API communication and constructs OnCrawl Query Language (OQL) arguments as structured objects, minimizing the risk of injection vulnerabilities. There is no usage of `eval` or direct shell command execution with user-controlled input. Data parsing and manipulation are handled safely with Python's built-in `json` module. The server makes requests to a known external API (OnCrawl) and sets timeouts for requests.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
SDS-Manager icon

sds-mcp-server

by SDS-Manager

Sec6

This server provides a Model Context Protocol (MCP) interface to an SDS Manager backend, enabling an AI assistant to search, retrieve, upload, and manage Safety Data Sheets for regulatory compliance and organizational purposes.

Setup Requirements

  • ⚠️Requires a running Redis server for session management and temporary file handling.
  • ⚠️Requires a separate SDS Manager backend service to be running (defaults to http://localhost:8000/mcp).
  • ⚠️Requires an API key for the SDS Manager backend for authentication with its services.
Verified SafeView Analysis
The server directly processes user-uploaded Excel files via `pandas.read_excel`. This introduces a significant security risk, as specially crafted malicious Excel files could exploit vulnerabilities in the pandas library or underlying system. User API keys are stored in Redis in plain JSON, posing a risk if the Redis instance is compromised or not adequately secured. While file uploads for PDFs are proxied to the backend, the Excel file processing occurs directly on this server. There is no usage of `eval` or intentional obfuscation.
Updated: 2025-12-18GitHub→
0
0
Medium Cost
GalSened icon
Sec3

The WeSign MCP Server enables AI assistants to manage digital signature workflows, documents, templates, and user administration with the WeSign platform.

Setup Requirements

  • ⚠️Requires WeSign API credentials (email, password) and an API URL to be configured via environment variables.
  • ⚠️File operation tools (e.g., upload, download) expect absolute local file paths on the server's filesystem, which requires the AI assistant to manage server-side file access or provide Base64 content.
  • ⚠️For integration with remote AI platforms like ChatGPT, the server must be exposed publicly using tools like ngrok or cloud deployment.
Review RequiredView Analysis
The server has critical security vulnerabilities if exposed publicly. The `wesign_download_document` tool allows a user-controlled `savePath` parameter, enabling potential directory traversal and arbitrary file write if not rigorously sanitized by the AI. Similarly, `wesign_upload_document` and `wesign_create_document_collection` read local files via `filePath`, posing an information disclosure risk if an attacker can control this path. The `docker-compose.yml` and configuration guides contain real-looking example credentials ('nirk@comsign.co.il', 'Comsign1!'), which is a bad practice as users might deploy them directly. Debug logging in `wesign-client.ts` includes full request/response data, which could expose sensitive information (e.g., passwords in login requests) in logs during production if not properly redacted.
Updated: 2025-11-23GitHub→
0
0
Medium Cost
hightemp icon
Sec3

Enables AI agents to perform desktop automation by controlling the mouse, keyboard, screen, windows, and processes on a local computer system.

Setup Requirements

  • ⚠️Building from source requires Go 1.21+, a GCC compiler, and X11 development libraries (on Linux).
  • ⚠️Requires the `DISPLAY` environment variable to be set for all GUI operations on Linux, without which most tools will fail.
  • ⚠️The `npx` quick start command (npx -y go-computer-use-mcp-server -t stdio) requires Node.js 18+ and executes pre-compiled binaries downloaded from npm, requiring trust in the package publisher.
  • ⚠️The `screen_capture` tool can return very large base64 encoded PNG images (tens to hundreds of thousands of tokens), significantly increasing token costs for LLM clients if frequently used.
Review RequiredView Analysis
The `process_run` tool executes arbitrary shell commands provided as a string, posing a critical command injection vulnerability if the input is not fully trusted and sanitized by the client. All tools granting mouse, keyboard, screen, and window control are high-privilege operations. Deploying this server, particularly using `npx` (which downloads and executes pre-compiled binaries), demands complete trust in the source and robust client-side input validation. Binding the SSE transport to `0.0.0.0` or exposing it to untrusted networks creates a severe remote control risk.
Updated: 2026-01-17GitHub→
0
0
Medium Cost
hballington12 icon

mcp-oignon

by hballington12

Sec9

Facilitates exploration of academic literature and building citation networks using the OpenAlex API, primarily for AI agents to conduct research tasks and literature reviews.

Setup Requirements

  • ⚠️Requires an OpenAlex API email for optimal performance (increasing rate limits).
  • ⚠️Requires specific integration steps to add to an MCP-compatible client's configuration (e.g., Claude Desktop, Gemini CLI).
Verified SafeView Analysis
The server appropriately uses environment variables for API configuration (`OPENALEX_EMAIL`), avoiding hardcoded secrets. It defaults to safer `stdio` or `localhost` for HTTP transport, reducing external network attack surface. No direct use of dangerous functions like `eval()` or `subprocess.run(shell=True)` was observed. The use of `json.loads` is within the expected operational flow of an MCP server processing tool outputs.
Updated: 2026-01-18GitHub→
0
0
Medium Cost
taufiqur0991 icon

MCP-Server-CSharp

by taufiqur0991

Sec4

Provides a server application built with C# for general-purpose backend services.

Setup Requirements

  • ⚠️Requires .NET SDK (e.g., .NET 6 or 8) to build and run.
Review RequiredView Analysis
CRITICAL: No C# source code was provided for analysis. The 'SOURCE CODE' section only contained the readme.md content. Therefore, a comprehensive security audit for 'eval', obfuscation, hardcoded secrets, or malicious patterns could not be performed. The score reflects this inability to audit rather than specific findings.
Updated: 2025-12-02GitHub→
PreviousPage 659 of 713Next