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
Low Cost
eagleisbatman icon
Sec1

External service for managing user profiles and conversation-based memory, including LLM-powered fact extraction from chat.

Setup Requirements

  • ⚠️Requires PostgreSQL database with `DATABASE_URL` environment variable.
  • ⚠️Requires OpenAI API Key (Paid) for LLM-based fact extraction.
  • ⚠️Requires Node.js version 18 or higher.
Review RequiredView Analysis
CRITICAL SQL INJECTION: The `update_profile` endpoint dynamically constructs the SQL `SET` clause by interpolating field keys (`${key}`) directly from `req.body.fields` into the SQL string. This allows for SQL injection if a malicious user provides crafted keys in the `fields` object, potentially leading to unauthorized data manipulation or deletion. INFORMATION LEAKAGE: Error messages expose internal server details, which could aid attackers. The default CORS origin `*` is broad and should be tightened in production deployments to specific origins to prevent unintended cross-origin access, though it might be intended for internal use as an MCP server.
Updated: 2025-11-28GitHub→
0
0
Low Cost
jarecsni icon

dep-context-mcp

by jarecsni

Sec9

Provides AI coding assistants with API context about project dependencies by reading directly from node_modules, enabling semantic search and local-first operations.

Setup Requirements

  • ⚠️Requires Node.js >= 20.0.0.
  • ⚠️Semantic search requires either an OpenAI API Key (paid service) for the 'openai' embedding provider, or a locally running Ollama server for the 'ollama' provider.
  • ⚠️GitLab source enrichment (an optional tool) requires a GitLab Personal Access Token.
  • ⚠️The first-time use of semantic search (or after dependencies change) will trigger a one-time indexing process which can take several seconds to minutes depending on the number of packages, and may require user confirmation.
Verified SafeView Analysis
The server prioritizes a 'local-first' architecture, reading directly from `node_modules` without external network calls for core functionality. Optional features like vector search (with OpenAI) or GitLab source enrichment are clearly documented as requiring external network access and environment variables for sensitive API keys/tokens. The use of `cross-spawn` (via `@modelcontextprotocol/sdk`) is present, but it's for managing dependencies (e.g., potentially triggering `npm install` for internal tasks) which is an expected capability for such a server. No `eval` or obvious malicious patterns are present in the provided source code. User input is not directly passed to shell commands without sanitization in the analyzed code.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
CrowdStrike icon

aidr-mcp-proxy

by CrowdStrike

Sec9

Protect Model Context Protocol (MCP) server communications by proxying all I/O through the CrowdStrike AIDR service for threat detection, prompt injection blocking, and content filtering.

Setup Requirements

  • ⚠️Requires Node.js v22.15.0 or greater.
  • ⚠️Requires a CrowdStrike AIDR API token, which must be set via the `CS_AIDR_TOKEN` environment variable.
  • ⚠️Requires the CrowdStrike AIDR base URL template, which must be set via the `CS_AIDR_BASE_URL_TEMPLATE` environment variable.
Verified SafeView Analysis
The proxy is designed to enhance security by routing all Model Context Protocol (MCP) server inputs and outputs through the CrowdStrike AIDR service. It correctly enforces the use of environment variables for API tokens (`CS_AIDR_TOKEN`) and base URLs (`CS_AIDR_BASE_URL_TEMPLATE`). Input and output content are serialized to JSON for analysis by the AIDR service, with error handling in place for parsing transformed output. No 'eval' calls, code obfuscation, or immediately identifiable malicious patterns were found within the provided source code. The overall security effectiveness is highly dependent on the underlying CrowdStrike AIDR service.
Updated: 2026-01-13GitHub→
0
0
Low Cost
Sec9

This server acts as a Model Context Protocol (MCP) server, exposing user and order data as tools for integration with external services like Intercom.

Setup Requirements

  • ⚠️Requires Node.js v18 or higher.
Verified SafeView Analysis
The code does not contain 'eval' or any obviously malicious patterns. It uses Zod for schema validation which is good. It relies on the `@modelcontextprotocol/sdk` which is assumed to be safe. No hardcoded secrets are visible. Network risks are minimal as it's designed to be exposed via a proxy like ngrok for external access.
Updated: 2025-11-20GitHub→
0
0
Medium Cost
Afnankazi icon

mcp_server_test

by Afnankazi

Sec5

A test server application to simulate or provide a backend for a Master Control Program or similar distributed system, inferred from the repository name.

Review RequiredView Analysis
Source code was not provided for analysis. Therefore, a comprehensive security audit for specific risks like 'eval', hardcoded secrets, network vulnerabilities, or malicious patterns is impossible. The score reflects an unknown security posture rather than a verified safe or unsafe one.
Updated: 2025-12-03GitHub→
0
0
Medium Cost
Jammy2005 icon
Sec7

A comprehensive MCP server designed to wrap and expose various Product REST APIs, offering tools for product management, supplier listing, product details, search, inventory updates, order placement, customer feedback, shopping cart management, and file uploads.

Setup Requirements

  • ⚠️Requires an external Product REST API server to be running and accessible, either at the hardcoded default `http://192.168.210.100:6051` or an address specified via the `PRODUCT_API_BASE_URL` environment variable.
  • ⚠️Depends on the `FastMCP` framework (imported as `mcp.server.fastmcp`) being installed and available in the Python environment.
  • ⚠️File paths provided for `upload_product_files` can originate from 'LLM virtual paths' or local absolute paths, implying specific environmental setup or client capabilities for file access.
Verified SafeView Analysis
The server acts as a thin wrapper/proxy for an upstream REST API. While it leverages `httpx` with `raise_for_status()` for robust HTTP error handling and manages temporary files securely for uploads, it lacks explicit input validation for complex JSON payloads (e.g., `product_dict`, `order_items_list`). This delegates input validation entirely to the upstream API. If the upstream API lacks robust validation, this server could become an unwitting conduit for vulnerabilities. The default `PRODUCT_API_BASE_URL` is an internal IP, suggesting an internal deployment where direct exposure to the internet would be a security misconfiguration. The `_safe_json` utility may mask underlying JSON parsing errors from the upstream service.
Updated: 2025-11-26GitHub→
0
0
Medium Cost
rubyimogenjohnson icon

mcp-server-email

by rubyimogenjohnson

Sec8

Automates Freedom of Information (FOI) request handling by integrating with Gmail and Claude, including drafting acknowledgment receipts and facilitating team allocation.

Setup Requirements

  • ⚠️Python 3.10+ is required, though the README suggests 3.14+.
  • ⚠️Requires manual setup of a Google Cloud Project with Gmail API enabled and OAuth 2.0 credentials.
  • ⚠️Requires the Claude Desktop application for integration and operation.
  • ⚠️Requires three specific CSV files (`camden_foi_responses.csv`, `foi_team_mapping.csv`, `foi_team_contacts.csv`) to be placed in the project root/src directory.
Verified SafeView Analysis
The server uses Google OAuth 2.0 for authentication with Gmail API, storing tokens locally. `credentials.json` is explicitly recommended not to be committed to version control. No 'eval' or direct code obfuscation detected. CSV files are loaded as internal knowledge bases, assuming trusted data sources. The primary security consideration for LLM integration is prompt injection, which is an inherent risk when sending user-provided email content to an AI model, though the server itself does not execute AI outputs. Logs may contain sensitive email content.
Updated: 2025-12-12GitHub→
0
0
High Cost
sleekcms icon
Sec3

A chatbot system that integrates with SleekCMS to provide AI-powered insights about website content and manage conversation context using the Model Context Protocol (MCP).

Setup Requirements

  • ⚠️Requires Anthropic API Key (Paid, or free evaluation for `claude-3-haiku-20240307` model).
  • ⚠️Requires a valid SleekCMS Pub Token.
  • ⚠️Frontend is a static HTML file; requires a separate local HTTP server (e.g., Python's `http.server` or `npx http-server`) for optimal functionality rather than simply opening the file in a browser.
Review RequiredView Analysis
The server has a critical Server-Side Request Forgery (SSRF) vulnerability. The `pubToken` input in the `/api/connect` endpoint can accept a full URL (`token.startsWith('http')`). If a URL is provided, the backend will attempt to `fetch` data from that arbitrary URL, making it possible for an attacker to probe internal networks, access cloud metadata services, or initiate requests to other unintended endpoints from the server's perspective. Additionally, the default CORS configuration (`app.use(cors())`) allows all origins, which is acceptable for local development but constitutes a security risk in a production environment without explicit origin restrictions.
Updated: 2025-12-02GitHub→
0
0
Low Cost
frnnk icon
Sec7

An MCP (Model Context Protocol) server template providing OAuth 2.0-protected Google Calendar tools to agentic clients.

Setup Requirements

  • ⚠️Requires Python 3.13
  • ⚠️Requires a Google Cloud Project and OAuth 2.0 Client ID/Secret JSON file (`client_secret.json`)
  • ⚠️Requires `uv` for dependency management and running the server
Verified SafeView Analysis
The server's design for local development uses unencrypted file-based token storage (`GOOGLE_LOCAL_TOKEN_PATH`) and a hardcoded 'localtest' principal_id, meaning all operations share the same authentication context. This is acceptable for single-user local testing as stated in the documentation, but a critical security flaw for multi-user or production deployments. The OAuth callback handler in `google_provider.py` performs an `http` to `https` URI replacement which is a workaround for `oauthlib`'s strictness; production environments should ensure proper HTTPS termination and redirect URIs. No obvious 'eval' or malicious obfuscation found.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
YeiyoNathnael icon

LichessMCP

by YeiyoNathnael

Sec1

A server component designed to interact with the Lichess platform, likely for managing custom clients or bots via a specific protocol.

Review RequiredView Analysis
Source code was not provided for analysis. Therefore, a comprehensive security audit could not be performed. This project may contain unknown vulnerabilities, hardcoded secrets, or malicious patterns. It is highly unsafe to run any code without reviewing its source. The low score reflects the complete lack of visibility into the code's security posture.
Updated: 2026-01-16GitHub→
0
0
Medium Cost
flowgrammer420 icon

otc-mcp-server

by flowgrammer420

Sec9

Manages Open Telekom Cloud (OTC) infrastructure, specifically Elastic Cloud Servers (ECS), via AI agents like Claude Desktop.

Setup Requirements

  • ⚠️Requires an Open Telekom Cloud (OTC) account with AK/SK credentials and a Project ID.
  • ⚠️Node.js version 18 or higher is required.
  • ⚠️Environment variables (OTC_ACCESS_KEY, OTC_SECRET_KEY, OTC_PROJECT_ID, OTC_REGION) must be correctly configured.
  • ⚠️Requires manual configuration in Claude Desktop's `claude_desktop_config.json` for AI integration.
Verified SafeView Analysis
The server uses environment variables for sensitive credentials (access/secret keys), which is a standard and secure practice. No 'eval' or other directly malicious patterns were found. Network requests are made to legitimate OTC API endpoints using Axios. The inherent security risk lies in exposing powerful cloud management tools to an AI, meaning a compromised or misconfigured AI could perform unintended actions on the cloud infrastructure.
Updated: 2025-11-25GitHub→
0
0
Low Cost
maxgerlach1 icon

granola-ai-mcp-server

by maxgerlach1

Sec9

Integrates Granola.ai meeting intelligence into Claude Desktop via the Model Context Protocol (MCP) for local AI processing.

Setup Requirements

  • ⚠️Requires macOS with Granola.ai application installed and actively generating meeting data.
  • ⚠️Requires Python 3.12+ and `uv` package manager for setup.
  • ⚠️The repository must be cloned to the user's home directory (`~`) to avoid macOS permission issues with Claude Desktop.
  • ⚠️Requires manual configuration of Claude Desktop's `claude_desktop_config.json` file with a specific, absolute path to the virtual environment's executable script.
Verified SafeView Analysis
The server operates entirely locally, processing data from Granola.ai's cache file on the user's machine. It explicitly states '100% Local Processing' and 'No External API Calls', minimizing network and data modification risks. Access to the cache is read-only. No dynamic code execution from untrusted input (like `eval`) or hardcoded secrets are apparent in the provided source code.
Updated: 2026-01-17GitHub→
PreviousPage 650 of 760Next