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
High Cost
sachdev27 icon
Sec7

Enables AI assistants (like Claude) to interact with Dell PowerScale (Isilon) storage clusters by dynamically generating tools from the OneFS REST API specification.

Setup Requirements

  • ⚠️Requires Python 3.10 or higher.
  • ⚠️Requires access to a Dell PowerScale cluster with its REST API enabled and appropriate API credentials.
  • ⚠️Requires a local OpenAPI specification file (e.g., `powerscale_9.7_comprehensive_openapi.json`) from which to generate tools. This file is expected to be present in the installation or specified via `LOCAL_OPENAPI_SPEC_PATH`.
Verified SafeView Analysis
The server uses HTTP Basic Authentication, which is sensitive. While credentials are to be provided via environment variables or per-request arguments (not hardcoded), the default `ISILON_TLS_VERIFY` setting for PowerScale API connections is `false`, which disables SSL certificate validation and poses a significant security risk for data in transit. The HTTP/SSE server (for n8n/web clients) uses `Access-Control-Allow-Origin: *` (open CORS), which is acceptable for internal/controlled environments but dangerous if exposed to the public internet. No instances of `eval` or obvious malicious patterns were found. The codebase appears professionally structured with explicit error handling.
Updated: 2025-12-10GitHub→
0
0
Low Cost
VenkatRamReddyK icon

git-repos-mcp

by VenkatRamReddyK

Sec9

This server exposes a Model Context Protocol (MCP) resource to list the public GitHub repositories of a specific user.

Setup Requirements

  • ⚠️Requires Node.js installed.
  • ⚠️For Node.js versions older than 18, `node-fetch` must be manually installed and polyfilled globally.
Verified SafeView Analysis
The server makes an API call to a standard GitHub endpoint. No 'eval' or obfuscation is present. There are no hardcoded secrets, and the username for the GitHub API call is public information. The network risk is minimal, relying on the security of the GitHub API itself.
Updated: 2025-11-24GitHub→
0
0
Medium Cost
dyl104 icon
Sec9

Provides a FastMCP-based server with basic arithmetic tools, dynamic resources, and sophisticated AI prompt generation templates.

Setup Requirements

  • ⚠️Python 3.13+ required
  • ⚠️Requires `mcp[cli]` installation
Verified SafeView Analysis
The provided source code for `main.py` does not contain obvious security vulnerabilities such as `eval`, hardcoded credentials, or risky file operations. The server exposes tools and prompts, and their safety depends on the inputs provided to them and the underlying `mcp` framework. Input validation for `name`, `task`, `raw_prompt`, etc., is implicit to the tool/prompt function signatures and not explicitly shown, but typically handled by the framework.
Updated: 2025-11-24GitHub→
0
0
High Cost
DawidSu icon

ha-mcp-server

by DawidSu

Sec5

Provides a Model Context Protocol (MCP) server for Claude AI to securely and efficiently interact with Home Assistant configuration files, offering both Docker-based server deployment and Linux desktop integration tools.

Setup Requirements

  • ⚠️Requires Docker and Docker Compose for server deployment.
  • ⚠️The Home Assistant Claude MCP Server Addon must be running in Home Assistant for core functionality and desktop tool integration.
  • ⚠️Linux desktop users leveraging the desktop tools need to perform SSH key setup (ssh-keygen, ssh-copy-id) and install Python 3.6+ with tkinter and netcat.
Verified SafeView Analysis
The project demonstrates significant effort in security, implementing input validation, file access control (path traversal, extension/size limits, suspicious patterns), and rate limiting via `security-utils.sh`. It uses non-root Docker users and includes extensive security documentation. However, the `cache-manager.sh` script uses `eval "$command"`, allowing arbitrary command execution. While this is currently used for internal commands, its presence in a script callable by the Node.js API server (via `child_process.exec`) poses a critical remote code execution (RCE) vulnerability if an injection vector were to be discovered or introduced. Similarly, the `claude-mcp-widget.py` uses `subprocess.Popen` with f-strings for SSH commands, which, if not properly sanitized or if user input is maliciously crafted, could lead to command injection, though SSH clients typically offer some protection. Users must ensure strict control over all inputs and environments.
Updated: 2026-01-19GitHub→
0
0
High Cost
saurabhmain icon

a-mem-mcp-server

by saurabhmain

Sec5

An agentic memory system for LLM agents, enhancing research by storing, linking, and evolving knowledge based on the Zettelkasten principle, with IDE integration.

Setup Requirements

  • ⚠️Requires a Python 3.x environment with various dependencies (e.g., `textual`, `requests`, `dash`, `plotly`).
  • ⚠️If using Ollama, requires a local Ollama server running and specific models (`qwen3:4b`, `nomic-embed-text`) to be pulled.
  • ⚠️If using OpenRouter, requires a paid API key (`OPENROUTER_API_KEY`).
  • ⚠️For advanced graph backends like FalkorDB, specific installations are needed (`falkordblite` for Linux/macOS, or `falkordb` and `redis` with the FalkorDB module for Windows).
  • ⚠️For web research and PDF extraction, may require local Docker containers for Jina Reader or Unstructured API, or their respective Python libraries and dependencies like `pdfminer.six`.
Review RequiredView Analysis
The server exposes a `/get_graph` endpoint via an `aiohttp` web server, by default on `127.0.0.1:42424`, which is read-only but exposes internal graph data. The `add_file` tool processes file paths provided by the user/agent; if a malicious actor controls this input, it could potentially be used to read arbitrary files accessible to the server process, leading to information disclosure. Additionally, public Google API keys are hardcoded as defaults, which, while likely for a public Custom Search Engine, is still poor practice and could lead to API quota exhaustion.
Updated: 2026-01-19GitHub→
0
0
Low Cost
alelunardi98 icon

mcp-server

by alelunardi98

Sec7

An AI tool server exposing domain-specific functionalities in health and insurance to be consumed by Large Language Models.

Setup Requirements

  • ⚠️Requires JDK 17+
  • ⚠️Requires Maven or Gradle to build and run
  • ⚠️Intended for use with an external AI model orchestrator to leverage its tool-calling capabilities
Verified SafeView Analysis
Default H2 in-memory database credentials (sa / "") and an enabled H2 console are present and insecure for production environments. Input validation for tool parameters, especially in methods exposed to AI, should be robust.
Updated: 2025-11-20GitHub→
0
0
Low Cost
MohamedSherifAbdelsamiea icon

prometheus-remote-mcp-CDK

by MohamedSherifAbdelsamiea

Sec7

Serves Prometheus Model Context Protocol (MCP) data via AWS Lambda and API Gateway with Cognito authentication for querying Amazon Managed Prometheus.

Setup Requirements

  • ⚠️Requires an AWS Account and AWS CDK for deployment.
  • ⚠️Requires pre-configured Amazon Managed Prometheus (AMP) workspace, as indicated by '⚠️ NOT PART OF CDK 👤 USER MUST CONFIGURE' and 'Workspace ARN Required' in the architecture diagram. The `AMP_WORKSPACE_ARN` environment variable is critical.
  • ⚠️Cognito User Pool and OAuth Client setup is managed by CDK, but client-side configuration (`mcp-server-config.json` generation) needs to be handled post-deployment using the provided script or manual steps.
Verified SafeView Analysis
The architecture utilizes AWS Lambda, API Gateway, and Cognito, which are robust AWS services for security. JWT validation is handled by a dedicated Lambda authorizer. The core MCP Lambda processes requests using pydantic models, reducing common injection vulnerabilities. The primary security concern is the `update-mcp-config-cloudshell.sh` script, which retrieves and writes `CLIENT_SECRET` to a local `mcp-server-config.json` file. While intended for secure setup in CloudShell, this file needs to be securely managed and ideally deleted post-configuration to prevent exposure of credentials if the deployment environment is compromised. No direct 'eval' or obvious malicious patterns were found in the application logic; `jq` is used for safe JSON manipulation in scripts. IAM roles for Lambda accessing AMP are assumed to be properly configured by the CDK.
Updated: 2025-12-05GitHub→
0
0
Low Cost
NaokiTest icon
Sec5

A backend service providing basic arithmetic calculations through an API interface.

Review RequiredView Analysis
A thorough security audit is impossible without the source code. Based solely on the project name 'simple-calculator-mcp-server', common risks for a server of this type include improper input validation, which could lead to denial-of-service or unexpected behavior. No indicators for 'eval', obfuscation, hardcoded secrets, or malicious patterns can be identified without the actual code.
Updated: 2025-11-27GitHub→
0
0
Medium Cost
twanlass icon

granola-mcp

by twanlass

Sec8

Provides tools for AI agents (like Claude) to access Granola meeting transcripts and AI-generated notes.

Setup Requirements

  • ⚠️Requires Node.js 20+
  • ⚠️Granola desktop app must be installed and logged in for credentials
  • ⚠️Requires manual configuration in Claude Desktop or Claude Code applications
Verified SafeView Analysis
The server loads credentials (WorkOS access token) from the local Granola desktop app's configuration file (~/Library/Application Support/Granola/supabase.json), rather than requiring them as environment variables or hardcoding them. This approach relies on the Granola app's security for credential storage. Input validation for tools is performed using Zod. API calls are made over HTTPS, and errors are handled. There are no indications of 'eval', code obfuscation, or other overtly malicious patterns. The User-Agent is hardcoded but not a secret.
Updated: 2026-01-16GitHub→
0
0
Medium Cost

vst-mcp-server

by thomasbunch

Sec8

An AI-assisted server for VST plugin development, offering DSP algorithms, audio formulas, JUCE templates, UI components, and code validation tools.

Setup Requirements

  • ⚠️Requires Node.js and npm installed.
  • ⚠️Running locally via `npm start` requires a build step (`npm run build`).
Verified SafeView Analysis
The server uses standard Node.js/Express practices and the MCP SDK. It explicitly enables `Access-Control-Allow-Origin: *`, which is common for open APIs but implies broad access from any web domain. The `security-licensing.ts` file defines `EncryptedString` and `ObfuscatedValidator` as examples for plugin developers, not as part of the server's own internal security mechanisms. No obvious malicious patterns or direct use of `eval` or similar dangerous functions were found in the provided server-side code.
Updated: 2025-11-27GitHub→
0
0
Medium Cost
techslaves icon
Sec2

Integrates Spring AI with a PostgreSQL database to expose read-only database operations as tools for AI agents.

Setup Requirements

  • ⚠️Requires Java 17+ and Maven.
  • ⚠️Requires a running PostgreSQL database.
  • ⚠️Database connection environment variables (DB_URL, DB_USER, DB_PASSWORD) must be configured.
Review RequiredView Analysis
CRITICAL: The `DatabaseService.executeQuery` method directly executes user-provided SQL strings without proper parameterization, making it highly vulnerable to SQL injection, even with the `SELECT` prefix check. An attacker could craft a `SELECT` statement to exfiltrate sensitive data, perform denial-of-service, or execute other malicious queries depending on database permissions. The example `claude_desktop_config.json` also hardcodes database credentials, which is a security risk if not managed properly.
Updated: 2025-11-29GitHub→
0
0
Low Cost
NaokiTest icon
Sec1

Provides a server-side implementation for basic calculator operations, potentially over a custom message communication protocol.

Setup Requirements

  • ⚠️Requires a compatible runtime environment (e.g., Node.js, Python, Java - specific version unknown).
  • ⚠️Requires a client application that understands the specific 'MCP' protocol for interaction.
  • ⚠️May require specific network port configuration to avoid conflicts.
Review RequiredView Analysis
Without access to the source code, a comprehensive security audit is impossible. Cannot check for specific vulnerabilities like 'eval' usage, obfuscation, hardcoded secrets, or malicious patterns. Any network risks associated with running a server cannot be assessed.
Updated: 2025-11-27GitHub→
PreviousPage 648 of 760Next