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
mayank-vikki icon

test-remote-mcp-server

by mayank-vikki

Sec9

This server provides an API for managing personal expenses, allowing users to add, list, and summarize financial transactions.

Setup Requirements

  • ⚠️Database data is ephemeral as it's stored in a temporary directory and will be lost on system restarts or temporary file cleanup.
  • ⚠️Requires Python 3.11 or higher.
  • ⚠️Dependencies `aiosqlite` and `fastmcp` must be installed.
Verified SafeView Analysis
The code utilizes parameterized SQL queries which prevents SQL injection vulnerabilities. No 'eval', 'exec', or similar dangerous functions are used. There are no hardcoded secrets found. The database is stored in a temporary directory, which is a functional detail rather than a security flaw, but implies ephemerality. The server defaults to listening on 0.0.0.0:8000, which is broad for production but standard for development and containerized environments.
Updated: 2025-11-26GitHub→
0
0
Medium Cost
slomo-b icon
Sec9

Provides comprehensive Hero UI documentation and design principles to AI assistants via the Model Context Protocol (MCP), enabling them to answer development-related queries.

Setup Requirements

  • ⚠️Requires Python 3.8 or higher.
  • ⚠️Requires `pip install fastapi uvicorn pydantic`.
  • ⚠️The `cwd` path in Claude Desktop/Cline integration configurations must be manually adjusted to the local repository path.
Verified SafeView Analysis
The server primarily reads local JSON files and processes simple string queries for information retrieval. No dynamic code execution (e.g., eval, exec), direct system calls, or external network requests are observed within the provided source. Input parameters are used for lookup and searching against predefined data, mitigating injection risks. Error handling for tool calls is robust. Security largely depends on the integrity of the local JSON data and the deployment environment.
Updated: 2025-11-29GitHub→
0
0
Low Cost
sentice icon

mcp-server

by sentice

Sec8

An MCP server providing a tool to retrieve user balance data from an external backend service, intended for use by LLMs or other agents that can consume MCP tools.

Setup Requirements

  • ⚠️Requires Docker and Docker Compose for the intended setup.
  • ⚠️An external 'food2' Docker network is expected to exist (or configuration adjustment needed).
  • ⚠️Requires a '.env' file with 'BACKEND_URL' pointing to the Adonis backend service.
Verified SafeView Analysis
The server uses environment variables for sensitive configurations like BACKEND_URL, which is good practice. It handles incoming requests and dispatches them to a backend service. The 'users_balance' tool accepts a 'filters' object from the client which is passed to an external Adonis backend. The security of this data flow (e.g., against SQL injection or other backend vulnerabilities) depends entirely on how the Adonis backend processes these 'filters'. However, within the scope of the provided MCP server code itself, no direct 'eval', command injection, or hardcoded secrets are present. Broad CORS ('*') is enabled, which is generally acceptable for public APIs or development environments but might need stricter control in production.
Updated: 2025-12-02GitHub→
0
0
Medium Cost
EfeSenerr icon

demo_mcp_learn

by EfeSenerr

Sec9

A multi-agent demonstration integrating the Model Context Protocol (MCP) with the Microsoft Agent Framework to create collaborative AI agents.

Setup Requirements

  • ⚠️Requires Python 3.10+ (pyproject.toml specifies >=3.10).
  • ⚠️Requires a GitHub Personal Access Token (`GITHUB_TOKEN`) for the GitHub Models API, which may incur costs or require specific GitHub account access.
  • ⚠️Requires a 'The One API' Key (`ONE_API_KEY`), which is an external API for LOTR quotes.
Verified SafeView Analysis
The code relies on external APIs (The One API, GitHub Models API) for functionality. API keys are properly handled via environment variables and are not hardcoded. No 'eval' or other directly dangerous patterns are observed.
Updated: 2025-11-21GitHub→
0
0
Medium Cost
SEMGOODD icon
Sec6

Facilitates an AI agent to access internal project data and fetch external website content through a standardized tool-calling interface (MCP).

Setup Requirements

  • ⚠️Requires Ollama to be running locally with the 'llama3.2:latest' model downloaded.
  • ⚠️Requires Python 3.12 or newer.
  • ⚠️The 'server.py' file must be present in the same directory as 'client.py'.
Verified SafeView Analysis
The `fetch_website_content` tool allows the AI model to make arbitrary HTTP GET requests to any URL. This presents a moderate risk for Server-Side Request Forgery (SSRF) if the server is running in an environment where it can access internal networks. It could also be misused for external reconnaissance or denial-of-service attempts against external targets. There are no other obvious hardcoded secrets or dangerous functions like `eval` detected.
Updated: 2025-11-26GitHub→
0
0
Low Cost
Sec8

Demonstrates how to configure Gilhari ORM to use database-generated primary keys (autoincrement IDs) for JSON objects in a RESTful microservice.

Setup Requirements

  • ⚠️Docker is required to build and run the microservice.
  • ⚠️JDK 1.8+ is required for compiling container domain model classes if modifications are made.
  • ⚠️The Gilhari SDK is required for development and customization.
Verified SafeView Analysis
The server exposes a RESTful API over HTTP, as is its purpose. It uses a base Docker image (softwaretree/gilhari), assuming the security of that base. No obvious malicious components, obfuscation, or arbitrary code execution (`eval`) detected. Standard microservice network exposure is the primary consideration.
Updated: 2025-11-18GitHub→
0
0
Low Cost
Taiinguyenn139 icon

self-mcp

by Taiinguyenn139

Sec9

Develops and hosts custom MCP (Model Context Protocol) tool servers for integration with LLMs like Claude, providing real-time information or capabilities.

Setup Requirements

  • ⚠️Requires Python 3.12+
  • ⚠️Requires Anthropic API Key (Paid) for the client application to interact with Claude
  • ⚠️Requires dependency installation (e.g., `uv sync` or `pip install -r requirements.txt`)
Verified SafeView Analysis
No direct 'eval' or obvious malicious patterns found. The client executes server scripts specified via command-line arguments, which is standard for CLI tools but assumes trusted input for the script path. External API calls use httpx with basic error handling. No hardcoded secrets; API keys are loaded from environment variables via python-dotenv.
Updated: 2025-11-23GitHub→
0
0
Medium Cost
nestr-dev icon

nestr-mcp

by nestr-dev

Sec9

Connects AI assistants to Nestr workspaces, enabling them to manage tasks, projects, organizational structures, and retrieve insights.

Setup Requirements

  • ⚠️Requires `NESTR_API_KEY` or `NESTR_OAUTH_TOKEN` environment variable for authentication.
  • ⚠️For self-hosted OAuth, `NESTR_OAUTH_CLIENT_ID` and `NESTR_OAUTH_CLIENT_SECRET` must be configured after contacting Nestr to register an OAuth client.
  • ⚠️Requires Node.js version 18 or higher.
Verified SafeView Analysis
The server implements robust security measures including explicit environment variable usage for API keys/OAuth tokens, proper input validation (using Zod schemas), and HTML escaping for error messages to prevent XSS. It handles OAuth with PKCE verification by proxying to Nestr, adding an important security layer. Session management relies on MCP client termination or server shutdown for cleanup, but `oauth/storage.ts` includes a periodic cleanup for pending auth requests. No `eval` or blatant obfuscation detected. Dynamic client registration, while a standard OAuth feature, always carries inherent risks that appear well-mitigated through validation.
Updated: 2026-01-19GitHub→
0
0
Low Cost
Ferretly-International icon

mcp-server-experiment

by Ferretly-International

Sec4

This project explores building and testing a Model Context Protocol (MCP) server using .NET and C#, integrating simple tools like 'echo' and 'get_config_value' for AI agent interaction.

Setup Requirements

  • ⚠️Requires `C:\Users\hokie\AppData\Roaming\npm` directory to be created (specific to the original developer's environment setup).
  • ⚠️Requires manually copying the 'Session token' from the MCP Inspector console into the inspector's Proxy Session Token property before connecting.
  • ⚠️The `MCP_SERVER_SETTINGS_PATH` environment variable must be set, pointing to the application's configuration file (e.g., `appsettings.json`), as the default configuration sources are cleared and overridden.
Review RequiredView Analysis
The `appsettings.json` file contains hardcoded sensitive information, specifically a `ConnectionStrings.DefaultConnection` with explicit `User Id` and `Password`, and an `ExternalApi.ApiKey`. The README acknowledges this as a temporary measure, stating 'Clearly better authentication needs to happen somewhere to protect these values.' This poses a significant security risk if deployed or run in an insecure environment, as credentials could be exposed.
Updated: 2025-11-20GitHub→
0
0
Low Cost
PrincejiCoder icon

awesome-mcp

by PrincejiCoder

Sec10

A curated list of Model Context Protocol (MCP) servers, tools, and resources, providing a catalog for developers to discover and compare integrations for AI applications.

Verified SafeView Analysis
This repository (`awesome-mcp`) is a curated list (an 'awesome list') and contains only Markdown documentation files. It is not an executable server and therefore does not pose security risks typically associated with running server code. The security section in the README refers to the security models of *listed* MCP servers, not this repository itself.
Updated: 2026-01-16GitHub→
0
0
Medium Cost
IceWreck icon
Sec6

Provides AI agents with search and URL content fetching capabilities via a SearxNG meta-search engine interface.

Setup Requirements

  • ⚠️Requires a separate, running SearxNG instance URL (e.g., `https://searx.be`)
  • ⚠️Requires Python 3.11 or higher
  • ⚠️The `markitdown[pdf]` dependency may have additional system-level requirements for PDF processing (e.g., Poppler utilities)
Review RequiredView Analysis
The `fetch_url` tool can fetch arbitrary URLs, which poses a significant Server-Side Request Forgery (SSRF) risk if the server is exposed to untrusted inputs. It could also be used to fetch large files for Denial of Service or to process malicious content with `MarkItDown`, potentially exposing vulnerabilities in the parsing library. The server listens on `0.0.0.0` when HTTP transport is enabled, making it network-accessible.
Updated: 2026-01-06GitHub→
0
0
High Cost
Shimmy0530 icon

kali-mcp-server

by Shimmy0530

Sec7

Facilitates automated security testing and vulnerability assessments by exposing Kali Linux tools via the Model Context Protocol to AI assistants and development environments.

Setup Requirements

  • ⚠️Docker must be installed and running on the host system.
  • ⚠️The 'kali-mcp-server' Docker image needs to be built or pulled prior to execution.
  • ⚠️Requires significant host system resources (memory, CPU) and elevated Docker capabilities (`--cap-add=NET_RAW`, `--cap-add=NET_ADMIN`) for full functionality.
  • ⚠️Strict adherence to legal and ethical guidelines is paramount, as these are offensive security tools intended solely for authorized testing.
Verified SafeView Analysis
The server's core `run_command` function utilizes `subprocess.run(shell=True)`, which poses a potential command injection risk if input is not meticulously sanitized. Although efforts are made to escape specific parameters within tool wrappers, relying on `shell=True` without comprehensive `shlex.quote` on all user-supplied components is less secure than `shell=False`. The container requires elevated Docker capabilities (`NET_RAW`, `NET_ADMIN`), inherently increasing the attack surface. However, the project mitigates this by providing extensive legal/ethical warnings, implementing Docker-level and per-process resource limits, and explicitly detailing security best practices and isolation recommendations.
Updated: 2025-11-28GitHub→
PreviousPage 716 of 760Next