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
jpg486-ual icon

papercut-mcp

by jpg486-ual

Sec8

Provides a Model Context Protocol (MCP) server exposing tools to interact with PaperCut NG/MF via its XML Web Services API for tasks like user management and printer information retrieval.

Setup Requirements

  • ⚠️Requires Node.js 18+.
  • ⚠️Requires a running and configured PaperCut NG/MF instance with XML Web Services enabled. Specific settings (auth-token, allowed caller IPs) must be configured in PaperCut.
  • ⚠️Requires manual creation and configuration of a .env file with PAPERCUT_XMLRPC_URL and PAPERCUT_AUTH_TOKEN.
Verified SafeView Analysis
The server retrieves sensitive PaperCut API credentials (URL, auth token, timeout) from environment variables, which is a good practice for configuration. Input validation for tool arguments is performed using Zod schemas, reducing the risk of malformed inputs. The server communicates over standard I/O (stdio) and does not open network ports, thereby limiting its direct network attack surface. The primary security considerations involve the underlying PaperCut NG/MF XML Web Services configuration, such as securing the endpoint, using strong authentication tokens, and restricting allowed caller IPs. Error messages from tools might expose internal error details, but this is a minor risk that can be handled client-side.
Updated: 2025-12-01GitHub→
0
0
Low Cost
0xvm icon
Sec1

Provides a conversational MCP server for host-side job automation and offensive security experimentation, executing shell commands and managing their state.

Setup Requirements

  • ⚠️Directly executes arbitrary shell commands provided by clients, making it a critical security risk if not strictly access-controlled and run in a controlled environment.
  • ⚠️Requires Python 3.8+ (due to typing features) and `zeromcp`, `rich` dependencies.
  • ⚠️Exposes an unauthenticated HTTP API on port 12983, which may require firewall configuration or specific network access control.
Review RequiredView Analysis
CRITICAL RISK: The `start_shell_job` tool, exposed via an unauthenticated API, defaults to `use_shell=True` and directly executes arbitrary commands provided by the client. This allows for trivial remote code execution and shell injection if the server is accessible to untrusted parties. The server is explicitly designed for 'Offensive Security What-Can-Go-Wrong-Experimentation' and described as an 'ignorant, possibly naive, assistant', meaning its inherent danger is a feature, not a bug, for its intended use case. However, from a general security standpoint, it is extremely unsafe for general-purpose deployment or in untrusted environments. No hardcoded secrets were found, and dependencies are standard.
Updated: 2025-12-14GitHub→
0
0
Medium Cost
JosephAwuku33 icon

wave-gmail-mcp

by JosephAwuku33

Sec9

Enables AI agents to securely manage Gmail, including reading, sending, searching emails, and executing personalized bulk email campaigns using uploaded customer data.

Setup Requirements

  • ⚠️Requires a Google Cloud Project with the Gmail API enabled and OAuth 2.0 credentials configured, including setting `http://localhost:3000/oauth2callback` as an Authorized Redirect URI.
  • ⚠️Node.js (v16 or higher) must be installed locally on the machine running the server.
  • ⚠️Environment variables (GOOGLE_CLIENT_ID, GOOGLE_CLIENT_SECRET, GOOGLE_REDIRECT_URI, OAUTH_PORT) must be explicitly configured, with absolute paths recommended when integrating with Claude Desktop.
Verified SafeView Analysis
The server employs secure OAuth2 for Google authentication, storing tokens locally. It uses established libraries for email handling (googleapis, nodemailer) and data parsing (xlsx), reducing common vulnerabilities. String interpolation for bulk emails is simple replacement, not code execution. Local web servers for OAuth callback and data upload are intended for local interaction; the upload server's `Access-Control-Allow-Origin: *` is a minor relaxation for local convenience but is acceptable for a non-public service. No 'eval' or other dynamic code execution patterns were found, and sensitive credentials are handled via environment variables.
Updated: 2025-11-24GitHub→
0
0
Low Cost
JZ1101 icon

web3-mcp

by JZ1101

Sec1

Converts EVM smart contracts into MCP (Minecraft Protocol) servers, bridging Web3 functionality with a gaming server environment.

Review RequiredView Analysis
No executable source code was provided for analysis beyond the README.md. Therefore, a comprehensive security audit for 'eval', obfuscation, network risks, hardcoded secrets, or malicious patterns could not be performed. The score reflects the inability to assess safety rather than an inherent insecurity of the (unseen) code.
Updated: 2025-12-05GitHub→
0
0
Low Cost
enzobjmendonca icon

mcp-it

by enzobjmendonca

Sec6

Transforms any FastAPI server or external API into an MCP (Model Context Protocol) server, exposing its endpoints as MCP tools.

Setup Requirements

  • ⚠️Requires an existing or new FastAPI application to integrate with.
  • ⚠️If using `bind_openapi`, network access to the OpenAPI specification URL is required.
  • ⚠️Interaction with the generated MCP server requires an MCP-compatible client.
Verified SafeView Analysis
The `bind_openapi` feature fetches and parses OpenAPI specifications from arbitrary URLs, introducing a potential risk if pointed to untrusted or malicious sources that could craft malformed schemas leading to parsing errors or resource exhaustion. The `_external_proxy_call` function forwards incoming MCP request headers to external APIs without explicit filtering beyond common hop-by-hop headers. This means sensitive headers (e.g., internal authentication tokens) could be inadvertently forwarded to untrusted external services if not carefully managed by the user configuring `mcp-it`.
Updated: 2025-12-09GitHub→
0
0
Medium Cost
gorizond icon
Sec6

An MCP server that provides an API for interacting with multiple Rancher Manager backends, offering cluster, node, project, and Fleet GitOps management capabilities.

Setup Requirements

  • ⚠️Requires access to at least one Rancher Manager instance.
  • ⚠️Rancher API tokens with appropriate permissions are mandatory for authentication.
  • ⚠️Configuration is primarily managed through environment variables or `.env` files, which need careful management for sensitive data.
Verified SafeView Analysis
The `k8s_raw` tool explicitly allows arbitrary HTTP requests to the Kubernetes API via the Rancher proxy, which is powerful and marked as 'DANGEROUS' in its description. If an attacker gains control over the MCP server's input, this tool could be exploited for privilege escalation or unauthorized access to Kubernetes resources. The server also supports `insecureSkipTlsVerify`, which bypasses TLS certificate validation and should be used with extreme caution. Configuration loaded from `RANCHER_SERVERS` environment variable is parsed as JSON, which could be a vector for injection if the environment variable itself is untrusted. Tokens are obfuscated in logs, which is a good practice.
Updated: 2025-11-26GitHub→
0
0
Medium Cost
dmgrok icon
Sec9

Provides a searchable catalog of agent skills to AI agents and developer tools via the Model Context Protocol (MCP).

Setup Requirements

  • ⚠️Requires 'mcp' Python library.
  • ⚠️Requires 'aiohttp' Python library.
  • ⚠️Requires internet connectivity to fetch the 'catalog.json' from CDN.
Verified SafeView Analysis
The server primarily fetches and serves read-only data from a hardcoded CDN URL (`https://cdn.jsdelivr.net/gh/dmgrok/agent_skills_directory@main/catalog.json`). There is no user input used in `eval` or `subprocess` calls. The `search_skills` function uses safe string matching. The main security consideration is the trust in the external CDN source for the skill catalog itself.
Updated: 2026-01-19GitHub→
0
0
Medium Cost

mcp-python-server

by 20R25A0515

Sec7

Provides a server implementation using Python, likely for a specific protocol or game environment (e.g., Minecraft Coder Pack) based on the 'MCP' naming convention.

Setup Requirements

  • ⚠️Requires installation of Python dependencies from `requirements.txt`.
  • ⚠️Specific Python version may be required; check `pyproject.toml` or `main.py` for details.
  • ⚠️Network port configuration might be needed for server operation.
Verified SafeView Analysis
Cannot thoroughly audit for 'eval' or obfuscation without file contents. Inherent network risks exist as with any server application, requiring proper configuration and security practices.
Updated: 2025-11-23GitHub→
0
0
Low Cost
Sec9

An agent designed to interact with an MCP Server, likely for local cursor automation or control tasks.

Setup Requirements

  • ⚠️No server/agent code provided, only a LICENSE file.
  • ⚠️Requires full implementation of agent logic to be functional.
Review RequiredView Analysis
Only a LICENSE file is present; no executable code to audit for 'eval', obfuscation, or network risks. The repository itself poses no direct security threat from its current contents.
Updated: 2025-11-18GitHub→
0
0
Low Cost
pyhoon icon
Sec8

To enable HTTP streamable/SSE transport for Claude Desktop, which typically only supports stdio, by using a local proxy/bridge via the mcp-remote utility.

Setup Requirements

  • ⚠️Requires Node.js and npm to execute `npx` commands.
  • ⚠️Relies on the `mcp-remote` npm package, which must be installed or accessible in the execution environment.
  • ⚠️Assumes a separate HTTP-streamable MCP server is already running and accessible at `http://127.0.0.1:8080/mcp` for `mcp-remote` to connect to.
Verified SafeView Analysis
The provided source code consists solely of a README and a configuration file. No direct executable code is present for analysis within this repository. The `claude_desktop_config.json` specifies running `npx mcp-remote`, an external npm package. The security of the overall setup depends heavily on the trustworthiness and implementation of the `mcp-remote` package itself, which is not part of this repository's source code. The server it configures `mcp-remote` to connect to is set to `127.0.0.1:8080`, limiting network exposure to localhost.
Updated: 2025-12-12GitHub→
0
0
Low Cost

mcp-fast-server

by fancier21

Sec10

This project is a placeholder for a fast server application, currently only printing a greeting message.

Setup Requirements

  • ⚠️Requires Python 3.13+ as specified in pyproject.toml.
Verified SafeView Analysis
The code is extremely simple and contains no obvious security risks. It does not interact with external systems, process user input, or use any dangerous functions.
Updated: 2025-11-22GitHub→
0
0
Medium Cost
Sec4

This server is designed to provide remote memory management capabilities, likely for applications interacting with microcontrollers or specific protocols (MCP).

Setup Requirements

  • ⚠️Requires Node.js runtime (version specified in package.json, typically 16+).
  • ⚠️Project dependencies must be installed first using 'npm install' or 'yarn install'.
  • ⚠️TypeScript compilation may be required, usually handled by a build script (e.g., 'npm run build' or 'npm start').
Review RequiredView Analysis
As a network-facing server, it inherently exposes potential attack surfaces. Without access to the source code (files in 'src'), a comprehensive security audit for vulnerabilities like 'eval' usage, obfuscation, insecure API endpoints, or data handling practices is not possible. Inherent risks include unauthorized access to memory, data integrity issues, and potential denial-of-service.
Updated: 2025-11-18GitHub→
PreviousPage 351 of 760Next