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
Mandapati-SuryanarayanaRaju icon

Sample-MCP-client-and-Server

by Mandapati-SuryanarayanaRaju

Sec9

A minimal example of an MCP (Model Context Protocol) server and client demonstrating basic tool exposure and invocation.

Setup Requirements

  • ⚠️Python 3.13+ required
  • ⚠️Requires `mcp` package (version >= 1.22.0)
  • ⚠️Requires `uv` executable in PATH for the client to launch the server via `StdioServerParameters`
Verified SafeView Analysis
The client uses `StdioServerParameters` to launch the server as a subprocess. In this sample, the command (`uv run hello.py`) is hardcoded and points to a known, benign local script, making it safe. However, in a real application, if `command` or `args` were derived from untrusted user input, it could lead to arbitrary code execution. No other significant security risks like hardcoded secrets, 'eval', or network vulnerabilities were found in the provided code.
Updated: 2025-12-02GitHub→
0
0
Medium Cost
Akshay1018 icon

mcp-codedoc

by Akshay1018

Sec6

AI-powered tool for automated code documentation, quality auditing, refactoring, and security scanning within a local development environment.

Setup Requirements

  • ⚠️Requires Cursor or Claude Desktop IDE as the host environment.
  • ⚠️Installation requires `uvx` command-line tool.
  • ⚠️Relies on the integrated AI capabilities of Cursor/Claude for generating audits and refactored code.
Verified SafeView Analysis
The `generate_smart_doc` function can potentially read arbitrary local files if an absolute path is provided for `file_path`. The `refactor_and_optimize`, `evaluate_and_refactor`, and `predict_impact` functions, while employing aggressive path resolution, are primarily constrained to the project root. The `global_security_audit` function performs local regex-based scanning for secrets, which is safe. No `eval` or direct network exfiltration is observed. The server's file system interaction is inherent to its functionality as a local development agent, but the direct use of user-provided `file_path` without explicit `realpath` and path-in-root checks for reading presents a moderate risk if the calling AI/IDE does not sufficiently sanitize input.
Updated: 2026-01-18GitHub→
0
0
Low Cost
miguelfradeflores icon

MCP-tool-lesson

by miguelfradeflores

Sec6

Provides detailed Pokemon data from PokeAPI to AI assistants and other MCP clients via various tools.

Setup Requirements

  • ⚠️Requires Python 3.10 or higher.
  • ⚠️Requires active internet connection to access PokeAPI.
Review RequiredView Analysis
The `export_pokemon_to_csv` tool's `filename` parameter is vulnerable to path traversal if not properly sanitized or restricted. An attacker could potentially write files outside the intended directory by providing a manipulated `filename` (e.g., `../../malicious.csv`). No other critical vulnerabilities like `eval` or hardcoded secrets were found. Network requests are made to a public, well-known API.
Updated: 2025-11-20GitHub→
0
0
Medium Cost
abhitatachar2000 icon

container-dockter

by abhitatachar2000

Sec1

This server provides a web interface to deploy and manage applications within Docker containers by interacting with the Docker daemon and Git repositories.

Setup Requirements

  • ⚠️Docker daemon must be running and accessible.
  • ⚠️Docker Compose must be installed.
  • ⚠️Requires Git client installed on the host.
Review RequiredView Analysis
The application is critically vulnerable to remote code execution. It uses `child_process.exec` extensively (via `src/lib/docker.js`) to execute Docker commands, and it passes unsanitized user inputs (e.g., `repoUrl`, `appName`, `envVars`, `buildArgs`, `port`) directly from API requests (e.g., `/api/apps/deploy`) into these `exec` calls. This allows attackers to inject arbitrary shell commands. For example, by crafting a malicious `appName` or `envVars` payload, an attacker can execute commands on the host system where the 'container-dockter' server is running. No input validation or sanitization is evident in the provided code snippets before these dangerous operations.
Updated: 2025-12-06GitHub→
0
0
Low Cost
sharmaratnesh icon

first_mcp_server

by sharmaratnesh

Sec8

This server provides a multi-purpose HTTP endpoint to route requests to specific handlers (e.g., math operations, employee data retrieval) based on the incoming JSON payload.

Setup Requirements

  • ⚠️The 'employee_details.csv' file must be present at the repository root for the employee handler to function correctly.
Verified SafeView Analysis
The server generally handles inputs safely. Numbers are cast to float, and CSV parsing normalizes values. No 'eval' or similar dangerous functions are used. Pathing for the 'employee_details.csv' is hardcoded relative to the script, not user-controlled. Generic 'Exception' catching returning 'str(e)' could potentially expose minor internal details, but is not a critical vulnerability.
Updated: 2025-11-28GitHub→
0
0
Low Cost
Sec6

A Python-based server designed to control and interact with Digilent Analog Discovery devices, enabling remote measurement, data acquisition, and signal generation.

Setup Requirements

  • ⚠️Requires physical Digilent Analog Discovery hardware to be connected and utilized.
  • ⚠️Requires installation of Digilent's WaveForms SDK, including device drivers, which might be platform-dependent and installed separately from standard Python packages.
  • ⚠️Python 3 and dependencies from `requirements.txt` are required.
Verified SafeView Analysis
The server exposes network functionality (`server.py`) which introduces inherent network risks. Without source code analysis, it's impossible to verify input sanitization, authentication mechanisms, or potential for command injection. The `WF_SDK` suggests interaction with low-level hardware SDKs, which if compromised, could grant deep system access. Running it in a controlled, local environment is recommended.
Updated: 2025-11-18GitHub→
0
0
Low Cost
frkr icon

ubuntu-mcp

by frkr

Sec2

Execute shell commands within a Dockerized Ubuntu environment via HTTP API or MCP stdio.

Setup Requirements

  • ⚠️Requires Docker (recommended for setup and running)
  • ⚠️For Apple Silicon/ARM users, `--platform linux/amd64` is pinned, which might require specific Docker configurations or impact native performance.
Review RequiredView Analysis
The `/api/exec` endpoint directly executes arbitrary shell commands using `subprocess.run` with `shell=True`, making it highly vulnerable to command injection if exposed to untrusted input or networks. While the README warns against this and suggests running in a disposable container with a non-root user, the core functionality allows any shell command sent by the client, which is a critical security risk.
Updated: 2025-12-01GitHub→
0
0
High Cost
subramanya1997 icon

agentic-trust

by subramanya1997

Sec2

A unified platform for deploying, authenticating, monitoring, and managing production AI agents within an enterprise environment.

Setup Requirements

  • ⚠️Requires Node.js 18.0 or higher.
  • ⚠️Requires a configured Sanity.io project with specific schemas and corresponding environment variables (`NEXT_PUBLIC_SANITY_PROJECT_ID`, `NEXT_PUBLIC_SANITY_DATASET`, `SANITY_API_TOKEN`).
  • ⚠️The blog newsletter subscription form uses a hardcoded Google Form URL. Customizing this functionality would require manually identifying the form's entry ID for a different form.
Review RequiredView Analysis
Critical vulnerabilities identified: 1. Webhook Revalidation (src/app/api/sanity/revalidate/route.ts): The `isValidSignature` function implements a simplified signature verification that merely compares the received signature header with the `SANITY_WEBHOOK_SECRET`. This is NOT proper HMAC verification. If the `SANITY_WEBHOOK_SECRET` is compromised, an attacker can easily forge requests to trigger cache revalidation for arbitrary paths, potentially leading to denial-of-service (DDoS) on the cache or presentation of stale/incorrect content. 2. Unauthenticated Image Generation API (src/app/api/generate-blog-cover/route.tsx): This API endpoint is completely unauthenticated and unvalidated. Any unauthenticated user can send a POST request to this endpoint with a `title`, `category`, `authors`, and optionally a `postId`. This allows attackers to: - Consume server resources by repeatedly triggering image generation. - Upload arbitrary images to the Sanity project's asset storage. - If a valid `postId` is provided, an attacker could attach any generated image as the `coverImage` for an existing blog post, leading to content defacement or injection. This is a severe vulnerability for content integrity and resource abuse. Sensitive environment variables (`SANITY_API_TOKEN`, `SANITY_WEBHOOK_SECRET`) are correctly referenced via `process.env` but their secure handling and protection in deployment are paramount given the identified vulnerabilities.
Updated: 2025-12-10GitHub→
0
0
Medium Cost

amazon_sp_mcp

by jay-trivedi

Sec8

Provides AI agents with access to Amazon Seller Central data via the Amazon Selling Partner API (SP-API) for business analytics and operations.

Setup Requirements

  • ⚠️Requires Amazon SP-API developer application registration and approval.
  • ⚠️Requires AWS IAM credentials and LWA OAuth 2.0 credentials (Client ID, Client Secret, Refresh Token) from Amazon.
  • ⚠️Requires Node.js 18+ and npm installed locally.
Verified SafeView Analysis
The server handles highly sensitive Amazon Seller Central credentials (AWS, LWA refresh tokens). While the project outlines security considerations like 'least privilege' and 'rotate refresh tokens', the security score reflects the critical importance of secure environment configuration and credential management to prevent unauthorized access or data breaches.
Updated: 2025-11-17GitHub→
0
0
Low Cost
frekkanzer2 icon

kompass

by frekkanzer2

Sec8

This project acts as a Minecraft Protocol (MCP) server or proxy, handling client connections and potentially providing web-based statistics and management.

Setup Requirements

  • ⚠️Requires Node.js runtime
  • ⚠️Requires an available network port (default 25565)
Verified SafeView Analysis
No 'eval' or obfuscation found. The web server serves static files from a 'public' directory, which appears to be path-constrained, mitigating simple path traversal. The core server handles raw Minecraft protocol packets, which always requires careful validation to prevent malformed data exploits; no obvious flaws detected in the provided snippets. No hardcoded secrets were identified.
Updated: 2025-12-04GitHub→
0
0
Low Cost
tokenring-ai icon

mcp

by tokenring-ai

Sec3

Client-side plugin for TokenRing agents to connect with Model Context Protocol (MCP) servers and register their external tools.

Setup Requirements

  • ⚠️Requires a running TokenRingApp instance to operate as a plugin or for manual usage.
  • ⚠️Requires an external MCP server (via stdio, SSE, or HTTP) to connect to, as this package is a client.
  • ⚠️Configuration for transports must strictly adhere to Zod schemas, particularly specifying 'command' for 'stdio' or 'url' for 'sse'/'http' transports.
Review RequiredView Analysis
The `stdio` transport type allows arbitrary command execution via the `command` field in the configuration. If the application's configuration (specifically `mcp.transports[name].command`) can be sourced from or influenced by untrusted input, it poses a severe arbitrary code execution vulnerability. The `sse` and `http` transports also allow configurable URLs. If these URLs can be set by an untrusted source, it could lead to Server-Side Request Forgery (SSRF) or data exfiltration. Robust external validation of all configuration inputs is critical.
Updated: 2026-01-13GitHub→
0
0
Medium Cost
avinash221988 icon

prometheus-mcp-server

by avinash221988

Sec7

Enables AI assistants to interact with Prometheus and Alertmanager for intelligent monitoring and incident response through Model Context Protocol (MCP) tools, resources, and prompts.

Setup Requirements

  • ⚠️Requires Python 3.9+ (Python 3.13 is specifically referenced in setup scripts for FastMCP compatibility).
  • ⚠️Requires a running Prometheus instance and optionally an Alertmanager instance, accessible from where the MCP server is deployed.
  • ⚠️Using the MCP Inspector for testing requires Node.js 22.7.5+ and npm.
Verified SafeView Analysis
The server exposes a `prometheus_query` tool that directly executes arbitrary PromQL queries provided by the AI. If the AI or the MCP server itself were compromised, this could lead to resource exhaustion on the Prometheus server or unauthorized data access. The `--no-verify-ssl` option, configurable via an environment variable, can also introduce security vulnerabilities if used improperly in production environments. No explicit hardcoded secrets or malicious patterns were found in the provided source code.
Updated: 2025-12-05GitHub→
PreviousPage 407 of 760Next