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(8554)

0
0
Medium Cost
Amardeshmukh2566 icon

test-remote-mcp-server

by Amardeshmukh2566

Sec1

A server for testing remote interactions, possibly related to a Multiple-Choice Protocol (MCP).

Review RequiredView Analysis
No source code was provided for analysis. 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.
Updated: 2026-01-17GitHub→
0
0
Medium Cost
akraradets icon

boilerplate-mcp

by akraradets

Sec3

This repository serves as a boilerplate/template for developing a Model Context Protocol (MCP) server, integrating tools, resources, and prompts for LLM applications.

Setup Requirements

  • ⚠️Requires Python 3.13 or newer.
  • ⚠️FastMCP is a stateful framework, which can impact horizontal scaling and might lead to loss of elicitation/sampling features when behind a load balancer without sticky sessions.
  • ⚠️Requires Node.js and npm/npx for `MCP Inspector`.
Review RequiredView Analysis
The server exposes a resource template `files://{story_name}` which directly uses the `story_name` from client requests to construct file paths. Without explicit sanitization or validation, this is vulnerable to path traversal (e.g., `files://../../../../etc/passwd`), potentially allowing unauthorized reading of arbitrary files on the server. The `allow_origins=["*"]` in CORS settings is also overly permissive for production.
Updated: 2025-12-27GitHub→
0
0
Medium Cost
trashchenkov icon

nasa_mcp

by trashchenkov

Sec9

The server provides a collection of tools to interact with various NASA APIs for astronomy pictures, space weather, media search, and near-earth objects, acting as a unified interface for agent-based systems.

Setup Requirements

  • ⚠️Requires 'fastmcp' Python library to be installed.
  • ⚠️Requires 'NASA_API_KEY' environment variable for full functionality, otherwise a rate-limited 'DEMO_KEY' is used.
Verified SafeView Analysis
The server retrieves the NASA API key from an environment variable, using a 'DEMO_KEY' as a fallback, which is a good practice. It utilizes `httpx` with `raise_for_status()` for robust HTTP requests. No direct `eval` or other arbitrary code execution patterns are visible. Input parameters are mostly handled by the underlying NASA APIs, and string inputs for `event_type` in `nasa_donki_recent_events` are passed directly after uppercasing, which is generally safe within the context of predefined NASA API event types.
Updated: 2025-12-22GitHub→
0
0
Medium Cost
nickweedon icon
Sec7

Provides AI assistants with tools to read, create, edit, and manage Google Docs and Google Drive files, including advanced formatting and bulk operations.

Setup Requirements

  • ⚠️Requires a Google Cloud Project setup, including enabling Google Docs and Drive APIs, configuring an OAuth Consent Screen, and creating OAuth Desktop app credentials (a multi-step manual process).
  • ⚠️The Docker socket (`/var/run/docker.sock`) must be mounted into the container (read-only) for the automatic OAuth port discovery feature to function.
  • ⚠️A blank `credentials/token.json` file needs to be created manually before the initial Google authentication process.
Verified SafeView Analysis
The server requires mounting the Docker socket (`/var/run/docker.sock`) into the container as read-only. While this mitigates some risks, access to the Docker socket can still be a significant security concern if the container is compromised, potentially allowing privilege escalation on the host system. The application requests broad Google Drive API permissions (`https://www.googleapis.com/auth/drive`), granting extensive access to a user's Drive content. Users should carefully review the implications of these permissions and ensure they are comfortable with the scope. No hardcoded secrets, `eval()` calls, or obvious malicious patterns were found in the provided source code. Input validation and error handling are present to prevent common API abuse and provide user-friendly messages.
Updated: 2025-12-25GitHub→
0
0
Medium Cost
waqasm86 icon
Sec8

Provides a Model Control Protocol (MCP) interface for local GGUF Large Language Models, enabling tool-based interaction.

Setup Requirements

  • ⚠️Requires a separate llama.cpp server instance running locally with a GGUF model.
  • ⚠️Explicitly references Python 3.11 in configuration, though the README states Python 3.8+.
Verified SafeView Analysis
The primary FastAPI server binds to localhost (127.0.0.1) by default, limiting network exposure. The 'server_stdio.py' component, if run directly as an HTTP server, would bind to all network interfaces (0.0.0.0), potentially exposing it; however, it appears intended for subprocess management via stdio. Both servers make HTTP requests to a configurable LLAMA_COMPLETION_URL; ensuring this URL points to a trusted local llama.cpp instance is crucial to prevent data leakage or external compromise. No 'eval', obfuscation, or hardcoded secrets were found. Basic input validation for numeric parameters is present.
Updated: 2025-12-13GitHub→
0
0
Low Cost
atani icon
Sec1

An MCP server that allows direct manipulation of the standard macOS Reminders app from Claude Code for personal automation and AI-driven task management.

Setup Requirements

  • ⚠️Requires macOS (uses AppleScript, will not work on Windows/Linux).
  • ⚠️Requires manual macOS privacy settings to grant Terminal/Node.js access to Reminders.
  • ⚠️Requires manual JSON configuration in Claude Code's configuration file.
Review RequiredView Analysis
The `ReminderServiceImpl.sanitizeForAppleScript` function, used to sanitize user inputs (like list names and reminder names) before embedding them into AppleScript commands, only escapes double quotes (`"`). This is insufficient. An attacker could inject single quotes (`'`), backslashes (`\`), or newline characters (`\n`, `\r`) into inputs, which would break the AppleScript syntax. This could lead to a denial of service (script failure) or, more critically, allow for AppleScript injection where arbitrary `do shell script` commands could be executed on the user's macOS system. For instance, if a reminder name includes an unescaped single quote, the generated AppleScript will be syntactically invalid.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
jenksed icon

nerve

by jenksed

Sec7

This project acts as an intercepting proxy for Minecraft Protocol (MCP) traffic, allowing for custom logic or modifications between a Minecraft client and server.

Setup Requirements

  • ⚠️Requires Python 3.x environment.
  • ⚠️SSL certificates (key and cert files) are needed for secure proxy operation.
  • ⚠️Requires an existing Minecraft server to proxy connections to.
Verified SafeView Analysis
As an intercepting network proxy, it inherently handles untrusted client input, which requires robust packet validation to prevent vulnerabilities. The 'plugins/' directory suggests an extensible architecture; if plugins can be loaded from untrusted sources, it introduces a significant risk. Proper firewalling and access control are critical for deployment to limit exposure.
Updated: 2026-01-16GitHub→
0
0
Medium Cost
efranlund icon

ep-gql-mcp

by efranlund

Sec9

Enables natural language queries for hockey statistics, players, teams, leagues, and drafts by interfacing with the EliteProspects.com GraphQL API via Model Context Protocol (MCP).

Setup Requirements

  • ⚠️Requires running `npm run generate-schema` initially and whenever the upstream EliteProspects GraphQL API schema changes, before `npm run build` or running the server.
  • ⚠️Relies on an external EliteProspects GraphQL API endpoint (configured via `EP_GQL_URL`) to be accessible and functional.
Verified SafeView Analysis
The server primarily acts as a proxy for the EliteProspects GraphQL API. It uses a standard GraphQL client (graphql-request) and includes basic input validation for GraphQL query format. File system access is restricted to internal `generated` directories during build and resource loading, which is controlled. No direct use of `eval` or other obvious injection vulnerabilities are present. Security largely depends on the robustness of the underlying EliteProspects GraphQL API.
Updated: 2025-12-03GitHub→
0
0
Medium Cost
jbromfld icon
Sec8

This server acts as a Model Context Protocol (MCP) gateway, exposing internal knowledge base search (RAG) and CI/CD database query (NL2SQL) tools to AI assistants like GitHub Copilot.

Setup Requirements

  • ⚠️Requires Docker and Docker Compose for the full demo system.
  • ⚠️Dependent on external RAG (port 8000) and NL2SQL (port 8088) backend services to be running for full functionality.
  • ⚠️A PostgreSQL database (port 5432) with `pgvector` is needed for the backend services.
  • ⚠️Editor integrations (VS Code, Cursor, IntelliJ) require specific `.mcp.json` configuration or manual setup to connect to the server.
Verified SafeView Analysis
The server itself primarily acts as a proxy, delegating complex or potentially risky operations (like RAG search and SQL execution) to external backend services. It does not contain direct `eval()` or `exec()` calls within its source code. Database credentials for the demo setup are test credentials and are confined to the Docker network, not hardcoded for production. Robust production security practices, such as a reverse proxy with authentication (e.g., client certs, basic auth, API Gateway), are explicitly recommended in the `CLAUDE.md` and are essential given the server's external exposure.
Updated: 2026-01-19GitHub→
0
0
Low Cost
AlexanderChuykin icon

maixpy-mcp-server

by AlexanderChuykin

Sec8

Provides MaixPy v4 documentation to LLM models via GitHub Copilot and other clients using the Model Context Protocol (MCP).

Setup Requirements

  • ⚠️Requires GitHub Copilot Chat for full integration.
  • ⚠️Requires Docker for the recommended setup, or a local Python 3.x environment.
  • ⚠️Manual configuration of VS Code settings.json is necessary, especially for local Python execution where the server.py path must be precisely specified.
Verified SafeView Analysis
The server explicitly implements read-only access to documentation files and includes path validation to prevent directory traversal. The `docker-compose.yml` mounts the documentation directory as read-only, further enhancing container security. No obvious use of `eval` or other dynamic code execution from user input was found.
Updated: 2025-12-11GitHub→
0
0
Medium Cost
charanadi4u icon
Sec8

Provides a Model Context Protocol (MCP) server for AI models to interact with Hugging Face Hub resources (models, datasets, spaces, papers, collections) via a Groq-powered conversational client.

Setup Requirements

  • ⚠️Requires a Groq API Key (paid API) for the client component.
  • ⚠️Requires Python 3.11 or higher.
  • ⚠️The client component (gradio_mcp_client.py) expects `MODEL_NAME` and `GROQ_API_KEY` environment variables to be set.
  • ⚠️While `server.py` is the MCP server, the `client.py` provides the Gradio UI and automatically launches `server.py` as a subprocess to connect to it.
Verified SafeView Analysis
The server uses `json.loads` to parse tool call arguments from the Groq model's output. While `json.loads` itself is safe for JSON, the parsed data is then used in API calls to the Hugging Face API. The risk lies in potential malicious data within these arguments (e.g., unexpected values for parameters) that could trigger unforeseen behavior or vulnerabilities in the underlying Hugging Face API or `httpx` client. However, URL encoding is used where applicable (`quote_plus`), and no direct `eval` or command injection points for local execution are apparent. The server operates in a read-only manner for Hugging Face resources, which limits the potential impact of vulnerabilities.
Updated: 2025-11-19GitHub→
0
0
Medium Cost

Task-4

by Zehra-code743

Sec7

Automated analysis and auditing of software projects, including security, efficiency, and setup requirements.

Setup Requirements

  • ⚠️Requires Gemini API Key (Paid)
  • ⚠️Specific Python version required, indicated by .python-version file.
Review RequiredView Analysis
Actual code review of `main.py` and its dependencies is required to assess the full security posture. The presence of `temp_uploads` could pose risks if not properly secured against malicious file uploads or directory traversal. Potential network interaction as a 'server' implies additional security considerations for exposed endpoints.
Updated: 2025-11-23GitHub→
PreviousPage 555 of 713Next