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
Sandeep850-bit icon
Sec7

A Java-based test automation framework supporting web UI testing with Playwright, data-driven testing, and optional integration with an external Model Context Protocol (MCP) server for remote execution of browser actions.

Setup Requirements

  • ⚠️Requires Java 11+ and Maven 3.6+.
  • ⚠️Playwright browsers must be installed explicitly via 'mvn exec:java -Dexec.mainClass=com.microsoft.playwright.CLI -Dexec.args="install"'.
  • ⚠️If MCP mode is enabled (`mcp.enabled=true`), an external, separately developed MCP server is required to be running and accessible at the configured `mcp.endpoint`.
  • ⚠️Test data files (`testdata.xlsx`, `testdata.properties`) need manual creation or population for data-driven tests.
Verified SafeView Analysis
The provided code is primarily a client for an external MCP server, not the server itself. While the client framework itself has no malicious patterns, hardcoded *sample* credentials (`superuser@sks`, `Welcome1`) are present for testing purposes in `AppConstant.java` and `TestConfiguration.java` which should be overridden or managed securely in production test environments. The `mcp.endpoint` is configurable (`http://localhost:8080` by default); configuring it to an untrusted or vulnerable server could lead to browser control by an attacker managing that endpoint. Users should ensure the MCP server and its configuration are trusted.
Updated: 2025-12-01GitHub→
0
0
Low Cost
jeff-atriumn icon

annex-gmail-mcp

by jeff-atriumn

Sec9

Orchestrates Gmail API functionality via an MCP server for reading, drafting, and sending emails, integrated with the RAM orchestration layer.

Setup Requirements

  • ⚠️Requires manual Google Cloud Project setup, including enabling Gmail API and configuring OAuth Consent Screen.
  • ⚠️Requires a manual, browser-based OAuth 2.0 authentication flow on first run to generate a persistent token file.
  • ⚠️Requires secure storage of Google API client credentials and OAuth token files in a user-specific directory (e.g., ~/.config/ram/).
  • ⚠️The 'gmail_send' tool will execute if called; RAM (the orchestrator) is solely responsible for gating access with user approval, not this server.
Verified SafeView Analysis
The project design emphasizes a clear trust model, where RAM (the orchestration layer) is responsible for enforcing user approval for email sending, not this MCP server. Credentials are handled via OAuth2 and stored in the user's home directory outside the repository, explicitly with a .gitignore recommendation. The server does not store email content locally, reducing data exposure risk. No 'eval' or other highly dangerous patterns are mentioned or implied in the provided design/setup documentation.
Updated: 2025-12-02GitHub→
0
0
Low Cost
Shubham5070 icon

MCP_SERVER

by Shubham5070

Sec8

Provides a Micro-Agent Control Plane (MCP) server to expose smart meter data, usage calculations, and billing information as callable tools.

Setup Requirements

  • ⚠️Requires 'fastmcp' and 'sqlalchemy' Python packages to be installed.
  • ⚠️Initializes and seeds a local SQLite database ('smart_meters.db') upon first run.
Verified SafeView Analysis
The application uses SQLAlchemy ORM which mitigates common SQL injection vulnerabilities. Environment variables are used for port configuration. There are no hardcoded secrets or 'eval'/'exec' patterns found in the provided code. The primary security considerations would be the underlying FastMCP framework (not provided) and potential for data exposure if not properly authenticated/authorized in a production environment, although no authentication is present in this snippet.
Updated: 2025-12-03GitHub→
0
0
High Cost
arthurfantaci icon

mcp-snapshot-server

by arthurfantaci

Sec9

Transforms Zoom meeting transcripts into instant AI-powered insights or comprehensive 11-section Customer Success Snapshots.

Setup Requirements

  • ⚠️Requires Anthropic API Key (Paid Service) for Claude AI access.
  • ⚠️Requires manual creation and configuration of a Zoom Server-to-Server OAuth app with specific recording and user scopes (multi-step process involving Zoom Marketplace).
  • ⚠️Requires manual download of spaCy and NLTK data models after installation.
Verified SafeView Analysis
The server demonstrates strong security practices: uses environment variables for API keys (e.g., Anthropic, Zoom) via Pydantic settings, includes explicit input validation for VTT files and paths, implements robust error handling with retries, and outputs structured JSON logs. Data is stored temporarily in-memory with a TTL, and the project explicitly documents security best practices and PII handling. No 'eval' or malicious patterns were found. Assumes secure configuration of environment variables and Zoom OAuth application.
Updated: 2025-11-25GitHub→
0
0
Medium Cost
j0hanz icon
Sec9

Provides an in-memory server for structured, sequential thinking with revision support, exposing a single MCP tool for AI agents.

Setup Requirements

  • ⚠️Requires Node.js version >= 20.0.0
  • ⚠️Requires an MCP client (e.g., VS Code, Cursor, Claude Desktop, Windsurf) for interaction
  • ⚠️In-memory thought history is ephemeral and lost on server shutdown
Verified SafeView Analysis
The server itself runs over stdio, limiting direct network exposure. Input validation is performed using Zod schemas, which helps prevent common injection vulnerabilities. No hardcoded secrets or 'eval' statements are found in the core application logic. The 'execSync' command is present in a benchmark script for CPU pinning, but this is a development utility and not part of the deployed server's runtime, thus it does not impact the server's operational security. Overall, good security practices are evident for its design.
Updated: 2026-01-19GitHub→
0
0
Low Cost
apisani1 icon

mcp-multi-server

by apisani1

Sec7

Orchestrates multiple Model Context Protocol (MCP) servers, aggregating their capabilities (tools, resources, prompts) for unified access and intelligent routing, particularly useful for AI agents.

Setup Requirements

  • ⚠️Requires OPENAI_API_KEY environment variable for OpenAI integration (a paid service).
  • ⚠️Requires Python 3.10 or higher.
  • ⚠️Requires 'poetry' installed and configured, and project dependencies ('poetry install --extras examples') for running example servers and clients.
Verified SafeView Analysis
The 'eval' function is used in 'tests/conftest.py' within a mock for a 'calculate' tool. This is in test code, not directly in the production client library, and its purpose is for mocking a tool invocation. While 'eval' can be highly dangerous if used with untrusted input in production, its isolated use in testing does not directly expose the 'mcp-multi-server' client library to runtime 'eval' vulnerabilities. A key aspect of this library is its reliance on 'mcp_servers.json' to define commands for starting external MCP server processes. This design implies a trust relationship: the user (or system administrator) is responsible for ensuring that the commands specified in 'mcp_servers.json' are safe and trustworthy, as the MultiServerClient will execute them. Maliciously crafted server configurations could lead to arbitrary code execution outside the scope of the library itself.
Updated: 2025-12-08GitHub→
0
0
Medium Cost
Hsidhu icon
Sec6

Integrate LLMs with Invoice Shelf for managing customers, invoices, and estimates through a Model Context Protocol (MCP) server.

Setup Requirements

  • ⚠️Requires Node.js v18 or higher.
  • ⚠️Requires an existing Invoice Shelf instance.
  • ⚠️Requires an API Token from Invoice Shelf, which might need to be generated using provided scripts and Invoice Shelf credentials (username/password).
  • ⚠️Disabling SSL certificate validation (`NODE_TLS_REJECT_UNAUTHORIZED=0`) is enabled by default in `src/index.ts` for local development/testing, posing a critical security risk if used in production.
Verified SafeView Analysis
The server explicitly sets `process.env.NODE_TLS_REJECT_UNAUTHORIZED = "0";` in `src/index.ts`, which disables SSL certificate validation. While the README warns against using this in production, its direct inclusion in the main entry point is a critical security vulnerability, as it makes the application susceptible to Man-in-the-Middle (MITM) attacks if deployed with this setting. No `eval` or obfuscation was found. API tokens are managed via environment variables, which is a good practice.
Updated: 2025-11-24GitHub→
0
0
Low Cost

golang-image

by transform-ia

Sec5

Creates a Docker image for a Go development environment or a Go application, facilitating containerized deployment.

Setup Requirements

  • ⚠️Requires Docker installed on the host system.
  • ⚠️The Docker image must be built locally before it can be run, using 'docker build'.
Review RequiredView Analysis
Cannot perform a comprehensive security audit without access to the Dockerfile content and any potential Go source code. The project is assumed to be a base Go image or a simple application. No 'eval' or obfuscation detected due to the lack of code access. Score is neutral due to unknown factors.
Updated: 2025-11-18GitHub→
0
0
Medium Cost

spotify-mcp

by cstair-23

Sec7

A modular command processor or control panel for interacting with Spotify services, enhanced with AI capabilities.

Setup Requirements

  • ⚠️Requires API Keys (e.g., Spotify, Claude AI)
  • ⚠️Python environment and dependencies (pip install -r requirements.txt)
Verified SafeView Analysis
Cannot definitively check for 'eval' or obfuscation without source code. '.env.example' suggests external API integration, requiring secure handling of credentials. AI integration (Claude) might introduce prompt injection or data privacy considerations, which are inherent to LLM-powered applications.
Updated: 2025-11-18GitHub→
0
0
Medium Cost
k5tuck icon
Sec8

Provides a Model Context Protocol (MCP) interface to the Binelek Platform's knowledge graph, search, AI, and data pipeline services.

Setup Requirements

  • ⚠️Requires a running Binelek API Gateway instance (e.g., at `http://localhost:8092`)
  • ⚠️Requires a JWT token for full functionality, obtained via Binelek platform authentication
  • ⚠️Requires Node.js 18.0.0 or higher
Verified SafeView Analysis
The server acts as a proxy, forwarding requests to a configurable API Gateway. It does not contain hardcoded secrets or use dangerous functions like `eval`. All external calls go to `BINELEK_GATEWAY_URL`. Direct arguments from the MCP client are passed to gateway functions (e.g., Cypher queries, YAML content), which could pose a risk if the backend services (reachable via the gateway) are not robustly validating or sanitizing these inputs. However, this is inherent to powerful tool-calling agents and implies the backend services are responsible for deep input validation.
Updated: 2025-11-22GitHub→
0
0
Low Cost
stevensblueprint icon

blueprint_mcp

by stevensblueprint

Sec9

Minimal Model Context Protocol (MCP) server for integrating custom tools with AWS Bedrock AgentCore.

Setup Requirements

  • ⚠️Python 3.10+ required for AWS Bedrock AgentCore deployment.
  • ⚠️AWS credentials must be configured for cloud deployment.
  • ⚠️An OAuth provider (e.g., AWS Cognito) is required for production deployment with AWS Bedrock AgentCore.
Verified SafeView Analysis
The provided server code is minimal, defining simple, non-malicious tools. It relies on the `mcp` library for protocol handling and `FastMCP` for the server implementation, which are presumed to be robust. No 'eval' or direct dangerous patterns are observed. The server itself does not handle sensitive data or external APIs directly. Deployment notes indicate OAuth is supported by AgentCore for production environments, enhancing security.
Updated: 2025-12-10GitHub→
0
0
Low Cost
franciscocunha55 icon

kubernetes-mcp-server

by franciscocunha55

Sec2

This server exposes a set of Kubernetes cluster management tools (e.g., listing namespaces) and a basic 'hello world' utility via the Mark3Labs Protocol (MCP) over standard I/O or HTTP.

Setup Requirements

  • ⚠️Requires access to a Kubernetes cluster.
  • ⚠️Relies on a valid `~/.kube/config` file for Kubernetes authentication.
  • ⚠️If building from source, requires a Go development environment.
Review RequiredView Analysis
The server, when run in HTTP mode, exposes Kubernetes API functionality (e.g., listing namespaces) over an unauthenticated endpoint at `http://localhost:8080/mcp`. This allows any entity with network access to the server to perform Kubernetes operations with the permissions granted by the `~/.kube/config` file used by the server. This is a critical security vulnerability for a network-facing service and makes it unsafe to expose to untrusted networks or users without additional, external authentication/authorization layers.
Updated: 2025-12-10GitHub→
PreviousPage 505 of 760Next