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
Medium Cost
hmake98 icon

nestjs-mcp

by hmake98

Sec8

A NestJS library for integrating the Model Context Protocol (MCP) into applications, enabling decorator-based development of MCP servers that expose tools, resources, and prompts.

Setup Requirements

  • ⚠️Requires NestJS v10.0.0+, `reflect-metadata`, and `rxjs` as peer dependencies.
  • ⚠️Optional transport dependencies (`ws`, `ioredis`, `@grpc/grpc-js`, `@grpc/proto-loader`) must be installed manually for specific transports (WebSocket, Redis, gRPC) due to lazy loading.
  • ⚠️When using the `rootPath: true` option to place MCP endpoints at the root level, the NestJS `app.setGlobalPrefix()` must be configured with an `exclude: ['/mcp(.*)']` pattern.
Verified SafeView Analysis
The library is well-structured and follows NestJS best practices. It correctly uses `readFileSync` for static internal files (playground HTML) and employs `axios` for client-side introspection, which are standard practices. Transport adapters (`grpc`, `websocket`, `redis`) bind to network interfaces, which is expected server behavior; network exposure should be managed through deployment configurations. No `eval` or arbitrary code execution from untrusted input was found. Input validation for MCP methods leverages Zod schemas. No hardcoded production secrets were identified.
Updated: 2025-11-27GitHub→
0
0
Low Cost
EiriniOr icon
Sec9

Exposes fictional municipal policy documents via Model Context Protocol (MCP) for AI assistants to list, search, and retrieve programmatically.

Setup Requirements

  • ⚠️Requires Python 3.11+
  • ⚠️Requires local 'policies.json' file in the same directory as server.py
Verified SafeView Analysis
The code uses a local JSON file for data, performs simple string matching for search, and direct ID lookup for retrieval. There are no dynamic code execution (e.g., eval), hardcoded secrets, or obvious network vulnerabilities. Input handling is basic and does not appear susceptible to common injection attacks given the local file and string comparison methods. The re-loading of the policies.json file on every request (via _load_policies) is inefficient but not a security risk.
Updated: 2025-11-28GitHub→
0
0
Medium Cost
suparngp icon

mcp-servers

by suparngp

Sec4

Provides indexed documentation search capabilities for coding agents, enabling natural language queries over API references, SDKs, and technical guides.

Setup Requirements

  • ⚠️Requires OpenAI API Key (Paid) for embeddings and other LLM interactions.
  • ⚠️Requires Docker for running the local ChromaDB vector store (or an external ChromaDB instance).
  • ⚠️Requires Python 3.9+ (preferably 3.13) and Playwright browser dependencies for crawling, managed via a virtual environment setup script.
Review RequiredView Analysis
Critical vulnerabilities: Potential path traversal in file operations (reading/writing raw/cleaned documents) due to insufficient validation of 'projectName' and URL-derived paths. High risk of Cross-Site Scripting (XSS) in the web interface if unsanitized markdown content is indexed and rendered directly via 'x-html'. Insecure default: ChromaDB configured with permissive CORS ('*') in development Docker setup.
Updated: 2025-12-09GitHub→
0
0
Low Cost
markgromer icon

titan-mcp-server

by markgromer

Sec8

A Node.js server built to interact with the Model Context Protocol (MCP) for defining, validating, and serving data models, likely acting as an API layer for AI/ML contexts.

Setup Requirements

  • ⚠️Requires Node.js runtime environment (version >=18 as per SDK dependencies).
  • ⚠️A .env file is likely needed for configuration, including potential Model Context Protocol API keys or endpoints.
  • ⚠️Requires interaction with an external Model Context Protocol service.
Verified SafeView Analysis
No obvious direct security vulnerabilities like 'eval' or hardcoded secrets are present in the provided package.json and package-lock.json files. The project uses 'dotenv' for environment variables, which is good practice for managing secrets. Dependencies like 'express-rate-limit' and 'pkce-challenge' indicate an awareness of common API security practices. The actual server logic in 'server.mjs' is not available for a full code audit.
Updated: 2025-11-28GitHub→
0
0
Medium Cost
CODGODMW icon
Sec8

Provides a Model Context Protocol server that allows an agent to play Minesweeper by interacting with a local game server.

Setup Requirements

  • ⚠️Requires a separate Minesweeper game server to be running on http://localhost:5000.
  • ⚠️Requires Node.js and npm to run from source.
Verified SafeView Analysis
The server itself does not contain obvious security vulnerabilities like 'eval' or hardcoded secrets. Its primary function is to act as a proxy, forwarding commands (start_game, click, flag, unflag) to a local HTTP endpoint (http://localhost:5000/api/play) and returning the resulting image. The 'row' and 'col' arguments are numeric and used in a simple string interpolation, limiting direct injection risks from this server. However, the overall security depends heavily on the trustworthiness and security of the external Minesweeper game server running on 'http://localhost:5000'. If that external server is malicious or vulnerable, it could lead to risks, but this server's code itself is relatively safe.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
jadragfly icon

select_test_mcp

by jadragfly

Sec8

Collects, stores, and manages Web test operation reports via WebSocket and MCP protocol interfaces for local development and testing.

Setup Requirements

  • ⚠️Reports are stored in memory and will be lost after service restart.
  • ⚠️Requires Node.js 12.0 or higher.
  • ⚠️The 'ws' package is listed as a dev dependency in 'package.json' but is critical for runtime operation; it might be necessary to ensure dev dependencies are installed or move 'ws' to 'dependencies'.
Verified SafeView Analysis
The server is designed for local use (`ws://localhost:8982`) and stores data in memory. No obvious 'eval' or hardcoded secrets were found in the provided code snippets. Potential security considerations if deployed publicly without proper access controls or if excessively large/malformed input data is not handled robustly.
Updated: 2025-11-25GitHub→
0
0
Low Cost
radish2951 icon

linear-lite-mcp

by radish2951

Sec9

Provides a lightweight Model Context Protocol (MCP) server on Cloudflare Workers for interacting with Linear's issue tracking and document management features.

Setup Requirements

  • ⚠️Requires manual creation and configuration of a Linear OAuth Application (Client ID, Client Secret).
  • ⚠️Requires 4 environment variables/secrets (`LINEAR_OAUTH_CLIENT_ID`, `LINEAR_OAUTH_CLIENT_SECRET`, `COOKIE_ENCRYPTION_KEY`, `MCP_API_KEY_SECRET`) to be configured.
  • ⚠️Requires Cloudflare Workers infrastructure for full deployment, including KV Namespace and Durable Object bindings.
  • ⚠️Uses pnpm as the package manager, not npm.
Verified SafeView Analysis
The server employs robust security practices: Linear OAuth 2.0 with CSRF protection, nonce verification, and signed cookies. Sensitive Linear tokens are encrypted using AES-GCM with a randomly generated IV and stored in Cloudflare KV. API key authentication is protected by an `X-MCP-Secret` header. Input validation uses Zod, and human-readable names are resolved server-side to prevent ID injection. Callback URLs are validated to prevent open redirects. Automatic token refresh and rate limit handling enhance reliability. No 'eval' or obvious malicious patterns were found. The primary dependencies are from Cloudflare and Model Context Protocol SDKs, assumed to be secure.
Updated: 2025-12-13GitHub→
0
0
Medium Cost
pr0xc3nt4ur1 icon

mcp-hyperautomation

by pr0xc3nt4ur1

Sec8

The Hyperautomation MCP Server bridges LLM clients and HA workflows for dynamic security orchestration through natural language interactions in a SOAR-like fashion.

Setup Requirements

  • ⚠️Requires a Google Cloud Project with BigQuery API enabled, a specific dataset, and a table with a predefined schema.
  • ⚠️Requires a Google Service Account JSON key file for BigQuery access with appropriate roles, and its path must be securely configured via environment variables.
  • ⚠️Relies on pre-configured webhook endpoints for each HyperAutomation Agent, requiring setup within an external SentinelOne HyperAutomation platform.
Verified SafeView Analysis
The server uses environment variables for sensitive configurations (e.g., Google Cloud credentials path), which is good practice. It does not employ 'eval' or other obviously dangerous functions. External agents are contacted via configurable webhook endpoints. The primary security risks lie in the secure configuration and storage of the Google Cloud service account JSON key file and the security of the external HyperAutomation webhooks.
Updated: 2025-12-02GitHub→
0
0
High Cost
XXXaber icon
Sec2

Develop and manage smart multi-agent systems for AI research, supporting recursive reasoning, tool integration, and context-aware workflows.

Setup Requirements

  • ⚠️Requires Rust toolchain for `rust-research-agent`, `rig-rlm`, and `rig-deepagents` components.
  • ⚠️Requires Ollama running locally with specific models (e.g., `llama3.2`, `devstral-small-2`) pulled and served.
  • ⚠️May require API keys for external LLM providers (e.g., OpenAI, Anthropic, Google) and search services (Tavily), which are paid services.
  • ⚠️The Python components (`deepagents-cli`, `deepagents_sourcecode`) require a Python interpreter and specific package management (`uv`).
Review RequiredView Analysis
CRITICAL: The `rig-rlm` component explicitly allows for arbitrary Python code execution (`pyo3` executor) as stated in its AGENTS.md, posing a direct Remote Code Execution (RCE) vulnerability. Similarly, the `deepagents-cli` and `deepagents_harbor` libraries provide `shell_tool` and `execute` functionalities that run arbitrary shell commands via `subprocess.run` or `shlex.split`. While acknowledged in the documentation as a 'prototype' or requiring 'sandboxing for production,' this makes the system inherently unsafe for untrusted inputs without external sandboxing solutions (e.g., WASM, Firecracker, gVisor) which are not implemented in the provided code. Running this server as-is with LLM-generated code poses a significant security risk to the host system.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
consigcody94 icon

sheets-wizard

by consigcody94

Sec9

AI-powered Google Sheets automation for creating, reading, writing, adding formulas, charting, and exporting spreadsheet data.

Setup Requirements

  • ⚠️Requires Node.js 18+ to be installed locally.
  • ⚠️Requires a Google Cloud account with Google Sheets API enabled.
  • ⚠️Requires manual OAuth 2.0 credential setup and token acquisition from Google.
Verified SafeView Analysis
The server correctly delegates OAuth credential management to the client by requiring credentials as a JSON string argument for each tool call. This prevents the server from persistently storing sensitive access tokens, reducing the risk of server-side data breaches. It avoids `eval` or similar high-risk functions. However, the security of the credentials string itself (how it's obtained, stored, and passed by the client application) is outside the scope of this server, and if not handled securely by the client, could still lead to exposure.
Updated: 2025-11-25GitHub→
0
0
Low Cost
sluosapher icon
Sec8

This server provides an API to search and retrieve Minecraft Coder Pack (MCP) mapping data, enhancing accessibility and query capabilities for developers.

Setup Requirements

  • ⚠️Requires Node.js
  • ⚠️Requires `ts-node` to run directly, or compile TypeScript first.
Verified SafeView Analysis
The server uses environment variables for configuration and includes rate limiting and CORS for basic protection. No 'eval' or hardcoded secrets found. The primary data source URL is configurable via `MCP_DATA_URL`; ensure this is set to a trusted source.
Updated: 2025-11-23GitHub→
0
0
Medium Cost
Bing-Xuan-Lu icon

MCP_NodeServer

by Bing-Xuan-Lu

Sec1

This server acts as a coding agent providing tools to an orchestrating AI for full-stack PHP development, including file system management and direct database interaction.

Setup Requirements

  • ⚠️Requires a running MySQL database instance, configured for `root` access (though this is a severe security risk and should be changed).
  • ⚠️Assumes a `D:\Develop` base directory for file operations, implying a Windows-like environment or requiring manual path configuration.
  • ⚠️Relies on the `@modelcontextprotocol/sdk`, suggesting it's designed to be orchestrated by a larger AI system, likely interacting via standard I/O.
Review RequiredView Analysis
CRITICAL SECURITY VULNERABILITIES DETECTED: 1. Hardcoded Root Database Credentials: The `dbConfig` object explicitly uses `user: 'root'` with an empty password. This is an extremely dangerous practice that grants full administrative access to the database if the server or its configuration is compromised, or if an attacker can trigger database operations. 2. SQL Injection Vulnerability: The `execute_sql` tool directly executes arbitrary SQL provided in `args.sql` without any apparent sanitization or validation. This allows for direct SQL injection attacks, enabling unauthorized data manipulation, schema alteration (e.g., `DROP TABLE`), or data exfiltration if an attacker can influence the tool's input. 3. Path Traversal Vulnerability: File system tools (`list_files`, `read_file`, `create_file`, `apply_diff`) construct file paths by joining a `basePath` with user-provided `relative_path` or `path`. While `path.join` helps normalize paths, it does not inherently prevent directory traversal (`../`) sequences, potentially allowing an attacker to access, create, or modify files outside the intended `D:\Develop` base directory. 4. Powerful Unrestricted Operations: The combination of arbitrary SQL execution and unrestricted file system modification (including creating/overwriting files) makes this server a high-risk component if its inputs are not meticulously validated and authenticated. Given its role as an agent's tool, it's particularly susceptible if the orchestrating AI can be subjected to prompt injection attacks. RECOMMENDATIONS: The hardcoded credentials and direct execution of arbitrary commands (SQL, file system) are critical flaws that must be addressed before deployment. Database credentials and sensitive paths should be moved to environment variables, inputs should be rigorously validated and sanitized, and operations should be restricted with strong access controls.
Updated: 2026-01-18GitHub→
PreviousPage 704 of 760Next