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
jpkaladjian icon

mcp-server-qobra

by jpkaladjian

Sec9

Enables AI assistants to securely read sales compensation data from Qobra via the Model Context Protocol (MCP).

Setup Requirements

  • ⚠️Requires a Qobra API Key (obtained from Qobra account settings)
  • ⚠️Requires Python 3.10 or higher
  • ⚠️An active Qobra account is necessary to use this server
Verified SafeView Analysis
The server is explicitly designed for 'READ-ONLY MODE', preventing any write, update, or delete operations on Qobra data, which is a significant security control. It uses environment variables (QOBRA_API_KEY) for sensitive credentials, preventing hardcoding. The `qobra_client.py` strictly enforces GET requests only. It uses `httpx` for API communication, which is a modern, secure HTTP client. No `eval`, `exec`, or other high-risk functions are used. Input parameters for tools are type-hinted and processed, reducing injection risks. Error handling for API calls is present. The architecture is straightforward and follows best practices for secure API integration. The only potential risk would be if the Qobra API itself had vulnerabilities or if the API key were compromised externally; the server mitigates risks on its side.
Updated: 2026-01-16GitHub→
0
0
Medium Cost
joe-watkins icon

wcag-mcp

by joe-watkins

Sec8

Provides comprehensive WCAG 2.2 guidelines, techniques, glossary terms, and Understanding documentation to agentic systems via a Model Context Protocol (MCP) server.

Setup Requirements

  • ⚠️The data (wcag.json) must be built/updated by running `npm run build` manually after `npm install` if not deploying to Netlify, as `npm install` does not automatically trigger the data build process (despite what the README implies).
  • ⚠️Requires Git to be installed on the system for managing and updating the W3C WCAG git submodule during the data build process.
  • ⚠️Requires Node.js version 18.0.0 or higher.
Verified SafeView Analysis
The server primarily performs lookups on pre-loaded static WCAG data, reducing runtime security risks. User input is parsed as JSON, and tool arguments are handled internally without apparent injection vulnerabilities. The 'execSync' command is used in build-time scripts for data acquisition (git submodule updates, fetching W3C JSON, parsing HTML), not at runtime based on arbitrary user input. Cross-Origin Resource Sharing (CORS) is set to allow all origins ('*'), which is typical for a public API but means no origin-based access control is enforced at the server level.
Updated: 2026-01-16GitHub→
0
0
Low Cost
Sec8

Demonstrates streaming queries with batching for efficient retrieval of large JSON result sets from a relational database using the Gilhari RESTful ORM microservice framework.

Setup Requirements

  • ⚠️Docker is required to build and run the microservice.
  • ⚠️Gilhari SDK and JDK 1.8+ are required for compiling source code if modifications are made.
Verified SafeView Analysis
Standard RESTful microservice security practices apply if exposed externally. The `jdx_force_create_schema` parameter should be set to `false` in production to prevent unintended schema recreation.
Updated: 2025-11-18GitHub→
0
0
High Cost
PolecatWorks icon

chatagent-root

by PolecatWorks

Sec7

Build and deploy an AI-powered conversational bot for Microsoft Teams, leveraging LangChain/LangGraph for LLM interaction and tool execution.

Setup Requirements

  • ⚠️Requires API keys for LLM providers (e.g., Google GenAI, Azure OpenAI), which are typically paid services.
  • ⚠️Requires registration and setup in Azure Bot Services for MS Teams integration (App ID, App Secret, Tenant ID, Messaging Endpoint).
  • ⚠️Deployment primarily targets Kubernetes using Helm charts, requiring kubectl and helm CLI tools.
  • ⚠️Python 3.12+ is required for the application.
  • ⚠️Local development with MS Teams requires a reverse proxy like ngrok.
Verified SafeView Analysis
The project uses Pydantic's SecretStr for API keys and integrates with Kubernetes secrets for deployment, which are good practices. There are no obvious hardcoded secrets or direct uses of 'eval' or 'exec' on user input. The primary security consideration for this type of LLM agent is the inherent risk of prompt injection leading to unintended tool execution. Tools like 'delete_record_by_id' (even if mocked in the provided code) highlight the need for robust access control and careful sandboxing of real-world tool implementations. The 'interactivedebugger' in CLI is opt-in and primarily for development.
Updated: 2026-01-18GitHub→
0
0
Medium Cost
brynsp icon

mcp-ynab

by brynsp

Sec9

Integrates the YNAB API for read-only budgeting data access via Model Context Protocol, allowing AI assistants to query YNAB data.

Setup Requirements

  • ⚠️Requires Python 3.10 or higher
  • ⚠️Requires a YNAB Personal Access Token (obtained from YNAB developer settings)
  • ⚠️Docker recommended for containerized deployment
Verified SafeView Analysis
The server is explicitly designed for read-only access to the YNAB API, minimizing risks of data modification. The YNAB API token is securely handled via environment variables, not hardcoded. Good container security practices are mentioned in the documentation, including running as a non-root user and installing only necessary dependencies. No obvious malicious patterns or unsafe functions like `eval` were found in the provided source code. Input arguments for tools are passed directly to the YNAB client, relying on the YNAB API for input validation.
Updated: 2025-11-26GitHub→
0
0
Low Cost
edgarlopezcalomarde icon

mcp-for-sql-server

by edgarlopezcalomarde

Sec3

This server provides tools for an AI agent to interact with and manage a SQL Server database, enabling schema querying, table creation, data insertion, and execution of raw SQL queries.

Setup Requirements

  • ⚠️Requires Docker to run the SQL Server database container.
  • ⚠️Requires Bun runtime for development scripts and building, though the compiled output can be run with Node.js.
  • ⚠️Requires environment variables: DB_USER, DB_PASSWORD, DB_HOST, DB_NAME, DB_PORT.
Review RequiredView Analysis
The `compose.yml` uses a hardcoded default SA password ('PassSegura777') for the SQL Server database, which is insecure for production environments. More critically, the `create-table` and `insert-data` tools are vulnerable to SQL injection: they construct SQL queries by directly interpolating user-provided `tableName` and column names (e.g., `campos.nombre`) into the SQL string via `prisma.$queryRawUnsafe` without proper sanitization or escaping. This allows an attacker to execute arbitrary SQL commands by manipulating these input parameters. The `execute-raw-queries` tool explicitly allows raw queries, making its security dependent on the trustworthiness of its caller.
Updated: 2025-11-24GitHub→
0
0
High Cost
alkampfergit icon
Sec8

An MCP server demonstrating Semantic Kernel integration for AI-powered task management, exposing intelligent tools to AI clients like GitHub Copilot.

Setup Requirements

  • ⚠️Requires .NET 10.0 SDK (preview 6 or higher).
  • ⚠️AI features (natural language processing, agent conversation) require a paid OpenAI or Azure OpenAI API Key.
  • ⚠️Primarily designed for integration and testing with VS Code and the GitHub Copilot extension.
Verified SafeView Analysis
The project uses environment variables for API keys in its detailed guides, which is good practice. However, a quick start section suggests directly hardcoding API keys in `SemanticKernelAgentTools.cs`, which is a security risk if committed to version control. The server primarily communicates via stdio (local process), reducing network exposure. No 'eval' or obfuscation found.
Updated: 2025-11-27GitHub→
0
0
Medium Cost
xbgmsharp icon
Sec9

Provides AI agents with read-only access to marine vessel data from PostgSail, enabling them to search logs, moorages, and monitor vessel systems for daily briefings and historical analysis.

Setup Requirements

  • ⚠️Requires a Model Context Protocol (MCP) compatible AI platform (e.g., Claude App, Claude AI, OpenAI GPT with remote connectors).
  • ⚠️Requires a PostgSail API instance accessible via POSTGSAIL_URL.
  • ⚠️Requires a PostgSail authentication token (POSTGSAIL_TOKEN) or username/password (POSTGSAIL_USER and POSTGSAIL_PASS) for API access.
  • ⚠️Using remote AI connectors may require a paid plan on the AI platform.
Verified SafeView Analysis
The server handles sensitive PostgSail authentication tokens, which are properly configured via environment variables and marked as sensitive in the manifest, reducing direct exposure risks. It operates over STDIO, which is generally more secure than exposing network ports. No usage of 'eval' or obvious obfuscation was found. The primary external dependency for data is the PostgSail API itself, and security largely depends on the integrity and configuration of that upstream service and the provided POSTGSAIL_URL. Input validation is present in tool schemas.
Updated: 2026-01-07GitHub→
0
0
Low Cost
rkumarus040599 icon

prk-mcp-weather-matcher

by rkumarus040599

Sec9

This project demonstrates converting a function to an MCP server, integrating it with an MCP client like Claude Code Desktop to fetch weather information.

Setup Requirements

  • ⚠️Python 3.12+ required
  • ⚠️Requires 'uv' for package management (as specified in README)
Verified SafeView Analysis
The code properly sanitizes user input (location) using `strip()`, `replace()`, and `urllib.parse.quote()` before constructing the URL for the external API call, significantly reducing URL injection risks. No 'eval' or similar dangerous patterns were found. The use of `urllib.request` is standard. No hardcoded secrets were identified in the provided code.
Updated: 2025-11-20GitHub→
0
0
Medium Cost
mari2020 icon
Sec8

This Spring Boot application provides a natural language interface, powered by an AI chat model and tool calling, for querying and managing employee information.

Setup Requirements

  • ⚠️Requires Java Development Kit (JDK) 17+.
  • ⚠️Requires a running Ollama server or compatible LLM API endpoint.
Verified SafeView Analysis
No 'eval' or similar dangerous patterns were found. No hardcoded secrets. The primary concern is that the 'seedDatabase' tool, although described as 'Dev-only', is exposed via the AI model, allowing data modification (insertion of sample employee data) through a prompt. While this is less critical for a development/demo setup with a local LLM like Ollama, it could be a security vulnerability in a production environment if not properly restricted. The use of Spring Data R2DBC helps mitigate SQL injection risks.
Updated: 2025-11-22GitHub→
0
0
Low Cost
jmfrank63 icon

vscode-mcp-windbgX

by jmfrank63

Sec8

Integrates the mcp-windbgX MCP server into VS Code for Windows debugging, supporting CDB, WinDbg, and Time Travel Debugging (TTD).

Setup Requirements

  • ⚠️Requires Windows 10 or later.
  • ⚠️Requires Windows Debugging Tools (part of Windows SDK) to be installed.
  • ⚠️Requires Node.js for running the managed MCP server.
  • ⚠️The mcp-windbgX server artifact is downloaded from GitHub releases, requiring network access for initial setup.
Verified SafeView Analysis
The extension automatically downloads and manages the mcp-windbgX server from GitHub releases. This introduces a supply chain risk, as a compromised GitHub repository could lead to the execution of malicious server code. The extension utilizes `execAsync` and `spawn` for system tool detection and server process management, which are necessary for its core functionality but increase the attack surface. Environment variables like `GITHUB_TOKEN` can be used optionally for GitHub API authentication, primarily for rate limits, but are not strictly required for basic functionality.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
GaijinEntertainment icon

pararam-nexus-mcp

by GaijinEntertainment

Sec7

This MCP server provides a programmatic interface for interacting with the Pararam.io communication platform, enabling message, chat, file, and user management.

Setup Requirements

  • ⚠️Requires a pararam.io account.
  • ⚠️Requires `PARARAM_LOGIN` and `PARARAM_PASSWORD` environment variables to be set for authentication (and optionally `PARARAM_2FA_KEY` for 2FA).
  • ⚠️Requires `uv` package manager (or Python 3.11+ and standard `pip` installation).
  • ⚠️File download size limit of 1MB.
Verified SafeView Analysis
The server uses Pydantic for robust input validation on chat and post IDs, and URL patterns, which is a strong positive for security, mitigating common injection risks. Credentials (`PARARAM_LOGIN`, `PARARAM_PASSWORD`, `PARARAM_2FA_KEY`) are correctly loaded from environment variables. Session cookies are persisted securely. However, the `upload_file_to_chat` and `download_post_attachment` tools accept `file_path` and `output_path` parameters, respectively, which allow an agent to specify arbitrary local file paths. While `file_content` uploads use safe temporary files, direct `file_path` usage in uploads and `output_path` in downloads, without strict path sanitization or restriction to a dedicated agent-controlled directory, could lead to information disclosure or unauthorized file overwrites if the server is run with elevated permissions in a vulnerable environment. The 1MB file size limit on downloads is a good defense against resource exhaustion.
Updated: 2025-12-05GitHub→
PreviousPage 523 of 760Next