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
Low Cost
Chaos2555 icon

bullet-mcp

by Chaos2555

Sec9

Validating and improving bullet point lists based on cognitive research principles, designed to be integrated as a tool for LLMs or other content generation systems.

Setup Requirements

  • ⚠️Requires Node.js (version 18+ is recommended by project dependencies and `moduleResolution: "NodeNext"`).
  • ⚠️Designed as a Model Context Protocol (MCP) server, meaning it functions as a tool called by an MCP client (e.g., an LLM orchestrator), not as a standalone GUI application for direct user input.
  • ⚠️The provided README.md describes a desktop application with `.exe`, `.dmg`, and `.zip` downloads, which contradicts the actual source code's implementation as a Node.js-based MCP server. This could lead to user confusion if the README is taken literally.
Verified SafeView Analysis
The server primarily communicates via standard I/O (`StdioServerTransport`), which limits direct external network attack surface. It includes input validation to prevent malformed data from reaching core logic. `fs.readFileSync` is used safely for `package.json`. No `eval` or obvious hardcoded secrets were found. The tool relies on the `@modelcontextprotocol/sdk`, assuming its security integrity.
Updated: 2026-01-19GitHub→
0
0
High Cost
Mutahir-15 icon
Sec8

Summarizes uploaded PDF documents and generates multiple-choice or mixed-style quizzes from the content using an AI agent.

Setup Requirements

  • ⚠️Requires Google Gemini API Key (paid service, must be set in a .env file as GEMINI_API_KEY or GOOGLE_API_KEY)
  • ⚠️Requires Python 3.13 or newer (as specified in pyproject.toml, which is a development version of Python and may not be readily available or stable)
Verified SafeView Analysis
The application sends user-uploaded PDF content to Google's Gemini API for processing, which introduces data privacy considerations inherent to its functionality. API keys for Gemini are correctly loaded from environment variables (GEMINI_API_KEY or GOOGLE_API_KEY). No 'eval' or other direct code execution vulnerabilities are present in the provided source code. PyPDF is used for text extraction, a standard library, but processing untrusted PDF files can sometimes pose risks (e.g., malformed content).
Updated: 2025-12-02GitHub→
0
0
Low Cost
Traia-IO icon
Sec7

An MCP server providing a standardized interface for AI agents and LLMs to interact with the Test Nikola 2 API, leveraging the D402 payment protocol.

Setup Requirements

  • ⚠️Requires Docker for recommended deployment or Python 3.12+ for manual installation.
  • ⚠️Requires configuration of D402 payment protocol environment variables (e.g., `SERVER_ADDRESS`, `MCP_OPERATOR_PRIVATE_KEY`, `D402_FACILITATOR_URL`), although a local setup script (`run_local_docker.sh`) attempts to auto-generate some for testing.
  • ⚠️The `run_local_docker.sh` script includes complex logic for referencing and copying the `traia-iatp` library locally, which might introduce friction if the local `IATP` repository structure is not as expected.
Verified SafeView Analysis
The server includes a `D402PaymentMiddleware` for payment verification, enhancing economic security. However, it configures CORS to `allow_origins=['*']`, `allow_methods=['*']`, and `allow_headers=['*']`, which is overly permissive and generally not recommended for production environments as it can expose the API to unauthorized cross-origin requests. Environment variables for sensitive data like `MCP_OPERATOR_PRIVATE_KEY` are used, which is good practice, but the `run_local_docker.sh` script generates *temporary* keys for local testing, requiring users to ensure proper, secure key management for production deployment. No direct use of `eval` or `exec` with untrusted input was found.
Updated: 2025-12-10GitHub→
0
0
High Cost
suvaidkhan icon

code-search-mcp

by suvaidkhan

Sec7

A high-performance semantic code search server that enables intelligent code discovery through natural language queries within a specified codebase.

Setup Requirements

  • ⚠️Requires OpenAI API Key (Paid Service)
  • ⚠️Requires Go 1.21 or higher
  • ⚠️Requires Git installed (for .gitignore integration)
  • ⚠️Currently only supports OpenAI for embeddings; local models are a roadmap item.
Verified SafeView Analysis
The server is designed to index a user-specified local codebase (`--path` flag or `CODE_SEARCH_WORKSPACE_ROOT` environment variable). Running it in an untrusted environment or pointing it to sensitive directories could lead to unintended data exposure if the server's API (localhost:8080 by default) is externally accessible without proper access controls. The `internal/fs` package executes the `git check-ignore` command, which involves external process execution, though the paths are controlled by the configured workspace. The OpenAI API key (OPENAI_API_KEY) is required and must be kept secure via environment variables.
Updated: 2025-12-15GitHub→
0
0
Medium Cost
jadjhaddad icon

mcp-dotnet-explorer

by jadjhaddad

Sec8

A Model Context Protocol (MCP) server that analyzes .NET assembly DLLs and stores metadata in a SQLite database for efficient querying.

Setup Requirements

  • ⚠️Requires .NET 9.0 SDK
  • ⚠️Requires WSL2 (if running on Windows)
  • ⚠️Requires manual configuration in Claude Code's MCP settings file with an adjusted path
Verified SafeView Analysis
The server's core function is to analyze arbitrary .NET DLLs. It uses `MetadataLoadContext` for reflection-only loading, which significantly mitigates direct code execution risks from potentially malicious DLLs compared to full assembly loading. There are no indications of `eval` usage, obfuscation, hardcoded secrets, or unintended external network communication in the provided code snippets. The primary security consideration for a tool of this nature is resource exhaustion (DoS) when analyzing extremely large or malformed DLLs, and potential information leakage if exposed to untrusted users, though it's designed for local use by a trusted client (Claude Code).
Updated: 2025-11-26GitHub→
0
0
Low Cost
Starborn icon
Sec5

Validates MCP Servers against a predefined specification of requirements to ensure compliance.

Review RequiredView Analysis
Insufficient source code provided for a comprehensive security audit. Only the README.md file was available for review. No 'eval', obfuscation, network risks, hardcoded secrets, or malicious patterns could be identified or ruled out due to the lack of code.
Updated: 2026-01-17GitHub→
0
0
High Cost
abumuslim1 icon

med-mcp-server

by abumuslim1

Sec6

Analyzing medical PDF conclusions for inconsistencies and errors using a Yandex Cloud-powered AI assistant.

Setup Requirements

  • ⚠️Requires Yandex Cloud API Key and Folder ID (Paid service for AI Studio)
  • ⚠️PDF files must be placed in the configured PDF_ROOT directory (default: data/pdfs) for analysis
  • ⚠️Requires Python 3.x and specific dependencies (dotenv, pypdf, openai, fastmcp, uvicorn)
Review RequiredView Analysis
Secrets (Yandex Cloud API Key/Folder ID) are loaded from environment variables, which is good practice. No hardcoded secrets or `eval` usage. However, the `pdf_id` argument in `analyze_pdf` and `read_pdf_text` is used directly in `PDF_ROOT / pdf_id` to construct a file path. If `pdf_id` is not properly sanitized (e.g., to prevent `../` or absolute paths) by FastMCP or the caller, this could lead to a directory traversal vulnerability, allowing access to arbitrary files outside the intended `PDF_ROOT` directory.
Updated: 2025-11-23GitHub→
0
0
Medium Cost
Danservfinn icon

claude-code-setup

by Danservfinn

Sec4

Enables Claude Code agents to make HTTP requests to retrieve information from arbitrary web URLs, facilitating data collection and real-time information access for development tasks.

Setup Requirements

  • ⚠️Requires Node.js runtime environment.
  • ⚠️Requires active network connectivity.
  • ⚠️Potential for resource exhaustion with very large web page fetches.
  • ⚠️May require proxy configuration in restrictive network environments.
Verified SafeView Analysis
A web fetching capability inherently carries risks, including Server-Side Request Forgery (SSRF) if not rigorously configured with egress filtering, potential for Denial of Service (DoS) through large file downloads or excessive requests, and information leakage if sensitive data is fetched from internal or restricted networks. Without reviewing the actual server implementation code, assumptions on input sanitization, timeout enforcement, and sandboxing cannot be definitively made. Users should be aware of the potential for unintended network access or data exposure.
Updated: 2026-01-17GitHub→
0
0
Medium Cost
MCPRUNNER icon

gossisMCP

by MCPRUNNER

Sec3

Analyzes SSIS (SQL Server Integration Services) DTSX files, providing detailed insights into package structure, data flows, control flows, logging, performance, security, and best practices, with extensible plugin support and workflow automation.

Setup Requirements

  • ⚠️Requires Go 1.19 or later.
  • ⚠️Plugin compilation (`go build -buildmode=plugin`) generates OS-specific shared libraries (`.so` on Linux/macOS, `.dll` on Windows), and the `create_analysis_rule` feature, if fully implemented, would enable on-the-fly compilation of arbitrary Go code into plugins, posing a significant security risk.
  • ⚠️Primarily tested on Windows 11; path handling and file system operations may require further validation on non-Windows platforms, potentially impacting full functionality, especially for specific tools like MSMQ analysis.
Review RequiredView Analysis
The `create_analysis_rule` tool's design permits passing Go code as a string, which is then intended to be compiled and loaded as a dynamic plugin. If the `buildPlugin` function (currently a no-op in the provided code) were fully implemented, this would introduce a critical Remote Code Execution (RCE) vulnerability. Additionally, while the README mentions plugin signature verification and sandboxing, the `LoadPlugin` implementation does not visibly enforce these security measures before dynamically loading shared libraries (`.so`/.dll files). This makes the system vulnerable to malicious plugins executing arbitrary code. Path traversal attacks are explicitly tested and mitigated in file path resolution utilities, and the server includes tools to detect hardcoded credentials and sensitive data patterns within SSIS packages, rather than storing them itself.
Updated: 2025-12-08GitHub→
0
0
Low Cost
jvermeir icon

mcp_server_test

by jvermeir

Sec6

A simple REST API service for storing and retrieving text documents, primarily used as a local test server and integrated with Model Context Protocol (MCP) plugins for AI interaction.

Setup Requirements

  • ⚠️Requires uv package manager for dependency management and execution.
  • ⚠️Requires Python 3.11 or newer.
  • ⚠️Manual configuration of Claude desktop (`claude_desktop_config.json`) with absolute paths to `uv` and the plugin folder is required for MCP integration.
  • ⚠️The server must be running on port 3000 for the MCP plugin to connect by default.
Verified SafeView Analysis
The Flask server (`test_server/server.py`) runs with `debug=True` by default, which is a significant security risk for anything beyond local development, as it can expose sensitive information and allow arbitrary code execution via the Werkzeug debugger. The MCP plugin (`plugins/rest_call_plugin/rest_call.py`) makes HTTP requests using `httpx`. While it limits the host to `http://localhost:3000`, an AI instructing it could still send arbitrary data as JSON bodies or headers to the local server, which is generally acceptable given its role as a plugin for an AI agent interacting with a local service.
Updated: 2025-12-13GitHub→
0
0
Low Cost
tbrandenburg icon

pycontextify

by tbrandenburg

Sec9

Provides a semantic search server with lightweight knowledge graph capabilities for diverse knowledge sources like codebases and documents, integrated via the MCP protocol for AI assistants.

Setup Requirements

  • ⚠️Requires 'uv' package manager for installation and execution.
  • ⚠️Requires Python 3.10 or newer (full test suite targets Python 3.13+).
  • ⚠️Requires FAISS, sentence-transformers, and PDF processing libraries (PyMuPDF, langchain-community) which may need to be installed.
  • ⚠️Embedding models (sentence-transformers) are downloaded on first run, requiring internet access and potentially causing a longer initial startup time.
  • ⚠️Requires 8 GB RAM minimum (16 GB recommended for larger corpora) as embeddings and FAISS indexes reside in-process.
Verified SafeView Analysis
The code generally follows good security practices, using `pathlib` for path manipulation and validating inputs. Hardcoded secrets are explicitly avoided, with `openai_api_key` being read from environment variables. The `BootstrapService` for downloading index archives is a potential supply chain risk if the archive URLs are untrusted, as it downloads and extracts remote content. However, it includes checksum verification to ensure integrity, which is a mitigating factor. `subprocess.run` calls are controlled and do not appear vulnerable to injection from user input within the server itself. No `eval` or obvious obfuscation patterns were found.
Updated: 2025-11-20GitHub→
0
0
High Cost
markusnieminen1 icon

tyomarkkinatori_mcp_server

by markusnieminen1

Sec8

An MCP server to query Finnish labor market job listings from the Työmarkkinatori API based on user-provided location and occupation criteria.

Setup Requirements

  • ⚠️Requires Python 3.12+
  • ⚠️Requires Claude Desktop installed and configured for MCP servers
  • ⚠️Requires Docker installed for containerized deployment, or `uv` for Python dependency management
  • ⚠️The tool `get_all_high_level_occupation_codes` actually returns 'low-level' occupation codes (from `ammatit_taso_3.json`), which is verbose and might consume more tokens than expected for a 'high-level' request.
Verified SafeView Analysis
The server includes good security practices such as input validation for codes and municipality names, using Pydantic models for API request structure with length constraints, and a timeout for external HTTP requests. When run via Docker, it uses secure container options like `--read-only` and `--cap-drop=ALL`. No direct 'eval' or hardcoded secrets were found. Data files are local and validated at startup. However, the external API call response content is not explicitly sanitized before being returned to the LLM, which could, in theory, contain malicious content if the Työmarkkinatori API were compromised (though highly unlikely for job listings).
Updated: 2025-11-25GitHub→
PreviousPage 578 of 713Next