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
consigcody94 icon

mcp-server-generator

by consigcody94

Sec8

Automates the generation of Model Context Protocol (MCP) servers from OpenAPI/Swagger specifications, enabling rapid integration for LLM agents and API orchestration.

Setup Requirements

  • ⚠️Requires network access to fetch the OpenAPI specification if a URL is provided.
  • ⚠️The generated MCP server will require installing its own language-specific dependencies (e.g., npm for TypeScript, pip for Python) after generation.
Verified SafeView Analysis
The generator itself appears safe, with no 'eval' or obvious hardcoded secrets in the provided source code. It fetches OpenAPI specs from a provided URL, which is a standard network operation. The primary security considerations would be in the quality and safety of the *generated* code for production use, especially regarding complex authentication flows, which the README notes may require manual enhancement. The generated server's security depends on the integrity of the input OpenAPI spec and the target API it integrates with.
Updated: 2025-11-24GitHub→
0
0
Low Cost
adrianolaselva icon

dataql

by adrianolaselva

Sec3

Query and transform data across multiple formats using SQL, specifically designed for efficient integration with Large Language Models.

Setup Requirements

  • ⚠️Remote data sources (S3, GCS, Azure, PostgreSQL, MySQL, MongoDB) require specific environment variables (e.g., AWS_ACCESS_KEY_ID, GOOGLE_APPLICATION_CREDENTIALS, AZURE_STORAGE_KEY) or local CLI configuration for authentication.
  • ⚠️Building from source requires Go 1.24+ and GCC (for CGO-enabled SQLite/DuckDB support).
  • ⚠️LLM integration requires configuring the specific LLM client (e.g., Claude Code, OpenAI Codex) with the MCP server details or installing skills in the LLM's environment.
Review RequiredView Analysis
The system directly executes SQL queries and utilizes file paths (for both input and output) provided by the LLM or user. This design, while enabling powerful functionality, poses significant security risks. Specifically: 1. Arbitrary File Read/Write/Delete: The `source` and `export` parameters allow the tool to read from, write to, and remove arbitrary files on the local file system (e.g., `os.Remove` in export functions). An attacker (or a misbehaving LLM) could craft paths to sensitive system files (e.g., `/etc/passwd`, `/root/.ssh/authorized_keys`) for exfiltration, modification, or deletion, assuming appropriate process permissions. 2. SQL Injection / Local File Exploits: Although SQL queries run against an embedded SQLite database, SQLite has capabilities for file I/O (e.g., `readfile`, `writefile` if extensions are loaded or custom functions are registered). A malicious SQL query could attempt to read or write local files. Additionally, providing connection strings for external databases (PostgreSQL, MySQL, MongoDB) directly from user/LLM input introduces a risk of exploiting vulnerabilities in those database systems or their drivers. 3. Resource Exhaustion: Processing large remote files from URLs or cloud storage (S3, GCS, Azure) specified by an attacker could lead to excessive disk/memory usage. It is critical to run this tool in a tightly sandboxed environment (e.g., a Docker container with restricted volume mounts, limited network access, and a non-privileged user) and only with trusted LLM inputs.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
odenizo icon

mcp-hq

by odenizo

Sec7

MCP server providing persistent code context, memory, and semantic search capabilities for AI development tools to enhance agent performance.

Setup Requirements

  • ⚠️Requires `CONTEXTSTREAM_API_KEY` or `CONTEXTSTREAM_JWT` for authentication (obtained from contextstream.io).
  • ⚠️Requires Node.js version 18+ and npm 10+ to run locally.
  • ⚠️Automated setup script `install-all.sh` recommends `jq` for seamless JSON configuration.
Verified SafeView Analysis
Secrets (API key/JWT) are managed via environment variables, not hardcoded. Installation scripts create backups before modifying configuration files. The core MCP server logic for `@contextstream/mcp-server` is an external NPM package, not directly auditable in this source code. Network access to `https://api.contextstream.io` is required for functionality.
Updated: 2026-01-06GitHub→
0
0
Low Cost
vgunti1982 icon
Sec1

Provides log search capabilities, including regex-based keyword search and natural language semantic search, for local log files.

Setup Requirements

  • ⚠️Requires an internet connection for the initial download of the 'all-MiniLM-L6-v2' SentenceTransformer model for semantic search.
  • ⚠️Log files must be present in the configured LOG_DIRECTORY for the server to perform useful operations.
Review RequiredView Analysis
CRITICAL VULNERABILITY: The `read_resource` function, which calls `log_resource.tail_log`, is susceptible to path traversal. The `uri.replace("log:///", "")` sanitization is insufficient to prevent an attacker from using `../` sequences in the URI (e.g., `log:///../../../../etc/passwd`) to read arbitrary files outside the designated log directory. This allows unauthorized access to sensitive system files. Additionally, the `LogSearchTool` uses `re.compile` directly on user-provided regex patterns, which could potentially expose the server to a Regular Expression Denial of Service (ReDoS) attack, although this is less critical than the path traversal.
Updated: 2025-12-14GitHub→
0
0
Low Cost

git-context

by osick

Sec10

Unable to determine the use case due to the absence of file content or a README.

Verified SafeView Analysis
No files were provided for analysis, therefore no security risks like 'eval', obfuscation, or network risks could be identified within the project's codebase. The score of 10 reflects the absence of identifiable risks *from the provided content*.
Updated: 2025-11-22GitHub→
0
0
Low Cost
AmitafAdir-RidaFatima icon

mcp-shark-viewer-vscode

by AmitafAdir-RidaFatima

Sec8

Inspect and analyze Model Context Protocol (MCP) traffic directly within Visual Studio Code, providing real-time network monitoring and debugging capabilities.

Setup Requirements

  • ⚠️Requires Node.js Version 14.x or higher to run `npx` command.
  • ⚠️Requires Visual Studio Code Version 1.56 or later.
  • ⚠️Relies on the `npx` command to download and execute the `@mcp-shark/mcp-shark` package, necessitating an internet connection for the initial server startup.
Verified SafeView Analysis
The extension spawns an external process `npx @mcp-shark/mcp-shark@latest` to run the core server functionality. While this command is hardcoded and not directly susceptible to user input injection, it relies on the integrity and security of the `@mcp-shark/mcp-shark` package from npm. Stopping the server involves `node:child_process.exec` with platform-specific commands (taskkill for Windows, kill for Linux/macOS) targeting a hardcoded port (9853), which is generally safe. There are no obvious hardcoded secrets or arbitrary code execution vulnerabilities found within the provided source code.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
bjoxiah icon
Sec9

Provides a Model Context Protocol (MCP) server for retrieving real-time and historical stock market data and company sentiment using the Alpha Vantage API.

Setup Requirements

  • ⚠️Requires Python 3.10 or higher.
  • ⚠️Requires Poetry for dependency management.
  • ⚠️Requires an Alpha Vantage API key (free tier has a limit of 25 requests/day).
  • ⚠️Requires manual configuration in Claude Desktop's `claude_desktop_config.json` with absolute paths for the virtual environment and project directory.
Verified SafeView Analysis
The server loads sensitive API keys from environment variables, which is a good practice. Error logging specifically redacts the API key from URLs. It uses the `httpx` library for asynchronous HTTP requests with a reasonable timeout. There are no obvious 'eval' statements, obfuscation, or other malicious patterns found in the provided source code. Security risk is primarily dependent on the security of the Alpha Vantage API itself and correct environment variable configuration.
Updated: 2025-11-23GitHub→
0
0
Medium Cost
itripleg icon

moha-maven

by itripleg

Sec8

Maven is an autonomous AI Chief Financial Officer (CFO) assistant that leverages LLMs and MCP for persistent identity, memory, financial decision-making, and treasury operations for the Motherhaven platform.

Setup Requirements

  • ⚠️Requires Docker, PostgreSQL, and Redis for full functionality (orchestrated via docker-compose).
  • ⚠️Requires an Anthropic API Key (paid LLM service) for core AI capabilities.
  • ⚠️Requires the 'mcp' Python package (likely a proprietary client library from Anthropic).
  • ⚠️Requires an EMAIL_API_SECRET for interaction with the motherhaven.app email system.
Verified SafeView Analysis
The project uses environment variables for sensitive API keys (Anthropic, Email API), which is good practice. File uploads (for chart analysis) are handled with `secure_filename` and a restricted set of allowed extensions. External network communication (email API, Hyperliquid API) is standard, but relies on the security of those external services and the provided API keys. Git-first persistence uses `git` commands via `subprocess.run`, which could be a risk if commit messages or file paths were unsanitized user input, but here the commit messages are programmatically generated. The Flask API and MCP server are designed to be exposed locally (or within a Docker network), but if exposed to the public internet without proper firewall rules, they would present a vulnerability. Overall, it follows reasonable security practices for its domain, but like any system handling financial transactions and API keys, caution is advised regarding network exposure and key management.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
Jaskey15 icon

n8n-mcp-server

by Jaskey15

Sec9

Enables Claude to list, inspect, and monitor workflows in a self-hosted n8n instance.

Setup Requirements

  • ⚠️Requires a self-hosted n8n instance with API access and a generated API key.
  • ⚠️Requires Node.js 18 or higher to run.
  • ⚠️Requires manual configuration in Claude Desktop's `claude_desktop_config.json` file, specifying an absolute path to the built server and setting environment variables.
Verified SafeView Analysis
The server demonstrates good security practices by using environment variables for sensitive API keys (`N8N_URL`, `N8N_API_KEY`), performing input validation for tool arguments, and handling various API errors gracefully. It explicitly focuses on read-only operations (inspection and monitoring), significantly reducing the attack surface. No `eval` or `child_process` executions of untrusted input were found. The `README` also provides explicit security recommendations, indicating developer awareness.
Updated: 2025-12-14GitHub→
0
0
Medium Cost
marc-shade icon

universal-ai-chat

by marc-shade

Sec9

Facilitates real-time, cross-platform communication and shared context/memory between different AI assistants like Claude Code, OpenAI Codex CLI, and Google Gemini CLI.

Setup Requirements

  • ⚠️Requires a running Qdrant vector database instance (defaults to localhost:6333).
  • ⚠️Requires `sentence-transformers` or `fastembed` for embedding text (which are installed via `pip install -e '.[vector]'`).
  • ⚠️Requires Python 3.10 or higher.
  • ⚠️The `STORAGE_BASE` environment variable (defaults to `/mnt/agentic-system`) must be a writable directory for SQLite databases.
Verified SafeView Analysis
The server uses SQLite for persistence and Qdrant for vector memory. SQL queries utilize parameter binding to prevent injection. Configuration relies on environment variables, which should be securely managed by the user/system. There is no obvious use of `eval` or `exec` on untrusted input, nor are sensitive hardcoded secrets present. The main `server.py` processes tool calls defined in the code, rather than dynamically executing arbitrary code from agents. Qdrant connection defaults to localhost, implying an expectation of a local/secured Qdrant instance.
Updated: 2025-11-29GitHub→
0
0
Low Cost
agentplexus icon

mcpkit

by agentplexus

Sec9

A toolkit for building MCP (Model Context Protocol) applications and servers in Go, supporting both direct in-process function calls (library mode) and standard MCP transports (server mode) with OAuth 2.1 authentication.

Setup Requirements

  • ⚠️Requires Go 1.24+ and MCP Go SDK v1.2.0+.
  • ⚠️NGROK_AUTHTOKEN environment variable is required if `ngrok` tunneling is used; custom ngrok domains may require a paid plan.
  • ⚠️Proper OAuth 2.1 configuration (Issuer, ClientID, ClientSecret, Users, RedirectURIs) is critical for public servers, especially when integrating with clients like ChatGPT.com.
Verified SafeView Analysis
The project implements OAuth 2.1 with PKCE, Dynamic Client Registration (DCR), and Protected Resource Metadata (RFC 9728, 8414, 7591, 7636). It utilizes cryptographically secure token generation (`crypto/rand`) and constant-time comparisons (`crypto/subtle`) for sensitive operations. A critical open URL redirect vulnerability (CWE-601) in the `isValidRedirectURI` function was identified and promptly fixed in v0.3.1, demonstrating a proactive approach to security. The `oauth2.Config` allows for basic authentication via a `Users` map, which requires careful management of credentials by the implementer, though a custom `Authenticator` can be provided for more robust solutions. `ngrok` integration requires a securely managed `NGROK_AUTHTOKEN`.
Updated: 2026-01-19GitHub→
0
0
Medium Cost
Konkuk-SWA-2025 icon

MCP_server

by Konkuk-SWA-2025

Sec3

This server provides an inventory management and forecasting system, interacting with Google Sheets for data storage and SQLite for user configuration and logs, all exposed as an MCP service.

Setup Requirements

  • ⚠️Requires a Google Service Account JSON key file, hardcoded to 'bold-tooling-466206-a9-960a00bb4c78.json' in the root directory.
  • ⚠️The Google Service Account must have edit permissions for the target Google Sheets.
  • ⚠️The Prophet library, used for forecasting, can have complex installation requirements, potentially needing C++ compilers (like gcc or clang).
Review RequiredView Analysis
CRITICAL: The Google Service Account JSON key file path (`KEY_FILE_PATH`) is hardcoded in the source code. This is a severe security vulnerability as it exposes sensitive credentials and should be loaded from environment variables or a secure secret management system. The application also logs potential errors, which is good, but the core credential handling is unsafe.
Updated: 2025-12-02GitHub→
PreviousPage 399 of 760Next