"How to Download Videos" matching MCP servers:

Routes web requests from AI tools through Tor for anonymized fetching, with selective per-URL routing to bypass Tor-blocking sites.

Enables AI coding agents to inspect GitHub repositories and shell commands for download-and-execute payloads, obfuscation, typosquatted dependencies, autorun hooks, and fake-star signals before following or running them.

Lets AI agents check whether an EVM wallet address carries an EIP-7702 delegation across eight chains (Ethereum, Base, BNB Chain, Arbitrum, OP, Polygon, Gnosis, Unichain) and learn how to obtain a deeper paid report with delegate bytecode heuristics and risk levels. Read-only, never touching private keys or seed phrases.

Enables an AI agent to send files end-to-end encrypted, encrypting on the user's computer and keeping the download link key, password, and login away from the model.

Local-first MCP proxy with BM25 tool discovery, quarantine security, Docker isolation, OAuth support, activity logging, and web UI. Routes multiple upstream MCP servers through a single endpoint.

Enables reading and verifying C2PA Content Credentials from images and videos through both embedded manifests and invisible watermarks. Supports direct filesystem access, URL checking, and provides structured provenance data including creator identity, AI generation info, and content authenticity.

Enables AI assistants to raise, submit, approve, amend, and cancel purchase orders and onboard suppliers in ERPNext or SAP S/4HANA while enforcing procurement controls such as duplicate detection, budget limits, split-purchase checks, price tolerances, and segregation of duties.

A secure email gateway MCP server that protects AI agents from prompt injection attacks by scanning emails for malicious instructions before they reach the agent.

Checks how long ago a package version was published and returns the newest version older than a minimum age (3 days by default), so an agent avoids brand new releases when adding dependencies. Also checks lockfiles across 15 ecosystems; read-only.

A demonstration server that reveals security risks by accessing sensitive environment variables, illustrating how MCP tools can potentially leak user data without explicit consent.

Enables verification of download, installer, repository, or model URLs to determine whether the source is official, returning verdicts with confidence scores, reasons, and verifiable evidence.

An MCP server that sends plain-text Gmail messages only to a predefined allowlist, using generated recipient IDs instead of email addresses to enforce security.

Enables AI coding agents to plan, policy-check, and cost-estimate Terraform changes while requiring human approval through Slack or CLI before any terraform apply can execute.

Connects AI clients to Tenable OT Security, exposing OT/ICS asset inventory, vulnerabilities, events, policies, and findings as read tools, with an opt-in dry-run write layer for asset edits and policy management.

A vulnerable MCP server implementation that demonstrates how poor coding practices can lead to security issues like Remote Code Execution, designed for educational purposes to add numbers.

Enables secure file delivery by encrypting files client-side and generating one-time, auto-deleting download links, with tools to create sends, check their status, and revoke them.

Enables MCP clients to query Abnormal Security for threats, message search, remediation history, ATO cases, vendor/BEC data, and opt-in evidence download and response actions.

Connects multiple T3 Code MCP environments through a single authenticated endpoint, giving clients such as ChatGPT one connection with per-instance OAuth authorization and prefixed tool names to keep each environment's tools distinct.

Enables users to view personal bank accounts, balances, and transaction history through a local stdio MCP connection. It uses the non-public mobile banking API with locally stored session credentials and no payment or generic HTTP tools.

Enables AI agents to control Tor Browser with full anonymity preservation, including navigation, Tor circuit management, and traffic interception.

Enables KUIK Agent to access on-premise SMB/CIFS shares on a Windows Server using the employee's own credentials, enforcing live ACLs. Supports file operations such as list, read, write, search, move, copy, delete, and upload/download without mounting or duplicating data.

Demonstrates how to secure an MCP server with OAuth 2.1 using AWS Cognito, with support for dynamic client registration and client ID metadata documents.

MCP server for UniFi Network Controller enabling AI assistants to manage UniFi infrastructure via natural language. It supports firewall rules, IPv6, and uses lazy/eager tool modes to minimize context usage.

Enables defenders to deploy a decoy MCP tool server that records and fingerprints how LLM agents probe, escalate, and persist, without exposing real systems.

Enables users to scan AI agent skills and configuration files for hidden Unicode instructions, prompt injection, download-and-execute payloads, exfiltration patterns, and overly broad permissions before installation. It provides static audit tools for skill files, agent configs, and revealing hidden text without executing or fetching the input.

Enables grading a website's security headers with per-gap fixes and a README badge, and analyzing logs, code, configs or suspicious messages to determine what happened, how severe it is, and what to fix first. Requests are masked for sensitive data and automatically retried across multiple AI providers when one refuses, subject to a defensive-use-only policy.

Enables AI agents to call backend tools under per-agent policy, deciding which tools each agent can see, what arguments it may pass, how often it may call, and which writes wait for human approval. It also redacts secrets and PII from tool results, fences untrusted output against injection, and records every call in a hash-chained audit log.

Enables AI clients to explore and query a Cloudflare D1 database safely by listing tables, describing their columns alongside notes on how the data really behaves, and running a single read-only SELECT capped at 500 rows. Access is granted through per-person hashed tokens with human first-use approval, and the underlying read-scoped credential makes writes impossible at the Cloudflare level.

Enables MCP-compatible agents to route HTTP requests through the Tor network, providing anonymity and access to .onion services. Includes tools for fetching URLs, checking exit IP, and forcing new Tor circuits.

Tells you how you and your Claude agent actually work together. Reads CLAUDE.md, hooks, skills, memory + scheduled tasks and writes you a letter. Local-only, no API keys, no data leaves your machine.