"Understanding local computer vision models like YOLO" matching MCP servers:

A zero-dependency Node.js playground for debugging how MCP clients authenticate to an MCP server over HTTP.

Safety middleware for AI computer use agents that monitors, enforces policies, and provides guardrails to enable safe desktop interaction.

Enables a constrained subagent to perform foreground GUI actions on Hyprland—observing, focusing windows, clicking, typing, scrolling, dragging, and managing the clipboard—under per-action approval with lease, audit log, and kill-switch gating.

Enables cloud-based MCP clients to delegate privacy-sensitive or large-output tasks to a local LLM, returning sanitized placeholders or digested summaries so private data never leaves the user's network.

Local-first Gmail MCP server using PKCE + loopback OAuth flow that stores refresh tokens in the OS keychain, enabling secure read/write Gmail access via MCP tools without tokens leaving the device.

Enables a cloud orchestrator to query a local Ollama model over Tailscale or a LAN as a side-channel for drafts, summaries, and other helper output, with tools to list available models and to redact text. Answers leaving the server are passed through output-only DLP that masks card numbers, IBANs, emails, phone numbers, API keys, and similar secrets before they reach the cloud.

A deterministic, fail-closed MCP server that discovers approved local resources, plans bounded routes, and renders—but never executes—selected calls.

A secure MCP server that allows Claude to read and write local files on your machine with explicit approval gating for each access.

Enables ChatGPT Web Developer Mode to securely read, search, list, and edit files inside user-approved local folders, and optionally run approved developer commands on the user's Windows machine.

Local-first MCP server for per-agent key management, generating and using signing keys without external KMS.

Generates, validates, and deploys CrowdSec WAF rules and scenarios through natural language.

MCP server that provides local, de-identified access to a demo EMR database using a private LLM for de-identification, ensuring raw patient data stays local.

A security-focused Model Context Protocol server that enables controlled local tool execution through strict network firewalls, filesystem protections, and rate-limiting policies. It features a plugin-based architecture for progressive tool discovery and includes reference implementations for web searching and bug tracking.

Enables PII detection and anonymization using Microsoft Presidio with tools, resources, and prompts via MCP.

Enables an AI agent to act as a security operations operator by providing tools to monitor camera feeds, analyze scenes, review situations and alarms, acknowledge or resolve alarms, make voice announcements, and consult audit trails and system status.

Enables local synthetic-data evaluation of domain trustworthiness via five tools for reporting, verifying, and looking up domain signals, with conservative observation, rate limiting, and privacy-preserving logging.

Inspects documents for tampering, ineffective redactions, and text aimed at language models before they enter an agent's context, and compares documents to confirm whether they are unchanged.

Local-first encrypted key-value vault for securely storing and retrieving secrets like API keys using AES-GCM 256-bit encryption and a PIN.

Automates Android app analysis using Frida via AI commands, connecting a rooted Android phone to a computer and running dynamic analysis scripts without manual command execution.

Enables AI agents to run Shipcheck on local JavaScript/TypeScript repositories, scanning for launch risks like exposed env vars, unsigned webhooks, and missing security guardrails.