"Integrating Claude Desktop with a Local LLM using the LMStudio API" matching MCP servers:

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.

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

MCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.

Enables AI agents to control a Linux desktop and browser through governed tools for mouse, keyboard, windows, clipboard, screenshots, navigation, and page interaction, with policy verdicts, human confirmation, secret redaction, and an append-only audit trail.

Enables AI agents to call tools through a security gateway that intercepts requests, enforces deterministic policy and risk checks, blocks or escalates high-risk actions for human approval, and keeps tool credentials and audit logs protected.

A local MCP daemon that turns an agentic coding client into a bug bounty operator, with 103 tools for offensive security testing including MITM proxy, traffic analysis, and OOB callbacks.

MCP server toolkit with payload library, WAF bypass generator, rate limiter, plugin system, and inter-MCP bridge for security testing.

A hosted Model Context Protocol server that lets AI agents triage review queues, investigate authors, tune policies and wordlists, respond to incidents, configure projects and webhooks, and report on moderation activity through a Moderation API account.

Local stdio MCP server for Bitwarden (Public API + Secrets Manager). 50+ admin tools for members, groups, collections, policies, licensing, projects, and secrets. For Claude Desktop / Claude Code.

Enables MCP clients to securely connect to a paired Windows machine through a self-hosted Cloudflare relay and use its local filesystem and command-execution tools over Streamable HTTP and WebSocket.

Exposes an OpenAI- and Anthropic-compatible HTTP, SSE, and stdio gateway that wraps multiple subscription CLIs, adding prompt-injection defense, PII redaction, cost-aware routing, and reasoning-trace capture for MCP-compatible clients like Claude Desktop and Cursor.

OpenAI-compatible proxy with PII scrubbing, audit logging, and model routing. Drop-in replacement — set OPENAI_BASE_URL to point to this server. Supports GPT-4o, Claude, Gemini, and Llama via single endpoint.

Enables AI agents to request an independent second opinion from a different frontier model, with PII scrubbing before transit, live web search grounding, caching, and multi-provider failover.

Provides a governance gateway for LLM and agent traffic via MCP, blocking prompt injection, redacting PII, enforcing per-tenant token budgets, and caching repeat questions semantically. Enables AI agents to route model calls through the same guardrails instead of calling providers directly.

Enables a local AI agent to check LINE compatibility and access status, list chats the user explicitly authorized, and read paginated message text and attachment metadata from selected LINE chats through a local stdio MCP connection with permission checks.

Enables AI coding agents to run one-shot commands and copy single files to and from remote servers through The Bastion, which authenticates, authorizes, and records each action. Access is controlled by the bastion rather than allowlists or deny lists.

This MCP server provides secure access to databases for AI agents, enforcing authentication, authorization, human approval, logging, and notifications to prevent dangerous actions.

Enables agents to detect and redact PII and secrets in text, HTML, and PDF documents before they reach an LLM, with reversible placeholder, mask, or hash redaction, and to list supported detectors and redaction styles.

Encrypted token store for Claude Code sessions, providing MCP tools for secure secret management with macOS Keychain integration, per-project allowlists, and native dialog input.

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 AI assistants to perform password security auditing using John the Ripper on a remote Kali system via SSH, supporting cracking, hash management, and session control.

Enables AI agents to use vault-stored credentials without ever exposing plaintext secrets to model context, transcripts, or telemetry. It decrypts AES-256-GCM envelopes locally via WebCrypto, resolves opaque secret handles into subprocess environments and outbound HTTP requests, issues auto-zeroizing time-bounded leases, and scrubs echoed credentials from output.

Implements a secure MCP server with API Key and JWT authentication, providing tools like echo, login, secure_action, and admin_action. Includes MCP Inspector integration for testing and debugging.

the-real-unifi-mcp License: MIT Node MCP SDK [![CI](https://github.com/mguttmann/the-real-unifi-mcp/actions

Signed, offline-verifiable authorization for API-contract changes. Before a contract change (OpenAPI, GraphQL, Protobuf, AsyncAPI, MCP manifests) merges or deploys, the agent calls preflight_change_set; the decision is deterministic, signed, and verifiable without calling CodeRifts. Three tools: preflight_change_set, verify_receipt, get_decision_details. Only a granted change can proceed.

Enables AI assistants and agents to securely access selected Windows files and developer resources through explicitly authorized workspace roots and capability-based permissions. It provides read-only tools for listing, reading, metadata inspection, and bounded filename search with path validation and escape checks.

Enables MCP-compatible AI assistants to list, inspect, read, search, and modify local files and directories within configured filesystem roots, with permission controls and optional read-only or deletion restrictions.

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

Enables applications to scan model replies for leaks, sanitize output, authorize model-proposed actions with signed single-use grants, and optionally score prompt injection in a way that can only tighten enforcement decisions.