"Desktop Operations" matching MCP servers:

Connects Claude Desktop to FortiGate firewalls via REST API for read-only config inspection and safe write operations with dry-run confirmation.

An MCP server that integrates Claude Desktop with the Lumu Defender API for AI-powered security incident analysis and management.

Enables AI-driven SOC investigations by providing automated Splunk querying, threat intelligence enrichment, and response actions through natural language. Includes tools for IP pivoting, lateral movement detection, and label harvesting.

A Model Context Protocol (MCP) server that exposes 48 tools covering the full spectrum of iSuite enterprise administration — user management, role verification, job monitoring, scheduler control, batch execution, audit trail lookup, and configuration validation.

Enables LLM clients to safely perform file operations such as create, read, edit, delete, move, copy, and more, with every path checked against an explicit permission database managed through a desktop GUI.

MCP server for interacting with Keepit backup and data protection services. Enables monitoring, management, and security operations through natural language.

Lets AI agents validate orders against configured pre-trade risk limits and obtain signed approvals through MCP tools, with mutating operations off until explicitly enabled.

This server enables interaction with SailPoint IdentityIQ through SCIM API endpoints, allowing MCP clients like Claude Desktop to manage identity resources using natural language.

Exposes Lacework API v2 alert operations as MCP tools, allowing AI agents to list, search, and manage alerts with flexible time ranges and authentication.

Enables LLM clients to read and modify MS-SQL, PostgreSQL, MySQL/MariaDB and SQLite databases through 38 MCP tools, with every table, view, function and procedure gated by explicit permission rules that deny by default. Ships with a desktop GUI for authoring rules, approving destructive operations and auditing what the model did.

This foundation-only service is intended to enable narrowly bounded, typed operations over Shayona business data, starting with an approval-bound, redacted-preview workflow for emailing customer service credentials. It is designed to keep usernames and decrypted passwords out of MCP results, previews, errors, logs, traces, and approval state.

Enables creation, verification, and evolution of cryptographically verifiable AI agent identities (.01ai) via MCP for Claude Desktop and other MCP clients.

MCP server for OSIDB (Red Hat Product Security's vulnerability management system). Enables read-only querying of flaws, affects, trackers, and status via natural language from MCP clients like Cursor or Claude Desktop.

Provides a governance proxy layer for MCP servers, enforcing per-tool allowlists, human approval for write operations, quotas, secret redaction, and a hash-chained audit log of all calls.

Disk is a personal cloud storage on Cloudflare with an MCP server enabling agents to perform file operations, sharing, and key management via natural language.

Enables deployment of an MCP server on Cloudflare Workers with OAuth login, allowing remote invocation of tools like math operations from MCP clients.

MCP server bridging AI assistants with CrowdStrike Falcon for SOC operations, enabling natural-language triage, investigation, and response across detections, endpoints, threat intelligence, and more.

Enables LLMs to manage PocketBase databases with comprehensive CRUD, authentication, file management, backup, and hook operations through a standardized protocol.

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

A secure, audit-logged MCP server for Frappe that exposes specific DocTypes and operations to AI agents with granular permissions and field-level control.