"Roots" matching MCP servers:

Enables AI assistants to execute shell commands safely within registered project roots, with blocking of dangerous operations, output filtering, and log inspection.

A proof-of-concept MCP server that scopes GitHub tools to the current repository without filesystem access, using MCP roots to carry the repo identity.

Enables AI assistants to safely read local files and directories from explicitly configured roots, without write, edit, or shell execution capabilities.

Enables local management of approved project folders through tools for file operations, project status, backups, health checks, git checkpoints, and rollback. Operations are restricted to configured allowed roots.

A notes server that demonstrates advanced MCP features like sampling, elicitation, roots, pagination, and OAuth 2.1, enabling users to manage in-memory notes via natural language through a client.

A demo MCP server showcasing every MCP capability with fake logic, including tools, resources, prompts, progress, cancellation, elicitation, sampling, roots, and subscriptions, over Streamable HTTP, HTTP+SSE, and stdio transports.

A Python-based MCP server that provides a suite of basic arithmetic tools, including addition, square roots, and percentage calculations, for AI assistants. It enables models to perform precise mathematical operations through the Model Context Protocol.

Enables secure filesystem operations (read, write, list, move, search files/directories) through the Model Context Protocol, with dynamic directory access control via MCP Roots.

MCP server for filesystem operations, enabling reading, writing, editing, moving, and searching files with dynamic directory access control via MCP Roots.

A mathematical utility server implementing the Model Context Protocol to provide tools for basic and advanced calculations. It enables users to perform operations such as addition, subtraction, powers, square roots, and percentages through natural language.

Provides safe, allowlisted local filesystem access for MCP-compatible AI clients, enabling directory listing, file reading/writing (with byte limits), and text search while blocking paths outside approved roots and symlink escapes.

Industry 4.0 / IIoT AI agents for manufacturing: explain OEE losses per shift, triage machine alarms, find downtime root causes, prepare predictive-maintenance jobs and write shift reports from Unified Namespace (UNS), MQTT or historian data. Plus an industrial AI-readiness diagnostic and a vendor-neutral digital-transformation advisor. Works in Claude Code, Codex and any MCP client.

A Model Context Protocol server that enables AI assistants to interact directly with Warden-managed Magento 2 development environments, automating common tasks like project initialization, environment management, database operations, and Magento CLI commands.

Enables any MCP-compatible client to perform filesystem operations — reading, listing, writing, searching, watching directories, and batch processing files — over JSON-RPC 2.0 stdio transport. Includes resource discovery, metrics tracking, and security controls such as allowed roots, size limits, and format allowlists, with a LangGraph agent that accesses files exclusively through MCP.

Enables controlling a local Scilab/Xcos installation to discover installed block libraries, create native block templates, read, write, and validate diagrams, and run simulations of arbitrary positive duration that return named numerical signal series. It exposes these capabilities as MCP tools over stdio or streamable HTTP, with model file access restricted to configured filesystem roots.

Provides comprehensive git tooling via MCP, including status, diffs, commits, branches, stashes, and multi-root inventory, enabling AI agents to manage repositories.

MCP server that scans workspace roots to build a registry of version-controlled projects, exposing tools for searching, listing, and inspecting projects to help AI coding agents navigate multi-repo workspaces efficiently.

Enables AI hosts to work directly on Godot Engine projects through a local, self-hosted gateway that performs structured, permission-aware operations such as creating and editing scenes, nodes, resources and scripts, running and debugging projects, and exporting builds. All actions stay confined to approved project roots, are auditable, and can require confirmation for destructive steps.

Enables LLM agents to explore JavaScript/TypeScript repositories through parsed syntax trees by returning compact file outlines, precise symbol definitions, and local dependency graphs. It keeps access read-only and sandboxed to chosen roots while using a bounded, flood-proof stdio transport.

Enables multi-user, per-namespace storage of AES-256-GCM-encrypted credentials (SSH, web, API, DB) managed through a web console with TOTP 2FA, and lets AI clients save, list, retrieve, or server-side invoke those secrets over a remote Streamable-HTTP endpoint without ever exposing the values in chat.