"A service or tool for navigation" matching MCP servers:

Provides agents with real Linux VMs to run commands, manage files, expose ports, and track costs, all through an ephemeral sandbox service.

MCP server that gives AI agents isolated, named Linux computers with stable IDs and lifecycle control. Supports multiple backends like Docker, Fly Machines, Modal, and E2B, with a dashboard for managing sandboxes.

Enables AI agents to invoke a local Stata installation, including a Windows Stata build under Wine on Linux and macOS, for regression analysis, econometrics, paper replication, and empirical research with command guards, resource monitoring, and automatic log capture.

Enables Large Language Models to access and manipulate Autodesk Revit models through a pyRevit-based bridge and the Model Context Protocol.

A simple MCP server implementation in TypeScript that communicates over stdio, allowing users to ask questions that end with 'yes or no' to trigger the MCP tool in Cursor.

Enable Claude (or any other LLM) to interactively debug your code (set breakpoints and evaluate expressions in stack frame). It's language-agnostic, assuming debugger console support and valid launch.json for debugging in VSCode.

A unified HTTP/HTTPS service that exposes Model Context Protocol (MCP) functionality over HTTP endpoints, allowing clients to list available tools and call them through a standardized API.

Composes arbitrary MCP tools using JavaScript, enabling discovery, composition, and execution of other MCP servers through a single 'exec' tool.

Ephemeral MicroVM-isolated code execution for AI agents. Run Python, Node, or bash — fresh hardware-isolated VM per call, hard-purged after. No state persists between calls.

Run DeepSeek as a real sub-agent inside Claude Code / Codex CLI — not just a single LLM call. DeepSeek gets its own 7-tool agent loop (Read/Write/Edit/Bash/Glob/Grep/NotebookEdit) inside a sandboxed workspace.

A Model Context Protocol (MCP) server that wraps the dbt CLI tool, enabling AI coding agents to interact with dbt projects through standardized MCP tools. Developed by Mammoth Growth.

Lets your AI find the open-source tool it needs on GitHub and install it as an MCP tool, in a sandbox, after you approve. Reads only the folders you grant; no network unless allowed.

A Model Context Protocol implementation that plays sound effects (completion, error, notification) for Cursor AI and other MCP-compatible environments, providing audio feedback for a more interactive coding experience.

Code-mode MCP server (docs_search + execute_code two-tool surface) backed by a unified capability manifest across three sandbox kernels (in-process node:vm, WASM via QuickJS / Pyodide / Wasmtime, and remote microVM via E2B / Cloudflare Sandbox). At N=30 tools the bootstrap-context cost drops to 13.6% of direct tool-use. Apache-2.0.

Enables agents to accomplish multi-step work by writing a single sandboxed JavaScript program that drives shell, filesystem, HTTP, and every tool of any configured MCP server, returning only a small summary instead of raw JSON. This collapses dozens of advertised tool schemas into one tool, cutting per-request context by roughly 26× while keeping disabled upstream servers reachable.

An MCP server for Task Trellis that provides tools for AI coding agents to manage tasks, currently featuring a simple hello_world demonstration tool.

Enables running Python and commands inside isolated, persistent Wasmer sandboxes on the host, while also exposing an Edge-deployed Postgres-backed service for storing notes and collecting feedback.

Enables Windows users to connect Antigravity CLI as an MCP subagent for coding tasks such as file reading, code execution, edits, and terminal commands, with model selection, conversation continuity, and streaming progress.

A minimal MCP server that exposes a single bash tool to execute commands inside a devcontainer, returning real output and exit codes.

A FastMCP server that turns JSON data into Plotly figures, deployable as an isolated service on Modal. Data goes in as JSON; a validated Plotly figure (JSON) or a rendered PNG comes back over the Model Context Protocol.