Skip to content
Agent Search Engine.
Submit a tool
Menu

Alternatives · MCP Servers

agent-device alternatives

These records overlap with agent-device's recorded tasks and have the same product type. The selection uses task text, then information completeness; stars and sponsorship do not set the order. Check the specific capability you need before switching.

8 task-related records from 194 category candidates · all mcp servers · how we rank

The product you're replacing

agent-deviceMCP serverMCP Servers

Let coding agents run, inspect and verify mobile, TV, web and desktop apps through a CLI or MCP.

Costs not checked · 5.2k stars · TypeScript · Open source · repository push Nov 2026

Visit agent-device →Full agent-device record

Building one yourself? How to build an MCP server →

Task-related research candidates

iOS Simulator MCP ServerMCP serverLet AI assistants inspect and drive the iOS Simulator: tap, type, swipe and read the UI.Costs not checkedOpen sourceJavaScript · recorded license: MITRecord checked · Recent push 2.2kGitHub stars

Recorded task overlap: coding workflow. Compare the documented setup and limits before treating it as a substitute. The recorded use cases differ: agent-device — Coding agents that should verify their changes in the running mobile app, not only in unit tests; iOS Simulator MCP Server — iOS developers who want a coding agent to verify UI changes in the simulator.

MCP Feedback EnhancedMCP serverPause an AI coding agent to collect your feedback in a web UI or desktop app before it finishes.Costs not checkedOpen sourceJavaScript · recorded license: MITRecord checked · Recent push 3.8kGitHub stars

Recorded task overlap: coding workflow. Compare the documented setup and limits before treating it as a substitute. The recorded use cases differ: agent-device — Coding agents that should verify their changes in the running mobile app, not only in unit tests; MCP Feedback Enhanced — Keeping a human checkpoint in long agent sessions so fewer requests are spent on wrong turns.

UI DiscoveryMCP serverSearch design references and inspect palettes through a hosted MCP connector.FreemiumLicense not checkedRecord checked

Recorded task overlap: coding workflow. Compare the documented setup and limits before treating it as a substitute. The recorded use cases differ: agent-device — Coding agents that should verify their changes in the running mobile app, not only in unit tests; UI Discovery — Designers and coding-agent users researching interface patterns with inspectable source references.

PAL MCP (formerly Zen MCP)MCP serverLet Claude Code, Gemini CLI or Codex CLI consult other models and spawn CLI subagents from one session.Costs not checkedOpen sourcePython · recorded license: Apache-2.0Record checked 12kGitHub stars

Recorded task overlap: coding workflow. Compare the documented setup and limits before treating it as a substitute. The recorded use cases differ: agent-device — Coding agents that should verify their changes in the running mobile app, not only in unit tests; PAL MCP (formerly Zen MCP) — Developers who want a second model's review or a separate subagent context without leaving their main coding CLI.

Gemini MCP ToolMCP serverLet Claude Code and other assistants hand large files and codebases to the Gemini CLI for analysis.FreeLicense not checkedTypeScriptRecord checked 2.3kGitHub stars

Recorded task overlap: coding workflow. Compare the documented setup and limits before treating it as a substitute. The recorded use cases differ: agent-device — Coding agents that should verify their changes in the running mobile app, not only in unit tests; Gemini MCP Tool — Offloading whole-repository or very large file analysis from Claude Code to Gemini.

wigoloMCP serverLocal-first web search, fetch, crawl, extraction and research for AI coding agents, without API keys.Costs not checkedOpen sourceTypeScript · recorded license: AGPL-3.0Record checked · Recent push 5.5kGitHub stars

Recorded task overlap: coding workflow. Compare the documented setup and limits before treating it as a substitute. The recorded use cases differ: agent-device — Coding agents that should verify their changes in the running mobile app, not only in unit tests; wigolo — Giving a coding agent web search and page fetching without a paid search API.

MATLAB MCP ServerMCP serverMathWorks' official MCP server that lets coding agents start MATLAB, run code and check it.FreeLicense not checkedGoRecord checked · Recent push 1.8kGitHub stars

Recorded task overlap: coding workflow. Compare the documented setup and limits before treating it as a substitute. The recorded use cases differ: agent-device — Coding agents that should verify their changes in the running mobile app, not only in unit tests; MATLAB MCP Server — Engineers who want an AI coding agent to execute and validate MATLAB code against their own installation.

XcodeBuildMCPMCP serverA Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.Costs not checkedOpen sourceTypeScript · recorded license: MITRecord checked · Recent push 6.5kGitHub stars

Recorded task overlap: coding workflow. Compare the documented setup and limits before treating it as a substitute. The recorded use cases differ: agent-device — Coding agents that should verify their changes in the running mobile app, not only in unit tests; XcodeBuildMCP — Agents working on iOS and macOS projects that need to drive Xcode builds, with the same tools available as a CLI for direct terminal use.

Browse all mcp servers →

Frequently asked

How were alternatives to agent-device selected?
Recorded task topics and meaningful shared terms qualify same-type candidates in the same category. Results are ordered by that overlap, then information completeness and a stable identifier. Sponsorship and GitHub stars do not participate. The method can miss suitable tools whose records lack task information.
Does inclusion mean a tested replacement?
No. These are catalogue-based research candidates. Check current sources, costs, permissions and deployment requirements, then test your own task. ASE has not run a performance benchmark of this shortlist.