Skip to content
MCP server

HardwareMCP

Search a catalog of hardware MCP servers from your agent, with install steps

Install
Pricing
Free
Platforms
API
Runs
Remotely
Version
0.1.0
Listing updated
2 days ago

About HardwareMCP

HardwareMCP is a free MCP server for developer tools. It runs as a hosted remote server, so there is nothing to install locally.

Instead of browsing a directory site, you connect your agent to this endpoint and ask in plain language, for example which server to use to monitor prints on a Bambu P1S or to flash an ESP32 with PlatformIO. It answers from a catalog of 103 servers across 60 device families, covering boards such as ESP32, Arduino, Raspberry Pi and RP2040, 3D printers (Bambu, Prusa, Klipper, OctoPrint), Home Assistant, cameras (Frigate, UniFi Protect, ONVIF), Zigbee, serial and BLE, and lab gear.

The server is stateless Streamable HTTP with no authentication and no API key, and it is free. Results are sorted by GitHub stars, and each server entry carries requirements, install commands and a client config snippet. The README warns that those install commands are copied from each project's own README and have not been bench-tested, so review code before giving an agent access to your hardware.

Setup instructions are given for Claude Code, Cursor, Claude Desktop (through mcp-remote or a custom connector), Grok Bot and Meta's Muse. A local stdio npm package is marked as coming soon.

Install

Run in a terminal

claude mcp add --transport http hardwaremcp https://hardwaremcp.khanex.ai/mcp

Add to Settings → Connectors → Add custom connector

https://hardwaremcp.khanex.ai/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "hardwaremcp": {
      "url": "https://hardwaremcp.khanex.ai/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "hardwaremcp": {
      "type": "http",
      "url": "https://hardwaremcp.khanex.ai/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "hardwaremcp": {
      "serverUrl": "https://hardwaremcp.khanex.ai/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "hardwaremcp": {
      "type": "http",
      "url": "https://hardwaremcp.khanex.ai/mcp"
    }
  }
}

Tools this server provides (4)

Taken from the project documentation; the running server may differ.

search_servers
Search the hardware MCP server catalog by query, device and category.
get_server
Get install steps and client config for one server by slug.
list_devices
List every device family with server counts.
recommend_for_device
Recommend servers for a device or model, optionally ranked by a goal.

What it does

Device-aware search
search_servers takes a query plus optional device and category filters.
Full server details
get_server returns what a server does, its requirements, install commands and a client config.
Device family list
list_devices shows every device family with its server count.
Per-device recommendations
recommend_for_device returns top picks for a model such as a Bambu P1S, optionally ranked by a goal.
No-install remote endpoint
Public Streamable HTTP endpoint with no sign-in, open CORS and JSON responses.

Good for

  • Find an MCP server for a specific 3D printer model
  • Set up an agent to flash an ESP32 or Arduino board
  • Compare Home Assistant MCP servers before installing one
  • Look up camera or Zigbee MCP servers and get ready-made client config

Pricing

Free

Free, no API key; source is MIT licensed

Prices change. Check hardwaremcp.khanex.ai before you buy.

HardwareMCP FAQ

Do I need an API key?

No. The endpoint is public, needs no authentication and is free to use.

Which clients can connect?

The page gives setup steps for Claude Code, Cursor, Claude Desktop, Grok Bot and Meta Muse; any client that supports remote Streamable HTTP servers should work.

Are the install commands tested?

No. They are taken from each project's README and have not been bench-tested by HardwareMCP, so review code before giving an agent access to your hardware.

Can I run it locally?

A stdio package installed with npx is listed as coming soon; the hosted endpoint is the available option.

Is HardwareMCP free?

Yes. HardwareMCP is free to use.

How do I add HardwareMCP to Claude Code?

Run this command in your terminal: claude mcp add --transport http hardwaremcp https://hardwaremcp.khanex.ai/mcp

What are the best alternatives to HardwareMCP?

The closest alternatives to HardwareMCP are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to HardwareMCP

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools