# io.github.emirmrkaljevic/usb-rea (pypi · usb-rea)

Reverse engineer USB gadgets: capture traffic, infer the protocol, generate a pyusb driver.

- Trust score: 65/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-22

## Components

- pypi · `usb-rea`: 65/100 (this document), [markdown](https://verifymcp.io/servers/emirmrkaljevic-usb-rea/usb-rea.md), [page](https://verifymcp.io/servers/emirmrkaljevic-usb-rea/usb-rea)

## Channel facts

- Registry: `pypi`
- Package: `usb-rea`
- Version: `0.6.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-22.

- **Supply Chain Security**: 50/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 1 of 29 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to emirmrkaljevic/usb-rea).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 1 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 65/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2103 tokens (~233/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "replay_packet" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the io.github.emirmrkaljevic/usb-rea MCP server?

io.github.emirmrkaljevic/usb-rea runs locally as a PyPI package, launched with uvx usb-rea. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add emirmrkaljevic-usb-rea -- uvx usb-rea
```

### Cursor

```json
{
  "mcpServers": {
    "emirmrkaljevic-usb-rea": {
      "command": "uvx",
      "args": [
        "usb-rea"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "emirmrkaljevic-usb-rea": {
      "command": "uvx",
      "args": [
        "usb-rea"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add emirmrkaljevic-usb-rea -- uvx usb-rea
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "emirmrkaljevic-usb-rea": {
      "type": "local",
      "command": [
        "uvx",
        "usb-rea"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add emirmrkaljevic-usb-rea --command uvx --arg usb-rea
```

### Hermes

```yaml
mcp_servers:
  emirmrkaljevic-usb-rea:
    command: "uvx"
    args: ["usb-rea"]
```

### Netclaw

```json
{
  "McpServers": {
    "emirmrkaljevic-usb-rea": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "usb-rea"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add emirmrkaljevic-usb-rea -t stdio -c uvx -a usb-rea
```

### Other

```json
{
  "mcpServers": {
    "emirmrkaljevic-usb-rea": {
      "command": "uvx",
      "args": [
        "usb-rea"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-21 (score 65, 0)

- [functional] Package version: 0.5.0 → 0.6.0

### 2026-10-20 (score 65, −15)

- [security regression] Malware scan: pass → unverified
- [functional regression] Schema quality: 196 → 223
- [functional] Package version: 0.4.0 → 0.5.0

### 2026-10-19 (score 80, +1)

- [security regression] Stability: 0.07 → unverified
- [security regression] Tool safety: pass → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified
- [functional] Package version: 0.3.0 → 0.4.0

### 2026-10-18 (score 79, +1)

- [security regression] Tool safety: pass → unverified
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Stability: unverified → 0.07
- [functional] First check of Schema quality: unverified
- [functional] Package version: 0.2.1 → 0.3.0

### 2026-10-17 (score 78, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-16 (score 63)

First indexed and scored.

## MCP tools (9)

### `capture_start` (~150 tokens)

Start a USB traffic capture into `out` (usbmon on Linux, USBPcap on Windows).

Side effects: launches a background capture process that keeps writing until capture_stop.
Needs elevated privileges on Linux (usbmon; typically root or a usbmon group). Does not
touch the device itself. Pair every start with capture_stop; do not start a second capture
while one is running. Prefer this over analysis tools when you still need live traffic.

Input parameters:

- `bus` (integer): usbmon bus number N for /dev/usbmonN; ignored on Windows/USBPcap. Default 0
- `out` (string): Output pcapng path (overwritten if it already exists)

Output parameters:

- `result` (string)

### `capture_stop` (~73 tokens)

Stop the running capture started by capture_start.

Side effects: terminates the background capture process. The pcapng at the path given to
capture_start is left on disk for report/diff_actions/scaffold_driver. Returns
'no capture running' if nothing was started (not an error). Call this before analysing.

Output parameters:

- `result` (string)

### `mark_action` (~368 tokens)

Record that the human is about to click this action in the vendor app.

Side effects: appends {label, start, end} to <capture>.actions.json (creates the file).
Call while capture_start is running, immediately before each click; end times are closed
when the next mark arrives. Use the same label stem with different values (brightness 0%,
50%, 100%) so inference can fit scales. For an already-finished Wireshark capture without
markers, skip this and pass `labels` to report/diff_actions instead.
A label starting with 'seen' ('seen rpm 1180', 'seen rpm 1180 temp 34') is an observation,
not an action: what the vendor app displays right now. It does not end the current action
and is never diffed; analysis uses it to name and scale the device's reply readings
(rpm = raw, temp = (raw - 40) / 2). Mark it when the human reads a value off the screen.
On/off states ('seen pump on', 'seen pump off, alarm on') name single status-flag bits; words
('seen mode silent', 'seen mode turbo, rpm 3900': the word last or before a comma) name a mode
byte with a value -> word map; negative values ('seen temp -5') allow signed i8/i16 readings.

Input parameters:

- `capture` (string): Capture path whose sidecar markers file (<capture>.actions.json) is updated
- `label` (string, required): Action label, ideally with a value, e.g. 'brightness 50%' or 'color 255 0 0'; or an observation starting with 'seen', e.g. 'seen rpm 1180 temp 34'

Output parameters:

- `result` (string)

### `diff_actions` (~353 tokens)

Diff packets per labelled action and infer the protocol (JSON: byte roles + evidence frames).

The JSON also has `background` (periodic polls set aside) and `responses`: device replies paired
with the query they answer (command, background poll or GET_REPORT), with byte roles
(const, echo of a query byte, value fitted to the labels, counter, checksum, or reading with
its observed min/max) and query/reply frame numbers. A reading that 'seen' markers explain
gets `name`, `scale` and `bias` (raw = value * scale + bias, `signed` for i8/i16) plus the
observations in `observed`; a named mode has `table` (raw value -> word the app showed);
\`observations` lists every 'seen' value and which reply bytes it matched.

Read-only analysis: does not write files or talk to hardware. Requires either markers from
mark_action or `labels` for a finished capture with pauses between clicks. Prefer report
when the human wants a Markdown evidence write-up; prefer scaffold_driver /
wireshark_dissector when they want generated code.

Input parameters:

- `capture` (string, required): Path to a usbmon or USBPcap pcap/pcapng file
- `device`: USB device address to analyse; default = bus address with the most host→device payloads
- `labels`: Marker-free mode: ';'-separated labels in click order, or a text file path (one label per line). Splits traffic at the largest pauses between host→device messages
- `markers`: Markers JSON path; default <capture>.actions.json. Ignored when labels is set

Output parameters:

- `result` (string)

### `report` (~228 tokens)

Generate a Markdown evidence report: every claim links to frame numbers in the capture.

Includes a 'Device responses' section when the device answers queries (status polls,
command ACKs, GET_REPORT), saying which reply bytes could not be explained, and an
'Observations' section for 'seen' markers (named readings and unmatched observations).

Read-only: returns Markdown text (does not write a file). Same inputs as diff_actions.
Use after capture_stop (or on an existing pcap). Choose this over diff_actions when the
human should read the protocol; choose scaffold_driver when they need a pyusb driver.

Input parameters:

- `capture` (string, required): Path to a usbmon or USBPcap pcap/pcapng file
- `device`: USB device address to analyse; default = bus address with the most host→device payloads
- `labels`: Marker-free mode: ';'-separated labels in click order, or a text file path (one label per line)
- `markers`: Markers JSON path; default <capture>.actions.json. Ignored when labels is set

Output parameters:

- `result` (string)

### `scaffold_driver` (~274 tokens)

Generate a standalone Python/pyusb driver source for the inferred protocol.

One set_<command>() per command; when the device replies, also query_<name>() methods that
send the command/poll (or GET_REPORT), read the reply and return it decoded as a dict
(readings named by 'seen' markers come back scaled and modes as words, e.g.
{'rpm': 1180, 'temp': 34, 'mode': 'turbo', 'ok': True}).

Read-only analysis that returns driver source as text (does not write a file or open the
device). Same capture/markers/labels inputs as report. Prefer wireshark_dissector when the
goal is to keep decoding traffic in Wireshark; use replay_packet only after the human
approved a specific packet from this driver.

Input parameters:

- `capture` (string, required): Path to a usbmon or USBPcap pcap/pcapng file
- `device`: USB device address to analyse; default = bus address with the most host→device payloads
- `labels`: Marker-free mode: ';'-separated labels in click order, or a text file path (one label per line)
- `markers`: Markers JSON path; default <capture>.actions.json. Ignored when labels is set

Output parameters:

- `result` (string)

### `wireshark_dissector` (~232 tokens)

Generate a Wireshark Lua dissector for the inferred protocol.

Read-only: returns Lua source as text. Labels commands, decodes values/counters/lookups,
and verifies checksums (usbrea.checksum_ok + expert warning). Load with
\`wireshark -X lua_script:<file>.lua capture.pcapng` or the same flag on tshark. Prefer
scaffold_driver for a pyusb driver; prefer hid_descriptor to inspect HID report layouts.

Input parameters:

- `capture` (string, required): Path to a usbmon or USBPcap pcap/pcapng file
- `device`: USB device address to analyse; default = bus address with the most host→device payloads
- `labels`: Marker-free mode: ';'-separated labels in click order, or a text file path (one label per line)
- `markers`: Markers JSON path; default <capture>.actions.json. Ignored when labels is set
- `name` (string): Wireshark protocol/filter prefix (fields become <name>.command, <name>.checksum_ok, …)

Output parameters:

- `result` (string)

### `hid_descriptor` (~179 tokens)

Decode a HID report descriptor (and optionally one report payload).

Read-only. When `source` is a capture path, finds GET_DESCRIPTOR type 0x22 transfers
(replug the device while capturing if none are present). When `source` is hex, parses that
descriptor directly (e.g. from /sys/class/hidraw/*/device/report_descriptor). Use this to
understand report IDs/sizes before or alongside report/scaffold_driver; it does not infer
vendor protocol fields from labelled actions.

Input parameters:

- `decode_hex`: Optional report payload hex to decode with the descriptor
- `report_type` (string): Report type for decode_hex: Input, Output, or Feature
- `source` (string, required): Capture path (searches for GET_DESCRIPTOR 0x22) or raw descriptor hex / hidraw report_descriptor bytes as hex

Output parameters:

- `result` (string)

### `replay_packet` (~246 tokens)

Send one packet to real USB hardware (destructive / irreversible on the device).

Side effects: opens the device via libusb/pyusb and writes the packet. Refuses unless
user_confirmed=true after the human approved this exact vid/pid/endpoint/hex_data
(and setup_hex if any). Needs OS permission to open the device. Prefer scaffold_driver to
generate a driver first; never set user_confirmed from an agent guess.

Input parameters:

- `endpoint` (integer, required): Endpoint address (e.g. 0x01 OUT); for control transfers use 0 with setup_hex
- `hex_data` (string, required): Payload bytes as hex (spaces optional), e.g. 'aa 01 ff 00 00 ab'
- `pid` (integer, required): USB product id (integer)
- `setup_hex`: Optional 8-byte control setup packet as hex; when set, sends a control transfer instead of bulk/interrupt
- `user_confirmed` (boolean): Must be true only after a human approved this exact packet; otherwise the call is refused
- `vid` (integer, required): USB vendor id (integer, e.g. 0x1234 or 4660)

Output parameters:

- `result` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/emirmrkaljevic-usb-rea/usb-rea#diagnostics

## Score history

- 2026-10-22: 65
- 2026-10-21: 65
- 2026-10-20: 65
- 2026-10-19: 80
- 2026-10-18: 79
- 2026-10-17: 78
- 2026-10-16: 63

## Common questions

### What is the io.github.emirmrkaljevic/usb-rea MCP server?

io.github.emirmrkaljevic/usb-rea is an MCP server listed in the public MCP registry as io.github.emirmrkaljevic/usb-rea. Reverse engineer USB gadgets: capture traffic, infer the protocol, generate a pyusb driver. This page covers its PyPI package (usb-rea).

### Is the io.github.emirmrkaljevic/usb-rea MCP server safe to use?

io.github.emirmrkaljevic/usb-rea scores 65 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 22 October 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.emirmrkaljevic/usb-rea MCP server expose?

io.github.emirmrkaljevic/usb-rea exposes 9 tools: capture_start, capture_stop, mark_action, diff_actions, report, and 4 more. Their descriptions and schemas cost roughly 2,103 tokens of context every time the server is loaded.

### Is the io.github.emirmrkaljevic/usb-rea MCP server still maintained?

io.github.emirmrkaljevic/usb-rea is still listed as active in the MCP registry. We last reached this channel on 22 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the io.github.emirmrkaljevic/usb-rea MCP server under?

io.github.emirmrkaljevic/usb-rea declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/usb-rea/
- Socket report: https://socket.dev/pypi/package/usb-rea
- Repository: https://github.com/emirmrkaljevic/usb-rea
- Changelog RSS feed: https://verifymcp.io/servers/emirmrkaljevic-usb-rea/usb-rea.xml
- Changelog JSON feed: https://verifymcp.io/servers/emirmrkaljevic-usb-rea/usb-rea.json
- HTML version of this page: https://verifymcp.io/servers/emirmrkaljevic-usb-rea/usb-rea