# Bluetooth LE Health Sensors (pypi · labmcp-ble-health)

MCP server for Bluetooth LE health sensors (standard GATT profiles).

- Trust score: 67/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-30

## Components

- pypi · `labmcp-ble-health`: 67/100 (this document), [markdown](https://verifymcp.io/servers/k-dense-ai-labmcp-ble-health/labmcp-ble-health.md), [page](https://verifymcp.io/servers/k-dense-ai-labmcp-ble-health/labmcp-ble-health)

## Channel facts

- Registry: `pypi`
- Package: `labmcp-ble-health`
- Version: `0.1.3`
- 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 2026-09-30.

- **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.
  - 2 of 33 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to K-Dense-AI/lab-instrument-mcps).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 3 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 78/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1299 tokens (~118/item across 11 items; 11 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 93% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 12 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).

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the Bluetooth LE Health Sensors MCP server?

Bluetooth LE Health Sensors runs locally as a PyPI package, launched with uvx labmcp-ble-health. 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 k-dense-ai-labmcp-ble-health -- uvx labmcp-ble-health
```

### Cursor

```json
{
  "mcpServers": {
    "k-dense-ai-labmcp-ble-health": {
      "command": "uvx",
      "args": [
        "labmcp-ble-health"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "k-dense-ai-labmcp-ble-health": {
      "command": "uvx",
      "args": [
        "labmcp-ble-health"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add k-dense-ai-labmcp-ble-health -- uvx labmcp-ble-health
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "k-dense-ai-labmcp-ble-health": {
      "type": "local",
      "command": [
        "uvx",
        "labmcp-ble-health"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add k-dense-ai-labmcp-ble-health --command uvx --arg labmcp-ble-health
```

### Hermes

```yaml
mcp_servers:
  k-dense-ai-labmcp-ble-health:
    command: "uvx"
    args: ["labmcp-ble-health"]
```

### Netclaw

```json
{
  "McpServers": {
    "k-dense-ai-labmcp-ble-health": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "labmcp-ble-health"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add k-dense-ai-labmcp-ble-health -t stdio -c uvx -a labmcp-ble-health
```

### Other

```json
{
  "mcpServers": {
    "k-dense-ai-labmcp-ble-health": {
      "command": "uvx",
      "args": [
        "labmcp-ble-health"
      ]
    }
  }
}
```

## 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.

### 2026-09-28 (score 67, −4)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-27 (score 71, 0)

- [functional] Package version: 0.1.2 → 0.1.3

### 2026-09-26 (score 71)

First indexed and scored.

## MCP tools (11)

### `get_connection_info` (~40 tokens)

Get Connection Info

Report which instrument is connected (identity, address, simulated or real),
whether the server is read-only, and the active safety limits. Call this first.

### `get_command_log` (~46 tokens)

Get Command Log

Return the most recent raw commands sent to / replies received from the
instrument (newest last). Useful for debugging and for recording what was done.

Input parameters:

- `limit` (integer)

Output parameters:

- `result` (array)

### `reconnect` (~35 tokens)

Reconnect

Close and re-open the connection to the instrument (e.g. after it was power
cycled or a cable was re-plugged).

### `scan_devices` (~111 tokens)

Scan Devices

Scan for nearby Bluetooth LE devices: address, name, signal strength and advertised health
services. Works without a configured --address.

Devices only show up while advertising (monitors often advertise only right after a
measurement), and some do not list every service in their advertisement, so `service`
filtering can miss them.

Input parameters:

- `name_contains`: Case-insensitive name filter
- `service` (string): Only list devices advertising this service
- `timeout_s` (number): How long to listen for advertisements

Output parameters:

- `devices` (array)
- `note` (string)
- `scanned_s` (number)
- `service_filter` (string)
- `timestamp` (string)

### `get_device_info` (~57 tokens)

Get Device Info

Read the device's identity (manufacturer, model, serial, firmware), the standard health
services it exposes and its features.

Features include the body sensor location, supported oximeter / blood-pressure status flags,
scale resolution and thermometer site.

Output parameters:

- `address` (string)
- `features` (object): Decoded feature characteristics (sensor location, supported flags, resolutions)
- `firmware_revision`
- `hardware_revision`
- `manufacturer`
- `model`
- `serial`
- `services` (array): Standard Bluetooth SIG services found on the device
- `software_revision`
- `system_id`
- `timestamp` (string)

### `read_battery` (~25 tokens)

Read Battery

Read the device's battery level (Battery Service, 0-100 %).

Output parameters:

- `address` (string)
- `battery_pct` (integer): Battery Level characteristic (0-100 %)
- `timestamp` (string)

### `record_heart_rate` (~124 tokens)

Record Heart Rate

Record heart rate for `duration_s`: bpm series, RR intervals and time-domain HRV (mean HR,
SDNN, RMSSD, pNN50).

The sensor must be worn with good skin contact. HRV statistics are for research, not clinical
ECG analysis. Use `save_path` to keep every packet as CSV.

Input parameters:

- `duration_s` (number): Recording length in seconds
- `max_points` (integer): Max points returned per series
- `save_path`: Optional new .csv file for the full recording (never overwrites a file)

Output parameters:

- `address` (string)
- `bpm_max`
- `bpm_mean`
- `bpm_min`
- `bpm_series` (array): Reported heart rate (downsampled to max_points)
- `disconnected_early` (boolean)
- `duration_s` (number)
- `energy_expended_kj`: Last cumulative energy expended reported by the sensor
- `hrv` (object)
- `malformed_packets` (integer)
- `notes` (array)
- `notifications` (integer)
- `rr_intervals_downsampled` (boolean)
- `rr_intervals_ms` (array): RR intervals in ms (downsampled to max_points if longer)
- `saved_to`
- `sensor_contact_pct`: Share of packets with skin contact (None if unsupported)
- `started_at` (string)

### `read_pulse_oximetry` (~176 tokens)

Read Pulse Oximetry

Read SpO2 (%) and pulse rate from a pulse oximeter, averaged over a few seconds or as a
single spot-check reading.

Continuous mode listens for `duration_s` and returns the latest valid values plus mean/min;
spot-check mode waits for the oximeter's single stable reading. Early packets are often NaN
while the sensor acquires; these are counted in `unavailable_samples`, never reported as values.

Input parameters:

- `duration_s` (number): Continuous mode: seconds to average over
- `mode` (string): auto: connect, then continuous if the oximeter supports it, else wait for a spot-check. spot_check: wait for a reading even if the oximeter is not advertising yet
- `timeout_s` (number): Spot-check mode: seconds to wait

Output parameters:

- `address` (string)
- `device_sensor_status` (array): Device and Sensor Status flags of the latest packet
- `device_timestamp`: Device clock time of a spot-check measurement
- `malformed_packets` (integer): Packets that could not be decoded (skipped)
- `measurement_status` (array): Measurement Status flags of the latest packet
- `mode` (string): continuous (PLX Continuous Measurement) or spot_check
- `pulse_amplitude_index_pct`
- `pulse_rate_bpm`: Latest valid pulse rate
- `pulse_rate_mean_bpm`
- `samples` (integer)
- `spo2_mean_pct`
- `spo2_min_pct`
- `spo2_pct`: Latest valid SpO2
- `timestamp` (string)
- `unavailable_samples` (integer): Packets whose SpO2 or PR was a special value (NaN, NRes, ...)

### `wait_for_blood_pressure` (~94 tokens)

Wait For Blood Pressure

Wait for a blood pressure monitor to send a measurement: systolic, diastolic and mean
arterial pressure (mmHg) and pulse rate.

Call this, then ask the participant to start a measurement on the monitor. kPa readings are
converted to mmHg; the unit sent is reported. Older stored readings are listed separately.

Input parameters:

- `timeout_s` (number): Seconds to wait for a measurement

Output parameters:

- `address` (string)
- `cuff_pressure_updates` (integer)
- `device_timestamp`: Measurement time from the device clock (device local time)
- `diastolic_mmhg`
- `max_cuff_pressure_mmhg`
- `mean_arterial_mmhg`
- `measurement_status` (array)
- `other_measurements` (array): Older stored measurements received in the same session (oldest first)
- `pulse_rate_bpm`
- `received_at` (string)
- `special_values` (array): Fields the device reported as NaN / NRes / INF
- `systolic_mmhg`
- `unit_reported` (string): Unit the device used (kPa values are converted to mmHg)
- `user_id`

### `read_temperature` (~87 tokens)

Read Temperature

Wait for a thermometer to send a temperature measurement and return it in °C.

°F readings are converted; the measurement site is included if the device reports one.

Input parameters:

- `accept_intermediate` (boolean): If no final measurement arrives before the timeout, return the latest Intermediate Temperature value (probe still settling) instead of an error
- `timeout_s` (number): Seconds to wait for a measurement

Output parameters:

- `address` (string)
- `device_timestamp`
- `final` (boolean): False if this is an Intermediate Temperature (probe still settling)
- `measurement_site`
- `other_measurements_c` (array)
- `received_at` (string)
- `special_value`
- `temperature_c`
- `unit_reported` (string): 'C' or 'F' as sent by the device
- `value_reported`

### `read_weight` (~64 tokens)

Read Weight

Wait for a scale to send a weight measurement (kg), with BMI and height if the scale sends
them.

Ask the person to step on the scale after calling this. lb readings are converted to kg.

Input parameters:

- `timeout_s` (number): Seconds to wait for a measurement

Output parameters:

- `address` (string)
- `bmi_kg_m2`
- `device_timestamp`
- `height_m`
- `notes` (array)
- `other_measurements_kg` (array)
- `received_at` (string)
- `scale_resolution_kg`
- `unit_reported` (string): 'kg' or 'lb' as sent by the scale
- `user_id`
- `value_reported`
- `weight_kg`: None if the scale reported 'measurement unsuccessful'

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/k-dense-ai-labmcp-ble-health/labmcp-ble-health#diagnostics

## Score history

- 2026-09-30: 67
- 2026-09-29: 67
- 2026-09-28: 67
- 2026-09-27: 71
- 2026-09-26: 71

## Common questions

### What is the Bluetooth LE Health Sensors MCP server?

Bluetooth LE Health Sensors is an MCP server listed in the public MCP registry as io.github.K-Dense-AI/labmcp-ble-health. MCP server for Bluetooth LE health sensors (standard GATT profiles). This page covers its PyPI package (labmcp-ble-health).

### Is the Bluetooth LE Health Sensors MCP server safe to use?

Bluetooth LE Health Sensors scores 67 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 30 September 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 Bluetooth LE Health Sensors MCP server expose?

Bluetooth LE Health Sensors exposes 11 tools: get_connection_info, get_command_log, reconnect, scan_devices, get_device_info, and 6 more. Their descriptions and schemas cost roughly 859 tokens of context every time the server is loaded.

### Is the Bluetooth LE Health Sensors MCP server still maintained?

Bluetooth LE Health Sensors is still listed as active in the MCP registry. We last reached this channel on 30 September 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 Bluetooth LE Health Sensors MCP server under?

Bluetooth LE Health Sensors declares the Apache-2.0 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/labmcp-ble-health/
- Socket report: https://socket.dev/pypi/package/labmcp-ble-health
- Repository: https://github.com/K-Dense-AI/lab-instrument-mcps
- Website: https://github.com/K-Dense-AI/lab-instrument-mcps/tree/main/servers/health/ble-health-sensors
- Changelog RSS feed: https://verifymcp.io/servers/k-dense-ai-labmcp-ble-health/labmcp-ble-health.xml
- Changelog JSON feed: https://verifymcp.io/servers/k-dense-ai-labmcp-ble-health/labmcp-ble-health.json
- HTML version of this page: https://verifymcp.io/servers/k-dense-ai-labmcp-ble-health/labmcp-ble-health