# Atlas Scientific EZO Sensors (pypi · labmcp-atlas-ezo)

MCP server for Atlas Scientific EZO sensor circuits (pH, ORP, DO, EC, RTD, HUM, CO2, PRS) over UART.

- Trust score: 69/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-30

## Components

- pypi · `labmcp-atlas-ezo`: 69/100 (this document), [markdown](https://verifymcp.io/servers/k-dense-ai-labmcp-atlas-ezo/labmcp-atlas-ezo.md), [page](https://verifymcp.io/servers/k-dense-ai-labmcp-atlas-ezo/labmcp-atlas-ezo)

## Channel facts

- Registry: `pypi`
- Package: `labmcp-atlas-ezo`
- Version: `0.1.2`
- 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**: 49/100
  - 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 17 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**: 79/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1426 tokens (~109/item across 13 items; 13 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 92% 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.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 14 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 Atlas Scientific EZO Sensors MCP server?

Atlas Scientific EZO Sensors runs locally as a PyPI package, launched with uvx labmcp-atlas-ezo. 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-atlas-ezo -- uvx labmcp-atlas-ezo
```

### Cursor

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

### VS Code

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

### Codex

```bash
codex mcp add k-dense-ai-labmcp-atlas-ezo -- uvx labmcp-atlas-ezo
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add k-dense-ai-labmcp-atlas-ezo --command uvx --arg labmcp-atlas-ezo
```

### Hermes

```yaml
mcp_servers:
  k-dense-ai-labmcp-atlas-ezo:
    command: "uvx"
    args: ["labmcp-atlas-ezo"]
```

### Netclaw

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

### Vellum

```bash
assistant mcp add k-dense-ai-labmcp-atlas-ezo -t stdio -c uvx -a labmcp-atlas-ezo
```

### Other

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

## 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.

### 2026-09-29 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-28 (score 68, +29)

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

### 2026-09-27 (score 39, −33)

- [security regression] Stability: 0.03 → 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: 0.1.1 → 0.1.2

### 2026-09-26 (score 72, 0)

- [security regression] Tool safety: pass → unverified
- [security regression] Malware scan: 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 → 0.03
- [functional] First check of Schema quality: unverified
- [functional] Package version: 0.1.0 → 0.1.1

### 2026-09-25 (score 72)

First indexed and scored.

## MCP tools (13)

### `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).

### `read_value` (~91 tokens)

Read Value

Take one reading (about 1 s) and return every enabled output with its unit: pH; ORP in mV;
DO in mg/L (and % saturation if enabled); EC in µS/cm plus TDS (ppm), salinity (PSU) and
specific gravity if enabled; RTD temperature; humidity %RH (+ air temperature, dew point);
CO2 ppm; or pressure.

Output parameters:

- `raw` (string)
- `sensor` (string): Circuit type, e.g. 'pH', 'Dissolved oxygen'
- `temperature_compensation_c`: Temperature the reading is compensated to (pH, EC, DO only)
- `timestamp` (string): UTC time of the reading (ISO 8601)
- `unit` (string): Unit of the primary output
- `value` (number): The primary output (first value)
- `values` (array): Every enabled output of the circuit
- `warnings` (array)

### `get_info` (~54 tokens)

Get Info

Report the circuit type, firmware, device name, supply voltage and last restart reason,
LED state, calibration state, temperature compensation and type-specific settings (enabled
outputs, EC probe constant K, DO salinity/pressure compensation).

Output parameters:

- `calibration`
- `calibration_point_names` (array)
- `calibration_points`
- `device_name`
- `do_pressure_kpa`: DO atmospheric pressure compensation
- `do_salinity`: DO salinity compensation
- `enabled_outputs` (array)
- `firmware` (string)
- `led_on`
- `model` (string)
- `notes` (array)
- `probe_constant_k`: EC probe cell constant K
- `restart_reason`
- `sensor` (string)
- `supply_voltage_v`
- `temperature_compensation_c`

### `get_calibration_status` (~46 tokens)

Get Calibration Status

Report how many calibration points are stored and what that means for this circuit type;
for pH also the probe slope (acid/base % of ideal and zero offset in mV).

Output parameters:

- `advice` (string)
- `meaning` (string)
- `ph_acid_slope_percent`: pH only: acid slope vs ideal probe (%)
- `ph_base_slope_percent`: pH only: base slope vs ideal probe (%)
- `ph_zero_offset_mv`: pH only: zero-point offset (mV)
- `points` (integer)
- `sensor` (string)
- `valid_points` (array)

### `calibrate` (~187 tokens)

Calibrate

Store one calibration point. The probe must already be in the named standard (buffer,
air, dry, ...) with a stable reading. Point names are validated per circuit type. pH: a `mid`
calibration erases existing low/high points, so always do mid first. EC: do `dry` first.

Input parameters:

- `point` (string, required): pH: mid|low|high; ORP: single; DO: atmospheric|zero; EC: dry|single|low|high; RTD: single; CO2: zero|high; PRS: zero|high
- `value`: Value of the standard the probe is in (pH units, mV, µS/cm, temperature in the RTD's current scale, ppm CO2, pressure in current units). Omit for DO atmospheric/zero, EC dry and CO2/PRS zero.

Output parameters:

- `calibration_points` (integer)
- `meaning` (string)
- `message` (string)
- `point` (string)
- `reference_value`

### `clear_calibration` (~57 tokens)

Clear Calibration

Delete all stored calibration data (Cal,clear). pH/ORP/DO/EC/RTD return to uncalibrated;
CO2/PRS return to their factory calibration. The probe must be recalibrated afterwards.

Output parameters:

- `advice` (string)
- `meaning` (string)
- `ph_acid_slope_percent`: pH only: acid slope vs ideal probe (%)
- `ph_base_slope_percent`: pH only: base slope vs ideal probe (%)
- `ph_zero_offset_mv`: pH only: zero-point offset (mV)
- `points` (integer)
- `sensor` (string)
- `valid_points` (array)

### `set_temperature_compensation` (~60 tokens)

Set Temperature Compensation

Set the sample temperature used to compensate pH, EC or DO readings (T,n; always °C).
Not retained through a power cycle. Returns the value the circuit now uses.

Input parameters:

- `temperature_c` (number, required): Sample temperature in °C

Output parameters:

- `result` (number)

### `set_probe_constant` (~75 tokens)

Set Probe Constant

EC circuits only: set the conductivity probe's cell constant K to match the probe
(printed on it). Recalibrate after changing it. Returns the K now in use.

Input parameters:

- `k` (number, required): Cell constant K of the EC probe (e.g. 0.1, 1.0, 10)

Output parameters:

- `result` (number)

### `set_do_compensation` (~107 tokens)

Set Do Compensation

DO circuits only: set salinity compensation (irrelevant below ~2500 µS/cm) and/or
atmospheric pressure compensation (default 101.3 kPa; lower at altitude). Neither is
retained through a power cycle.

Input parameters:

- `pressure_kpa`: Atmospheric pressure in kPa
- `salinity`: Sample salinity (see salinity_unit)
- `salinity_unit` (string): 'us_cm' (µS/cm) or 'ppt'

Output parameters:

- `calibration`
- `calibration_point_names` (array)
- `calibration_points`
- `device_name`
- `do_pressure_kpa`: DO atmospheric pressure compensation
- `do_salinity`: DO salinity compensation
- `enabled_outputs` (array)
- `firmware` (string)
- `led_on`
- `model` (string)
- `notes` (array)
- `probe_constant_k`: EC probe cell constant K
- `restart_reason`
- `sensor` (string)
- `supply_voltage_v`
- `temperature_compensation_c`

### `set_led` (~48 tokens)

Set Led

Turn the circuit's status LED on or off. Returns the new LED state.

Input parameters:

- `on` (boolean, required): True = LED on (default), False = off (e.g. light-sensitive cultures)

Output parameters:

- `result` (boolean)

### `log_series` (~107 tokens)

Log Series

Record a series of readings (e.g. to watch a probe stabilise before calibrating, follow pH
or DO in a bioreactor, or log temperature). Returns every point plus mean, stdev, min, max
and drift per minute for each output.

Input parameters:

- `count` (integer): Number of readings
- `interval_s` (number): Seconds between readings (>= 1)
- `save_path`: Optional new .csv file for the full series (never overwritten)

Output parameters:

- `count` (integer)
- `points` (array)
- `saved_to`
- `sensor` (string)
- `stats` (array)

## Diagnostics

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

## Score history

- 2026-09-30: 69
- 2026-09-29: 69
- 2026-09-28: 68
- 2026-09-27: 39
- 2026-09-26: 72
- 2026-09-25: 72

## Common questions

### What is the Atlas Scientific EZO Sensors MCP server?

Atlas Scientific EZO Sensors is an MCP server listed in the public MCP registry as io.github.K-Dense-AI/labmcp-atlas-ezo. MCP server for Atlas Scientific EZO sensor circuits (pH, ORP, DO, EC, RTD, HUM, CO2, PRS) over UART. This page covers its PyPI package (labmcp-atlas-ezo).

### Is the Atlas Scientific EZO Sensors MCP server safe to use?

Atlas Scientific EZO Sensors scores 69 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 Atlas Scientific EZO Sensors MCP server expose?

Atlas Scientific EZO Sensors exposes 13 tools: get_connection_info, get_command_log, reconnect, read_value, get_info, and 8 more. Their descriptions and schemas cost roughly 953 tokens of context every time the server is loaded.

### Is the Atlas Scientific EZO Sensors MCP server still maintained?

Atlas Scientific EZO 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 Atlas Scientific EZO Sensors MCP server under?

Atlas Scientific EZO 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-atlas-ezo/
- Socket report: https://socket.dev/pypi/package/labmcp-atlas-ezo
- Repository: https://github.com/K-Dense-AI/lab-instrument-mcps
- Website: https://github.com/K-Dense-AI/lab-instrument-mcps/tree/main/servers/biology/atlas-ezo-sensors
- Changelog RSS feed: https://verifymcp.io/servers/k-dense-ai-labmcp-atlas-ezo/labmcp-atlas-ezo.xml
- Changelog JSON feed: https://verifymcp.io/servers/k-dense-ai-labmcp-atlas-ezo/labmcp-atlas-ezo.json
- HTML version of this page: https://verifymcp.io/servers/k-dense-ai-labmcp-atlas-ezo/labmcp-atlas-ezo