Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

LabJack T-series DAQ

PYPI · LABMCP-LABJACK

MCP server for LabJack T4, T7/T7-Pro and T8 DAQ devices (LJM).

Available components

0 this week 79 Trust /100

Last scanned (19 hours ago)

Scores higher than 75% of PyPI servers

Category IoT and Hardware

Trust breakdown (7 categories)

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. How we score → Why this is hard to score →

Supply Chain Security48
  • Malware scan not yet available for this package.Unverified
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
  • 3 of 18 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to K-Dense-AI/lab-instrument-mcps). View diagnostics → Pass
  • Clear OSI-approved license (Apache-2.0).Pass
  • Actively maintained (last published 55 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability69
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1982 tokens (~165/item across 12 items; 12 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage96
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 88% of tool parameters carry a description.Partial
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
What we tested

Checks we ran (15)

  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Malware scan in Supply Chain SecurityMalware scan not yet available for this package.

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Nov 26 +1
    • Stability: 0.97 → pass security
  • 18 Nov 26 −1
    • Stability: pass → 0.97 functional
  • 13 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
  • 12 Nov 26 +16
    • Malware scan: unverified → pass ▲ security
    • Stability: 0.97 → pass security
  • 11 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
  • 10 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Nov 26 −2
    • Stability: pass → 0.90 functional
  • 6 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Analysed pypi/labmcp-labjack@0.1.3

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem pypi
Reason Verified
Discovered via Registry attestation endpoint
Source repo K-Dense-AI/lab-instrument-mcps
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/K-Dense-AI/lab-instrument-mcps/.github/workflows/release.yml@refs/tags/labmcp-labjack-v0.1.3
Rekor log index 2969517912
Predicate type PyPI publish attestation https://docs.pypi.org/attestations/publish/v1
Subject digest sha256:1c31a276be3ce82736ab458b1b816c3d6153f6b001aca890b13777f9de96d645

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend Known build tool hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 18 packages
Packages resolved 18
Stale 3
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 12 exposed · ~1,532 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
get_command_log ~46

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

NameTypeReqDescription
limitinteger––
NameTypeReqDescription
resultarrayyes–

No examples provided.

get_connection_info ~40

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

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

get_device_info ~56

Identify the connected LabJack (model, serial, firmware, connection) and list what it offers: analog inputs, valid input ranges, resolution indices, DAC range, digital lines and stream rate. Call this before configuring channels.

Input schema present but exposes no named parameters.

NameTypeReqDescription
analog_inputsarrayyes–
connectionstringyes–
dac_range_varrayyes[min, max] DAC output in V
dac_voltages_varrayyesCurrent DAC0, DAC1 settings in V
device_name–yes–
digital_linesarrayyes–
firmwarestringyes–
hardware_versionstringyes–
input_ranges_varrayyesValid ± input ranges in V (empty for the T4: fixed ranges)
ip_address–yes–
max_resolution_indexintegeryes–
max_stream_samples_per_snumberyes–
modelstringyes–
serialstringyes–
thermocouple_supportedbooleanyes–
timestampstringyes–

No examples provided.

read_analog_inputs ~250

Read one or more analog inputs once (command-response) and return volts. Range and resolution settings persist on the device until changed. On the T8, several channels are sampled simultaneously. Each reading reports what it was measured against (GND or the negative input). Fails while a stream is running.

NameTypeReqDescription
channelsarrayyesAIN numbers, e.g. [0, 1, 2]
differential––T7 only: true = measure AINn - AIN(n+1) for even n (e.g. AIN0-AIN1), false = single-ended, omit = keep the current setting
range_v––± input range in V for all listed channels (T7: 10/1/0.1/0.01; T8: 11 ... 0.018). Omit to keep the current range. Not settable on the T4.
resolution_index––Higher = less noise, slower (T4 0-5, T7 0-8, T7-Pro 0-12, T8 0-16; 0 = default). Omit to keep.
NameTypeReqDescription
readingsarrayyes–
simultaneousbooleanyesTrue if all channels were sampled at the same instant (T8)
timestampstringyes–

No examples provided.

read_device_temperature ~60

Read the LabJack's internal temperature sensor (°C, about ±2 °C) and the estimated ambient air temperature. On the T8 also returns the sensor next to each AIN terminal. Cannot be read while a stream is running.

Input schema present but exposes no named parameters.

NameTypeReqDescription
ambient_estimate_cnumberyesEstimated air temperature outside the enclosure
device_temperature_cnumberyesInternal sensor (TEMPERATURE_DEVICE_K), ±2 °C
terminal_temperatures_c–yesT8 only: sensor next to each AIN0-AIN7 terminal
timestampstringyes–

No examples provided.

read_digital_inputs ~104

Report the logic level and direction (input/output/analog) of digital I/O lines. Uses the DIO_STATE/DIO_DIRECTION bitmask registers, which never change a line's direction, so it is safe to call while lines are driving equipment. Outputs report the level actually on the terminal.

NameTypeReqDescription
lines––Lines to report, e.g. ['FIO0', 'EIO3'] or ['DIO4']. Omit for all lines.
NameTypeReqDescription
linesarrayyes–
timestampstringyes–

No examples provided.

read_thermocouple ~270

Read a thermocouple with the T7/T8 AIN thermocouple extended feature (types B, C, E, J, K, N, R, S, T) and return °C with the measured voltage and cold-junction temperature. This configures the AIN extended feature on the channel (the T7 switches a ±10 V range to ±0.1 V). A floating/open thermocouple returns valid=false. Accuracy is dominated by the CJC: about ±2 °C with the internal sensor. Not available on the T4.

NameTypeReqDescription
channelintegeryesAIN the thermocouple + lead is on
cjcstring–Cold-junction sensor: 'internal' (device sensor; best for T7 screw terminals / T8) or 'lm34' (LM34 on cjc_channel, e.g. on a CB37)
cjc_channel––AIN of the LM34 when cjc='lm34'
differentialboolean–T7 only: thermocouple between AINn (+) and AIN(n+1) (-); recommended on the CB37
resolution_index––Omit for the device default
thermocouple_typestring––
NameTypeReqDescription
channelstringyes–
cjc_sourcestringyes–
cjc_temperature_cnumberyes–
message–––
temperature_c–yesHot-junction temperature; None if the reading is invalid
thermocouple_typestringyes–
thermocouple_voltage_vnumberyes–
timestampstringyes–
validbooleanyes–

No examples provided.

reconnect ~35

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

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

set_digital_output ~115

Make a digital line an output and drive it high (3.3 V) or low (0 V). Digital outputs often switch relays, solid-state relays, valves or instrument trigger inputs, so confirm with the user what the line controls. The line keeps driving until changed or released with `set_outputs_safe`.

NameTypeReqDescription
levelstringyes–
linestringyesDigital line, e.g. 'FIO0', 'EIO2', 'CIO1' or 'DIO5'
NameTypeReqDescription
levelstringyes–
linestringyes–
timestampstringyes–

No examples provided.

set_outputs_safe ~112

Put the outputs in a safe state: stop any stream, set DAC0 and DAC1 to 0 V, and release every digital line this server drove (plus the `safe_dio` option lines) to input - or drive them low with dio_mode='low'. Use when finished or if anything looks wrong.

NameTypeReqDescription
dio_modestring–'input' (default) returns lines to the power-up state (input with pull-up); 'low' drives them to 0 V instead
NameTypeReqDescription
actionsarrayyes–
timestampstringyes–

No examples provided.

stream_analog ~288

Acquire a hardware-timed waveform on one or more analog inputs (LJM stream mode) and return per-channel statistics plus a downsampled waveform; optionally save everything to CSV. Bounded by the `max_stream_duration_s` and `max_scan_rate_hz` limits and the device maximum (T4 50 kS/s, T7 100 kS/s aggregate, T8 40 kscans/s). On the T8, list adjacent channels in order; on the T7 the streamed inputs are set to single-ended. Blocks for `duration_s`; `set_outputs_safe` stops a running stream early.

NameTypeReqDescription
channelsarrayyesAIN numbers, e.g. [0, 1]
duration_snumber–Acquisition time in seconds
max_pointsinteger–Max points per channel in the returned waveform
range_v––± range in V for all channels (T7/T8); omit to keep
resolution_index––Stream resolution index; omit for default
save_path––Write the full-resolution data to this new .csv file (never overwritten)
scan_rate_hznumber–Scans per second (one sample of every channel per scan). At least 1, so set_outputs_safe can stop the stream within a second; use read_analog_inputs for slower logging
NameTypeReqDescription
abortedbooleanyesTrue if set_outputs_safe stopped the stream early (the data covers the scans read)
channelsarrayyes–
downsample_factorintegeryesScans per min/max pair (1 = every scan returned)
duration_snumberyes–
requested_scan_rate_hznumberyes–
saved_to–yesAbsolute path of the full-resolution CSV, if requested
scan_rate_hznumberyesActual scan rate the device ran at
scansintegeryes–
skipped_scansintegeryesScans lost to buffer overflow (null in the waveform, empty in the CSV)
statsarrayyes–
time_sarrayyesTime of each returned (downsampled) point from the first scan
timestampstringyes–
waveforms_vobjectyesDownsampled waveform per channel. Each block of downsample_factor scans contributes its minimum and maximum in time order (placed at the block's first and last scan time), so spikes are kept

No examples provided.

write_dac ~156

Set an analog output (DAC0/DAC1) to a DC voltage. The output stays at this value until changed or `set_outputs_safe` is called. This energises whatever is wired to the DAC (a heater driver, valve, laser or motor controller input). Checked against `max_dac_voltage_v` and the model's hardware range before anything is sent. The DAC can source about 20 mA through 50 Ohm; loads pull the voltage down.

NameTypeReqDescription
dacintegeryes0 for DAC0, 1 for DAC1
voltage_vnumberyesOutput voltage (T4/T7: 0-5 V, T8: 0-10 V)
NameTypeReqDescription
dacstringyes–
readback_vnumberyes–
requested_vnumberyes–
timestampstringyes–

No examples provided.

Install

How do I install the LabJack T-series DAQ MCP server?

LabJack T-series DAQ runs locally as a PyPI package, launched with uvx labmcp-labjack. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · labmcp-labjack

# add to Claude Code
claude mcp add k-dense-ai-labmcp-labjack -- uvx labmcp-labjack
Common questions

What is the LabJack T-series DAQ MCP server?

LabJack T-series DAQ is an MCP server listed in the public MCP registry as io.github.K-Dense-AI/labmcp-labjack. MCP server for LabJack T4, T7/T7-Pro and T8 DAQ devices (LJM). This page covers its PyPI package (labmcp-labjack).

Is the LabJack T-series DAQ MCP server safe to use?

LabJack T-series DAQ scores 79 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 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 LabJack T-series DAQ MCP server expose?

LabJack T-series DAQ exposes 12 tools: get_connection_info, get_command_log, reconnect, get_device_info, read_analog_inputs, and 7 more. Their descriptions and schemas cost roughly 1,532 tokens of context every time the server is loaded.

Is the LabJack T-series DAQ MCP server still maintained?

LabJack T-series DAQ is still listed as active in the MCP registry. We last reached this channel on 21 November 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 LabJack T-series DAQ MCP server under?

LabJack T-series DAQ 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.

What did VerifyMCP test on the LabJack T-series DAQ MCP server?

VerifyMCP ran 15 checks on LabJack T-series DAQ, covering Known CVEs, Install scripts, Dependency health, Source repository and 11 more. One item could not be completed, a gap on our side rather than a finding about LabJack T-series DAQ: Malware scan. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.