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.

Thorlabs Optical Power Meter

PYPI · LABMCP-THORLABS-PM

MCP server for Thorlabs optical power meters (PM100 family, PM400, PM101, PM5020) over SCPI.

Available components

−15 this week 81 Trust /100

Last scanned (10 hours ago)

Scores higher than 80% 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 Security49
  • 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
  • 2 of 17 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 Usability79
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 1055 tokens (~95/item across 11 items; 11 tools + 0 resources), lean.Pass
  • 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 Coverage97
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 89% 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 11 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 12 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.

  • 20 Nov 26 −14
    • Malware scan: pass → unverified ▼ security
    • Stability: 0.97 → pass security
  • 19 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 18 Nov 26 −16
    • Malware scan: pass → unverified ▼ security
    • Stability: pass → 0.93 functional
  • 17 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 15 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
  • 13 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 12 Nov 26 +1
    • Stability: 0.97 → pass 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.

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-thorlabs-pm@0.1.2

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-thorlabs-pm-v0.1.2
Rekor log index 2969518269
Predicate type PyPI publish attestation https://docs.pypi.org/attestations/publish/v1
Subject digest sha256:99928e821a0b1dfae0ce00953a7f242eebfd5ca1d5f512d6310abd11edfd7408

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 17 packages
Packages resolved 17
Stale 2
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 11 exposed · ~657 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 ~45

Identify the meter console and the attached sensor head (model, serial, type, wavelength range, power ranges), and report the present wavelength, averaging, range and zero value.

Input schema present but exposes no named parameters.

NameTypeReqDescription
auto_range–yes–
averaging_countintegeryes–
firmwarestringyes–
manufacturerstringyes–
max_range_w–yesLeast sensitive range (W). Not the sensor damage threshold - check the sensor spec.
modelstringyes–
range_w–yesUpper limit of the power range in use, W
sensor–yesNone if no sensor head is plugged in
serialstringyes–
timestampstringyes–
wavelength_max_nm–yes–
wavelength_min_nm–yes–
wavelength_nm–yes–
zero_value–yesPresent dark-zero correction (A for photodiodes, V for thermal)

No examples provided.

log_power_series ~136

Log a series of power readings to characterise laser stability, warm-up or drift. Returns mean, stdev, min/max, RMS and peak-to-peak stability (%) and drift (%/min), plus the readings (downsampled to `max_points`; use `save_path`, a new .csv file, to keep all of them).

NameTypeReqDescription
countinteger–Number of readings
interval_snumber–Seconds between readings (0 = as fast as the meter allows)
max_pointsinteger–Maximum readings returned in the reply
save_path––Optional CSV path for every reading
NameTypeReqDescription
completedboolean–False if the series stopped early to stay within the tool's time budget
countintegeryesReadings actually taken
drift_percent_per_min–yesDrift relative to the mean, % per minute
drift_w_per_minnumberyesLeast-squares slope of power vs time, W per minute
duration_snumberyesActual elapsed time from first to last reading
interval_snumberyes–
max_wnumberyes–
mean_formattedstringyes–
mean_wnumberyes–
min_wnumberyes–
peak_to_peak_stability_percent–yes(max - min) / mean x 100
points_returnedintegeryes–
power_warrayyesReadings in W (downsampled to max_points)
rms_stability_percent–yesstdev / mean x 100 (None if mean <= 0)
saved_to–––
startedstringyes–
stdev_wnumberyes–
time_sarrayyesReading times relative to the first reading (downsampled to max_points)
wavelength_nm–yes–

No examples provided.

read_power ~41

Read the optical power once (in W, plus dBm and a formatted string). The reading uses the configured correction wavelength and averaging; set the wavelength first.

Input schema present but exposes no named parameters.

NameTypeReqDescription
formattedstringyesPower with an SI prefix, e.g. '1.234 mW'
power_dbm–yesPower in dBm re 1 mW; None if the reading is <= 0
power_wnumberyes–
sensorstringyes–
timestampstringyes–
wavelength_nm–yesCorrection wavelength used for this reading

No examples provided.

read_sensor_temperature ~32

Read the sensor head temperature in °C (thermal sensors and other heads with a built-in temperature sensor only).

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

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_averaging ~76

Set how many samples the meter averages for each reading. More averaging lowers noise but slows each reading (PM100 series: ~3 ms per sample; PM400/PM101/PM5020: 1 ms).

NameTypeReqDescription
countintegeryesSamples averaged per reading (PM100: ~3 ms per sample)

Structured output declared, but exposes no named fields.

No examples provided.

set_range ~79

Select auto-ranging, or a fixed power range that fits `range_w` (the meter picks the most sensitive range that can hold that power). A fixed range reports over-range if exceeded.

NameTypeReqDescription
modestring–auto-ranging or a fixed range
range_w––For manual mode: the highest power you expect, in W

Structured output declared, but exposes no named fields.

No examples provided.

set_wavelength ~63

Set the correction wavelength (nm) the meter uses to convert sensor signal to power. Must be within the sensor's calibrated range (see `get_device_info`); sent as a whole number of nm.

NameTypeReqDescription
wavelength_nmnumberyesSource wavelength in nm

Structured output declared, but exposes no named fields.

No examples provided.

zero_sensor ~64

Dark-zero the sensor (removes dark current / thermal offset). BEFORE calling, ask the user to block the beam and cover the sensor aperture completely, and wait for them to confirm: zeroing with light on the sensor corrupts all later readings. Takes a few seconds.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

Install

How do I install the Thorlabs Optical Power Meter MCP server?

Thorlabs Optical Power Meter runs locally as a PyPI package, launched with uvx labmcp-thorlabs-pm. 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-thorlabs-pm

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

What is the Thorlabs Optical Power Meter MCP server?

Thorlabs Optical Power Meter is an MCP server listed in the public MCP registry as io.github.K-Dense-AI/labmcp-thorlabs-pm. MCP server for Thorlabs optical power meters (PM100 family, PM400, PM101, PM5020) over SCPI. This page covers its PyPI package (labmcp-thorlabs-pm).

Is the Thorlabs Optical Power Meter MCP server safe to use?

Thorlabs Optical Power Meter scores 81 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 Thorlabs Optical Power Meter MCP server expose?

Thorlabs Optical Power Meter exposes 11 tools: get_connection_info, get_command_log, reconnect, get_device_info, read_power, and 6 more. Their descriptions and schemas cost roughly 657 tokens of context every time the server is loaded.

Is the Thorlabs Optical Power Meter MCP server still maintained?

Thorlabs Optical Power Meter 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 Thorlabs Optical Power Meter MCP server under?

Thorlabs Optical Power Meter 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 Thorlabs Optical Power Meter MCP server?

VerifyMCP ran 15 checks on Thorlabs Optical Power Meter, 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 Thorlabs Optical Power Meter: 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.