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.

Opentrons OT-2 / Flex

PYPI · LABMCP-OPENTRONS · SCANNED SEP 30

MCP server for Opentrons OT-2 and Flex liquid-handling robots (HTTP API).

Available components

70 Trust /100
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 Security50
  • 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 24 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 3 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability84
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 1617 tokens (~89/item across 18 items; 18 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management17
  • Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage98
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 94% 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 18 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 19 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
Install

How do I install the Opentrons OT-2 / Flex MCP server?

Opentrons OT-2 / Flex runs locally as a PyPI package, launched with uvx labmcp-opentrons. 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-opentrons

# add to Claude Code
claude mcp add k-dense-ai-labmcp-opentrons -- uvx labmcp-opentrons
// .cursor/mcp.json
{
  "mcpServers": {
    "k-dense-ai-labmcp-opentrons": {
      "command": "uvx",
      "args": [
        "labmcp-opentrons"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "k-dense-ai-labmcp-opentrons": {
      "command": "uvx",
      "args": [
        "labmcp-opentrons"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add k-dense-ai-labmcp-opentrons -- uvx labmcp-opentrons
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "k-dense-ai-labmcp-opentrons": {
      "type": "local",
      "command": [
        "uvx",
        "labmcp-opentrons"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add k-dense-ai-labmcp-opentrons --command uvx --arg labmcp-opentrons
# ~/.hermes/config.yaml
mcp_servers:
  k-dense-ai-labmcp-opentrons:
    command: "uvx"
    args: ["labmcp-opentrons"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "k-dense-ai-labmcp-opentrons": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "labmcp-opentrons"
      ]
    }
  }
}
# add to Vellum
assistant mcp add k-dense-ai-labmcp-opentrons -t stdio -c uvx -a labmcp-opentrons
// mcp.json
{
  "mcpServers": {
    "k-dense-ai-labmcp-opentrons": {
      "command": "uvx",
      "args": [
        "labmcp-opentrons"
      ]
    }
  }
}
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.

  • 29 Sept 26 +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.

  • 28 Sept 26 +29
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 27 Sept 26 0
    • Package version: 0.1.2 → 0.1.3 functional
  • 26 Sept 26 −33
    • Tool safety: pass → unverified ▼ security
    • 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. security
    • Capabilities: pass → unverified ▼ functional
    • Tool coverage: 100 → unverified ▼ functional
    • Stability: unverified → 0.03 ▲ functional
    • First check of Schema quality: unverified functional
    • Package version: 0.1.0 → 0.1.2 functional
    • Package version: 0.1.0 → 0.1.1 functional
  • 25 Sept 26 73

    First indexed and scored.

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 30 Sept 2026 · Analysed pypi/labmcp-opentrons@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-opentrons-v0.1.3
Rekor log index 2969517135
Predicate type PyPI publish attestation https://docs.pypi.org/attestations/publish/v1
Subject digest sha256:cb756f2fda7c4fe14ddbd271114137a0468d6e6d1d91e40759884a08e93f56f7

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted hatchling.build

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

Dependencies 24 packages
Packages resolved 24
Stale 2
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 18 exposed · ~1,122 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
deactivate_modules ~77

Switch attached modules off: stop heating/cooling (Temperature Module, Thermocycler block and lid, Heater-Shaker heater), stop shaking, and lower Magnetic Module magnets. Only possible when no run is in progress: stop the run first.

NameTypeReqDescription
module_ids––Module IDs from list_modules; omit to switch off all modules
NameTypeReqDescription
resultarrayyes–

No examples provided.

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_protocol ~85

Show a stored protocol's analysis: whether it is ready to run, analysis errors, the deck layout it expects (labware and modules per slot, pipettes per mount, liquids), the number of steps and the highest module temperature / shake speed it requests. Review this with the user before start_run.

NameTypeReqDescription
protocol_idstringyesProtocol ID from list_protocols
NameTypeReqDescription
analysis_errorsarrayyesErrors from the robot's protocol analysis
analysis_id–yes–
analysis_result–yes'ok', 'not-ok' or 'parameter-value-required'
analysis_status–yes'pending' or 'completed'
api_level–yes–
command_count–yesNumber of steps in the analyzed protocol
created_at–yes–
deck–yesLabware, modules and pipettes the protocol expects
filesarrayyes–
idstringyes–
max_module_temperature_c–yesHighest module temperature the protocol requests
max_shake_speed_rpm–yesFastest Heater-Shaker speed the protocol requests
messagestringyes–
namestringyes–
problemsarrayyes–
protocol_type–yes'python' or 'json'
ready_to_runbooleanyesTrue only if analysis completed with result 'ok' and limits pass
robot_type–yes–
run_time_parametersarrayyes–

No examples provided.

get_robot_status ~52

Report the robot's name, model (Flex/OT-2), software and firmware versions, lights, door and E-stop state, and the current run. Call this first to check the robot is ready.

Input schema present but exposes no named parameters.

NameTypeReqDescription
current_run_id–yes–
current_run_status–yes–
door_must_be_closed_to_run–yes–
door_open–yesFront door open (None if not reported)
estop–yesE-stop state on Flex ('disengaged' is OK); None on OT-2
firmware_version–yes–
lights_onbooleanyes–
model–yes'Flex' or 'OT-2'
name–yes–
problemsarrayyes–
protocol_api_versionsstringyesSupported Python Protocol API versions, e.g. '2.15-2.26'
ready_to_start_runbooleanyesNo active run, door OK, E-stop OK
serial–yes–
software_version–yesRobot software (opentrons) version
system_version–yes–
timestampstringyes–

No examples provided.

get_run_status ~78

Report a run's status, the step it is on, progress, recent steps and any errors, plus advice on what to do next (e.g. when the run is waiting for error recovery).

NameTypeReqDescription
recent_commandsinteger–How many recent steps to include
run_id––Run ID; omit for the current run
NameTypeReqDescription
advicestringyes–
commands_executedintegeryesCommands queued or run so far
commands_expected–yesCommands in the protocol analysis
completed_at–yes–
created_at–yes–
currentbooleanyes–
current_command–yes–
errorsarrayyes–
idstringyes–
progress_percent–yes–
protocol_id–yes–
recent_commandsarrayyes–
recovering_from–yes–
started_at–yes–
statusstringyesidle, running, paused, blocked-by-open-door, stop-requested, finishing, awaiting-recovery(-paused/-blocked-by-open-door), stopped, failed, succeeded
timestampstringyes–

No examples provided.

home_robot ~51

Home all axes of the robot (the gantry and pipettes move to their home positions). Refused while a run is active. Make sure nothing is in the robot's path and the door is closed.

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes–

No examples provided.

list_instruments ~41

List attached pipettes (and the Flex gripper): mount, name, channels, volume range, and whether a tip is detected and calibration data exists.

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultarrayyes–

No examples provided.

list_modules ~45

List attached modules (Temperature Module, Heater-Shaker, Thermocycler, Magnetic Module, Absorbance Plate Reader, ...) with live temperatures, targets, shake speed and status.

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultarrayyes–

No examples provided.

list_protocols ~27

List protocols stored on the robot (newest last) with their analysis status and result.

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultarrayyes–

No examples provided.

list_runs ~31

List recent protocol runs, newest first, with their status.

NameTypeReqDescription
limitinteger–Maximum runs to list
NameTypeReqDescription
resultarrayyes–

No examples provided.

pause_run ~44

Pause a running protocol. The robot finishes its current step and then holds; resume_run continues it.

NameTypeReqDescription
run_id––Run ID; omit for the current run
NameTypeReqDescription
acceptedbooleanyes–
actionstringyes–
messagestringyes–
run_id–yes–
status–yes–
timestampstringyes–

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.

resume_run ~124

Resume a paused run (the robot starts moving again), or leave error recovery. Refused while the door is open. For a run awaiting recovery, `error_recovery` must be given.

NameTypeReqDescription
error_recovery––Only for runs awaiting error recovery, after the user physically checked the robot: 'continue' resumes from the robot's current state (the failed step is skipped); 'assume_false_positive' treats the…
run_id––Run ID; omit for the current run
NameTypeReqDescription
advicestringyes–
commands_executedintegeryesCommands queued or run so far
commands_expected–yesCommands in the protocol analysis
completed_at–yes–
created_at–yes–
currentbooleanyes–
current_command–yes–
errorsarrayyes–
idstringyes–
progress_percent–yes–
protocol_id–yes–
recent_commandsarrayyes–
recovering_from–yes–
started_at–yes–
statusstringyesidle, running, paused, blocked-by-open-door, stop-requested, finishing, awaiting-recovery(-paused/-blocked-by-open-door), stopped, failed, succeeded
timestampstringyes–

No examples provided.

set_lights ~36

Turn the robot's deck (rail) lights on or off.

NameTypeReqDescription
onbooleanyesTrue to turn the deck lights on
NameTypeReqDescription
resultstringyes–

No examples provided.

start_run ~124

Create a run of an analyzed protocol and start it: the robot begins moving and pipetting. Refused unless the protocol's analysis completed without errors, its module setpoints are within the safety limits, no other run is active, the door is closed and the E-stop is released.

NameTypeReqDescription
deck_confirmedbooleanyesTrue only after the user confirmed the deck matches get_protocol's layout (labware, tips, liquids, modules) and nothing else is in the robot's path
protocol_idstringyesProtocol ID from upload_protocol or list_protocols
NameTypeReqDescription
advicestringyes–
commands_executedintegeryesCommands queued or run so far
commands_expected–yesCommands in the protocol analysis
completed_at–yes–
created_at–yes–
currentbooleanyes–
current_command–yes–
errorsarrayyes–
idstringyes–
progress_percent–yes–
protocol_id–yes–
recent_commandsarrayyes–
recovering_from–yes–
started_at–yes–
statusstringyesidle, running, paused, blocked-by-open-door, stop-requested, finishing, awaiting-recovery(-paused/-blocked-by-open-door), stopped, failed, succeeded
timestampstringyes–

No examples provided.

stop_run ~57

Stop (cancel) a run immediately. A stopped run cannot be resumed; the robot homes and drops any attached tips into the trash. Use this whenever something looks wrong.

NameTypeReqDescription
run_id––Run ID; omit for the current run
NameTypeReqDescription
acceptedbooleanyes–
actionstringyes–
messagestringyes–
run_id–yes–
status–yes–
timestampstringyes–

No examples provided.

upload_protocol ~129

Upload a protocol file (plus optional custom labware) to the robot. The robot analyzes it (simulates it) and this tool returns the analysis: errors, deck layout and whether it is ready to run. Uploading does not move the robot. Uploading identical files returns the existing protocol.

NameTypeReqDescription
labware_paths––Custom labware definition .json files used by a Python protocol
pathstringyesLocal path of the protocol file (.py Python API or .json)
wait_for_analysis_snumber–How long to wait for the robot's analysis to finish
NameTypeReqDescription
analysis_errorsarrayyesErrors from the robot's protocol analysis
analysis_id–yes–
analysis_result–yes'ok', 'not-ok' or 'parameter-value-required'
analysis_status–yes'pending' or 'completed'
api_level–yes–
command_count–yesNumber of steps in the analyzed protocol
created_at–yes–
deck–yesLabware, modules and pipettes the protocol expects
filesarrayyes–
idstringyes–
max_module_temperature_c–yesHighest module temperature the protocol requests
max_shake_speed_rpm–yesFastest Heater-Shaker speed the protocol requests
messagestringyes–
namestringyes–
problemsarrayyes–
protocol_type–yes'python' or 'json'
ready_to_runbooleanyesTrue only if analysis completed with result 'ok' and limits pass
robot_type–yes–
run_time_parametersarrayyes–

No examples provided.

Common questions

What is the Opentrons OT-2 / Flex MCP server?

Opentrons OT-2 / Flex is an MCP server listed in the public MCP registry as io.github.K-Dense-AI/labmcp-opentrons. MCP server for Opentrons OT-2 and Flex liquid-handling robots (HTTP API). This page covers its PyPI package (labmcp-opentrons).

Is the Opentrons OT-2 / Flex MCP server safe to use?

Opentrons OT-2 / Flex scores 70 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 Opentrons OT-2 / Flex MCP server expose?

Opentrons OT-2 / Flex exposes 18 tools: get_connection_info, get_command_log, reconnect, get_robot_status, list_instruments, and 13 more. Their descriptions and schemas cost roughly 1,122 tokens of context every time the server is loaded.

Is the Opentrons OT-2 / Flex MCP server still maintained?

Opentrons OT-2 / Flex 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 Opentrons OT-2 / Flex MCP server under?

Opentrons OT-2 / Flex 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.