# JULABO Circulator (pypi · labmcp-julabo)

MCP server for JULABO heating and refrigerated circulators (CORIO, MAGIO, DYNEO).

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

## Components

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

## Channel facts

- Registry: `pypi`
- Package: `labmcp-julabo`
- 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**: 82/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 1043 tokens (~104/item across 10 items; 10 tools + 0 resources), lean.
  - 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**: 97/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 89% 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 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 11 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 JULABO Circulator MCP server?

JULABO Circulator runs locally as a PyPI package, launched with uvx labmcp-julabo. 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-julabo -- uvx labmcp-julabo
```

### Cursor

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

### VS Code

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

### Codex

```bash
codex mcp add k-dense-ai-labmcp-julabo -- uvx labmcp-julabo
```

### opencode

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

### OpenClaw

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

### Hermes

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

### Netclaw

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

### Vellum

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

### Other

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

## 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, −5)

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

### 2026-09-27 (score 72, 0)

- [functional] Package version: 0.1.1 → 0.1.2

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

First indexed and scored.

## MCP tools (10)

### `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_temperatures` (~64 tokens)

Read Temperatures

Read the bath temperature, the heating/cooling power in % and the safety-sensor
temperature, and optionally the external Pt100 sensor.

Input parameters:

- `include_external` (boolean): Also read the external Pt100 sensor (MAGIO/DYNEO; not CORIO)

Output parameters:

- `bath_temperature_c` (number): Actual bath / internal temperature (in_pv_00)
- `external_temperature_c`: External Pt100 sensor (in_pv_02); None if not requested or not available (CORIO)
- `heating_power_pct` (number): Actuating variable in %; negative = cooling (in_pv_01)
- `safety_sensor_temperature_c` (number): High-temperature safety sensor (in_pv_03)
- `timestamp` (string)

### `get_status` (~56 tokens)

Get Status

Report the circulator's status message (decoded: operating state, rejected command or
alarm), whether temperature control is running, the setpoint, the device's own
excess-temperature protection setting and warning limits, and the firmware version.

Output parameters:

- `bath_temperature_c` (number)
- `code` (integer): Status code: 00-03 operating state, negative = alarm or rejected command
- `excess_temperature_protection_c` (number): Setting of the high-temperature safety function on the device (in_pv_04)
- `firmware` (string)
- `high_warning_limit_c`: in_sp_03; not available on CORIO CD
- `kind` (string)
- `low_warning_limit_c`: in_sp_04; not available on CORIO CD
- `meaning` (string)
- `message` (string): Status text sent by the circulator
- `remote_control`: True if remote control is enabled (None during alarms)
- `running` (boolean): Temperature control started (in_mode_05)
- `setpoint_c` (number)
- `timestamp` (string)

### `get_setpoint` (~22 tokens)

Get Setpoint

Read the current temperature setpoint and whether temperature control is running.

Output parameters:

- `running` (boolean)
- `setpoint_c` (number): Setpoint read back from the circulator
- `status` (string)
- `timestamp` (string)

### `set_setpoint` (~94 tokens)

Set Setpoint

Set the circulator's temperature setpoint (out_sp_00). If temperature control is running,
the circulator starts heating or cooling to it immediately. Refused outside
\`min_temperature_c`..`max_temperature_c`; the circulator itself also rejects values outside
its range or warning limits (reported as an error). Needs remote control enabled.

Input parameters:

- `temperature_c` (number, required): New setpoint in °C

Output parameters:

- `running` (boolean)
- `setpoint_c` (number): Setpoint read back from the circulator
- `status` (string)
- `timestamp` (string)

### `start_circulation` (~78 tokens)

Start Circulation

Start temperature control (out_mode_05 1): the pump runs and the bath heats or cools to
the setpoint, which is checked against the safety limits first (it may have been changed on
the front panel). Make sure the bath is filled and any external hoses are connected and
secured. Needs remote control enabled.

Output parameters:

- `running` (boolean)
- `setpoint_c` (number): Setpoint read back from the circulator
- `status` (string)
- `timestamp` (string)

### `stop_circulation` (~50 tokens)

Stop Circulation

Stop temperature control and the pump (out_mode_05 0), then confirm with in_mode_05.
Also ends a running `wait_for_temperature`. The bath stays hot/cold after stopping.

Output parameters:

- `result` (string)

### `wait_for_temperature` (~178 tokens)

Wait For Temperature

Poll the bath (or external) temperature until it has been within `tolerance_c` of the
target for `stable_for_s` seconds, or `timeout_s` passes. Does not change anything; start
circulation first. Stops early (reached = false) if the circulator raises an alarm or a
stop command is sent. Returns a short temperature trace.

Input parameters:

- `poll_interval_s` (number): Seconds between readings
- `sensor` (string): 'external' = Pt100 sensor (MAGIO/DYNEO)
- `stable_for_s` (number): Must stay within tolerance this long
- `target_c`: Temperature to wait for; default: the current setpoint
- `timeout_s` (number): Give up after this many seconds
- `tolerance_c` (number): Accepted deviation in °C

Output parameters:

- `aborted` (boolean): True if a stop command or an alarm ended the wait early
- `elapsed_s` (number)
- `final_temperature_c` (number)
- `message` (string)
- `reached` (boolean)
- `sensor` (string)
- `target_c` (number)
- `tolerance_c` (number)
- `trace` (array): (seconds since start, °C), at most ~30 points

## Diagnostics

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

## Score history

- 2026-09-30: 67
- 2026-09-29: 67
- 2026-09-28: 67
- 2026-09-27: 72
- 2026-09-26: 72

## Common questions

### What is the JULABO Circulator MCP server?

JULABO Circulator is an MCP server listed in the public MCP registry as io.github.K-Dense-AI/labmcp-julabo. MCP server for JULABO heating and refrigerated circulators (CORIO, MAGIO, DYNEO). This page covers its PyPI package (labmcp-julabo).

### Is the JULABO Circulator MCP server safe to use?

JULABO Circulator 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 JULABO Circulator MCP server expose?

JULABO Circulator exposes 10 tools: get_connection_info, get_command_log, reconnect, read_temperatures, get_status, and 5 more. Their descriptions and schemas cost roughly 663 tokens of context every time the server is loaded.

### Is the JULABO Circulator MCP server still maintained?

JULABO Circulator 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 JULABO Circulator MCP server under?

JULABO Circulator 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-julabo/
- Socket report: https://socket.dev/pypi/package/labmcp-julabo
- Repository: https://github.com/K-Dense-AI/lab-instrument-mcps
- Website: https://github.com/K-Dense-AI/lab-instrument-mcps/tree/main/servers/chemistry/julabo-circulator
- Changelog RSS feed: https://verifymcp.io/servers/k-dense-ai-labmcp-julabo/labmcp-julabo.xml
- Changelog JSON feed: https://verifymcp.io/servers/k-dense-ai-labmcp-julabo/labmcp-julabo.json
- HTML version of this page: https://verifymcp.io/servers/k-dense-ai-labmcp-julabo/labmcp-julabo