Use Guided Prompts

mcpyvisa ships with five MCP prompts — structured instruction templates that guide the LLM through common instrument workflows. Prompts are not tools. They do not execute commands directly. Instead, they provide the LLM with a step-by-step plan that references the appropriate tools, so the LLM knows what to call and in what order.

Think of prompts as domain expertise encoded into reusable scripts. They capture the knowledge of “what to do first” and “what to check when something goes wrong” so that the LLM does not have to figure it out from scratch each time.

Available prompts

Prompt	Parameters	Purpose
bench-init	backend	Connect, discover, and summarize all instruments on a backend
troubleshoot-bus	backend, instrument	Systematic diagnosis of a non-responsive instrument
quick-measure	instrument, measurement_type	Configure and capture a specific type of measurement
multi-instrument	backend	Coordinated measurements across multiple instruments
pymeasure-guided	instrument	Validated measurement preferring pymeasure drivers

bench-init

Use this when setting up a test bench for the first time or after power cycling instruments.

> Use the bench-init prompt for bench-a

The prompt instructs the LLM to:

1. Call connect_backend("bench-a") to open the connection
2. Call discover_instruments("bench-a") to find all instruments and identify them
3. Summarize the bench: firmware version, number of instruments, their resource strings, aliases, and identities
4. Flag any instruments that were discovered but failed *IDN?

If the connection fails, the prompt includes troubleshooting guidance for both serial and TCP transports. If no instruments are found, it suggests checking cables, power, and trying interface_clear.

This prompt is a good starting point for any session. It gets the entire bench into a known state before you start working.

troubleshoot-bus

Use this when a specific instrument is not responding, returning errors, or behaving unexpectedly.

> Use the troubleshoot-bus prompt for the ammeter on bench-a

The prompt walks through six escalating steps:

1. Bus connectivity — Discover instruments to check if the instrument is present
2. Identity — Send *IDN? to verify the instrument can communicate
3. Status byte — Serial poll to check for SRQ, MAV, or error bits
4. Error clearing — Send *CLS, then read SYST:ERR? until the queue is empty
5. Reset — Send *RST and re-identify
6. Bus recovery — Assert interface_clear and instrument_clear as last resort

The LLM exits the sequence at the first step that resolves the problem. For a simple error queue overflow, it stops at step 4. For a completely hung bus, it goes through all six.

Tip

This prompt encodes the status byte bit definitions (bit 6 = RQS, bit 5 = ESB, bit 4 = MAV), so the LLM can interpret serial poll results without you having to explain the IEEE 488.2 status model.

quick-measure

Use this when you want to take a specific type of measurement and need the LLM to handle instrument configuration, triggering, and validation.

> Use the quick-measure prompt for dc_voltage on the DMM

The prompt guides the LLM through:

1. Identify the instrument — Call *IDN? to determine the model and adapt commands accordingly
2. Configure — Send the appropriate CONF:* command for the measurement type (DC voltage, AC voltage, frequency, resistance, current)
3. Trigger and read — Choose between READ? for simple measurements or INIT / FETCH? for triggered acquisition
4. Validate — Check *STB? to verify the reading completed without error

Supported measurement_type values include dc_voltage, ac_voltage, frequency, resistance, 4wire_resistance, dc_current, and ac_current. The prompt provides the corresponding SCPI subsystem commands for each.

Note

The prompt reminds the LLM that SCPI commands vary by manufacturer. After identifying the instrument model, the LLM may adapt commands beyond what the prompt template provides. For example, some instruments use SENS:FUNC instead of CONF: for configuration.

multi-instrument

Use this for coordinated measurements across multiple instruments on the same backend, or for a periodic infrastructure audit.

> Use the multi-instrument prompt for bench-a

The prompt operates across all instruments on the specified backend:

1. Status check — Call server_status to show connected backends and instruments
2. For each connected backend — Discover instruments, check SRQ, serial poll all instruments
3. Coordinated reads — Take measurements from multiple instruments in sequence or with bus triggers
4. Generate a report — Total backends, total instruments, any SRQ assertions, any error statuses, and recommendations

This is useful at the start of a workday to verify that everything is online, or after a power event to assess what survived.

pymeasure-guided

Use this when you want the best available measurement approach — validated pymeasure control if a driver exists, raw SCPI if not.

> Use the pymeasure-guided prompt for the DMM

The prompt first calls instrument_inspect to check for a pymeasure driver. If one exists (8 instruments are supported), it guides the LLM through:

1. Inspect — Discover validated properties and methods
2. Check state — Read key control properties to understand current configuration
3. Configure — Set properties with validation, or call high-level methods
4. Measure — Read measurement properties (pymeasure handles SCPI and parsing)
5. Cleanup — Disable outputs, return to local control

If no driver exists, the prompt falls back to raw SCPI (instrument_query / instrument_write).

Tip

This prompt is the recommended starting point when you are not sure whether an instrument has pymeasure support. It handles the decision automatically — you do not need to check instrument_inspect yourself.

How prompts work in MCP

MCP prompts are part of the Model Context Protocol specification. When an MCP client (like Claude Code) supports prompts, it can:

• List available prompts with list_prompts
• Retrieve a prompt’s content with get_prompt, passing the required parameters
• Inject the resulting text into the conversation as context for the LLM

The LLM then follows the instructions in the prompt text, calling the appropriate mcpyvisa tools to carry out each step. The prompt itself does not execute anything — it provides a plan that the LLM executes.

Not all MCP clients support prompts yet. If yours does not, you can achieve the same result by describing the workflow to the LLM directly. The prompt text is documented in the mcpyvisa source code in prompts.py if you want to use it as a reference for manual instructions.