// SCAN REPORT

Ltspice

71 tools. 31 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated: 12 Jun 2026

31 can modify or destroy data

40 read-only

71 tools total

Community server · catalogue entry verified 12/06/2026

How to control Ltspice ↓

TOOL MAP

What Ltspice exposes to your agents

Read (40) Write / Execute (29) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Ltspice tools

Destructive · Medium resetToolTelemetry Resetting telemetry irreversibly destroys accumulated performance data. Destructive · Medium endLtspiceRenderSession Closing a window/session is an irreversible termination action — any unsaved simulation state or render session data associated with that window would be lost. Execute · Medium cancelJob Cancelling a job triggers an operational side effect (stopping a running or queued simulation/task). Execute · Medium daemonDoctor The tool actively 'runs' a health check against daemon/system processes, which constitutes executing an operation against the system.

31 of Ltspice's 71 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Ltspice

PolicyLayer is an MCP gateway — it sits between your AI agents and Ltspice, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "resetToolTelemetry": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "autoCleanSchematicLayout": {
    "limits": [
      {
        "counter": "autocleanschematiclayout_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "lintSchematic": {
    "limits": [
      {
        "counter": "lintschematic_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Ltspice — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON LTSPICE →

Free to start. No card required.

FULL CATALOGUE

All 71 Ltspice tools

DESTRUCTIVE 2 tools

Destructive resetToolTelemetry Reset rolling performance telemetry for one tool or all tools. Destructive endLtspiceRenderSession Close the LTspice window associated with a render session.

EXECUTE 16 tools

Execute cancelJob Request cancellation for a queued/running job. Execute daemonDoctor Run a daemon/system health check and return actionable recommendations. Execute runMeasAutomation Inject .meas directives into a netlist, run simulation, and parse measurement values. Execute runSimulation Run LTspice in batch mode for the currently loaded netlist. Execute runSweepStudy runSweepStudy Execute runVerificationPlan runVerificationPlan Execute simulateNetlist Write a netlist and run LTspice batch simulation in one call. Execute simulateNetlistFile Run LTspice batch simulation for an existing netlist path. Execute simulateSchematicFile Run LTspice batch simulation for an existing schematic (.asc) file. Execute startLtspiceRenderSession Open an LTspice window once for repeated image rendering. Execute autoDebugSchematic Iteratively validate, simulate, and apply targeted fixes to a schematic until it runs or stalls. Execute queueSimulationJob Queue a simulation job and return a job id for status polling/cancelation. Execute watchSchematicFromNetlistFile Poll a netlist file and regenerate schematic whenever the netlist changes. Execute closeLtspiceWindow Close LTspice windows whose title contains title_hint. Execute generateVerifyAndCleanCircuit One-shot orchestration: create intent circuit, lint, simulate, verify, clean, and inspect. Execute openLtspiceUi Open LTspice UI on a selected artifact.

WRITE 13 tools

Write autoCleanSchematicLayout Auto-clean schematic layout and return before/after quality analysis. Write loadCircuit Create a netlist file in the MCP workdir and mark it as the currently loaded circuit. Write syncSchematicFromNetlistFile Regenerate schematic from a netlist file only when source content changed. Write createIntentCircuit Create a circuit from high-level intent templates (filters, amplifier, regulator). Write createSchematic Create an LTspice .asc schematic from structured component/wire/directive data. Write createSchematicFromNetlist Create an LTspice .asc schematic from a SPICE netlist using auto-placement/routing. Write createSchematicFromTemplate Create an LTspice .asc schematic from a JSON template. Write generatePlotPresetSettings Generate deterministic .plt settings for a named preset. Write generatePlotSettings Generate a LTspice .plt file from vectors and return parsed settings for debugging. Write importModelFile Import a model file into the MCP workdir for reproducible .include usage. Write patchNetlistModelBindings Patch netlist model bindings by adding includes and remapping model/subckt names. Write setLtspiceUiEnabled Set default UI behavior for simulation calls where show_ui is omitted. Write setSchematicUiSingleWindow Set whether schematic UI opens reuse a single live schematic path.

READ 40 tools

Read lintSchematic Run structural lint checks on a schematic, including pin connectivity and dangling wires. Read parseMeasResults Parse LTspice .meas results from a run log or explicit log path. Read getBandwidth Compute -drop_db bandwidth for an AC response vector. Read getCaptureHealth Summarize ScreenCapture/LTspice capture health from in-process capture events. Read getGainPhaseMargin Compute gain and phase margins from an AC loop-gain vector. Read getLocalExtrema Get local minima/maxima for vectors. Read getLtspiceLibraryStatus Get LTspice symbol library ZIP status and basic counts. Read getLtspiceStatus Get LTspice executable status and server configuration. Read getLtspiceSymbolInfo Get pin map and metadata for a symbol in LTspice's lib.zip. Read getLtspiceUiStatus Return whether LTspice UI appears to be running on this machine. Read getPlotNames List LTspice plot names available in one RAW file or all RAW files from a run. Read getRecentErrors Scan recent daemon logs and return structured error entries. Read getRiseFallTime Compute first rise/fall times for a transient response. Read getRunDetails Get full details for a run_id, or the latest run if omitted. Read getSettlingTime Compute settling time to a target within tolerance_percent band. Read getToolTelemetry Return rolling performance telemetry for MCP tools. Read getVectorData Get data for vectors, optionally interpolated at explicit scale points. Read getVectorsInfo Get detailed information about vectors in a plot. Read inspectSchematicVisualQuality Inspect schematic visual quality and suggest coordinate-level fixes. Read jobStatus Get status for one queued/running/completed simulation job. Read listIntentCircuitTemplates List high-level circuit intent templates and default parameters. Read listJobHistory List archived (terminal) queue jobs retained across daemon restarts. Read listJobs List queued/running/completed simulation jobs. Read listLtspiceLibraryEntries List LTspice symbol ZIP entries (.asy), optionally filtered by query. Read listLtspiceSymbols List/search LTspice symbols parsed from the symbol library ZIP. Read listPlotPresets List built-in deterministic LTspice plot presets. Read listRuns List recent simulation runs (newest first). Read listSchematicTemplates List available schematic templates from the built-in or user-provided JSON file. Read loadNetlistFromFile Load an existing netlist file (.cir/.net/.sp/.spi/.sub/.lib/.txt) as the current circuit. Read readAgentGuide Read AGENT_README.md through MCP for interactive agent guidance. Read readLtspiceUiText Read visible LTspice window text using macOS Accessibility APIs. Read renderLtspicePlotImage Render one or more vectors from a RAW dataset to a plot image and return it through MCP. Read renderLtspicePlotPresetImage Render a plot image using a built-in deterministic preset. Read renderLtspiceSchematicImage Render an LTspice schematic (.asc) to an image and return it through MCP. Read renderLtspiceSymbolImage Render an LTspice symbol to an image and return the image through MCP. Read scanModelIssues Scan LTspice log text for missing model/include/subcircuit issues. Read tailDaemonLog Return tail text from the active daemon log file. Read validateLtspiceMeasurements Validate parsed metric endpoints against LTspice-native .meas values. Read validateSchematic Validate a schematic (.asc) for simulation readiness. Read resolveSchematicSimulationTarget Resolve which file simulateSchematicFile will execute and explain sidecar requirements.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Ltspice

Can an AI agent delete data through the Ltspice MCP server? +

Yes. The Ltspice server exposes 2 destructive tools including resetToolTelemetry, endLtspiceRenderSession. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Ltspice? +

The Ltspice server has 13 write tools including autoCleanSchematicLayout, loadCircuit, syncSchematicFromNetlistFile. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Ltspice.

How many tools does the Ltspice MCP server expose? +

71 tools across 4 categories: Destructive, Execute, Read, Write. 40 are read-only. 31 can modify, create, or delete data.

How do I enforce a policy on Ltspice? +

Register the Ltspice MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Ltspice tool call.

Deterministic rules across all 71 Ltspice tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON LTSPICE →

Free to start. No card required.

71 Ltspice tools catalogued and risk-classified — across an index of 43,000+ MCP servers.