ltspice-mcp

Work in progress. Core functionality is usable but expect rough edges and breaking changes.

An MCP server that connects LLM assistants (Claude, and any other MCP client) to real circuit simulation: LTspice and ngspice, plus direct editing of LTspice .asc schematics. Simulation results come back as structured numbers — cutoff frequencies, overshoot, phase margin, rise times — so the assistant can design, verify, and iterate on circuits in the same files you open in LTspice. Built on spicelib.

Quick start

1. Install the server:

uv tool install ltspice-mcp     # or: pip install ltspice-mcp / pipx install ltspice-mcp

2. Add it to your MCP client:

# Claude Code
claude mcp add -s project ltspice -- ltspice-mcp

// Claude Desktop (claude_desktop_config.json) and most other clients
{
  "mcpServers": {
    "ltspice": { "command": "ltspice-mcp", "args": [] }
  }
}

3. Have LTspice or ngspice installed. Both are auto-detected on Windows, Linux, and macOS; on WSL the LTspice path must be set explicitly (WSL notes). Circuit editing works with no simulator at all.

That's the setup. Python 3.13+ required. Verify with ltspice-mcp --help.

Claude Desktop config lives at ~/Library/Application Support/Claude/ (macOS), %APPDATA%\Claude\ (Windows), or ~/.config/Claude/ (Linux). Cursor, Windsurf, Gemini CLI, Continue, Cline, Zed and others take the same JSON snippet in their respective config files. Web clients (claude.ai, ChatGPT) need a stdio→HTTP bridge such as mcp-proxy — only expose this server on a network you fully control, since it writes files and spawns processes inside allowed_paths.

Related MCP server: Universal Netlist MCP Server

Using it

Once connected, you ask for circuit work in plain language. The assistant chooses the tools; the server runs the simulator and measures the results.

"Design a 1 kHz RC low-pass filter and verify its cutoff."

The assistant writes the netlist, validates it, runs an AC simulation, and reads the measurements back: cutoff 1000.4 Hz, −19.9 dB/decade roll-off, first-order response. If the cutoff is off-target, it changes a component value and re-runs — each iteration is a couple of seconds.

Other requests that work the same way:

• "What's the overshoot and settling time of this regulator's step response?" — runs a transient analysis and measures both from the waveform, plus rise time, ringing frequency, and the final value.

• "Run a 200-run Monte Carlo with 5% resistors and tell me the output spread." — perturbs components per run, simulates the batch, and reports mean, sigma, and worst-case values per measurement.

• "Sweep the load from 100 Ω to 10 kΩ and find where efficiency drops." — parameter sweep with per-run results.

• "Turn this netlist into a schematic I can open in LTspice." — generates a wired .asc file that produces the same circuit.

• "Is this loop stable?" — AC analysis of the loop gain; reports phase and gain margin at every crossover, not just the first.

Co-design on the same files

Everything operates on ordinary LTspice and SPICE files, so the work passes back and forth between you and the assistant instead of living inside a chat:

• Sketch a schematic in LTspice, then hand it over: "what's the bias point?", "why doesn't the output move?", "add compensation and check the phase margin."

• Or the reverse: the assistant designs and verifies the circuit and writes the .asc; you open it in LTspice, inspect it, and tweak by hand. Your manual edits are simply the file's new state — the assistant picks up from there on the next request.

• Changes can flow either direction mid-design: adjust a value in the GUI and ask for re-verification, or have the assistant sweep a change you're considering before you commit to it.

What it does

Simulation and measurement. Runs LTspice or ngspice and parses the binary output directly. Measurements are computed server-side and returned as numbers: time-domain (rise/fall, overshoot, settling, delay, period/duty/jitter, RMS), frequency-domain (filter cutoffs and roll-off, gain and phase at any frequency, stability margins, resonance peaks with Q), DC operating points, and .MEAS directive results including the ones that failed.

Schematic and netlist editing. Creates and edits real LTspice .asc files — place components, wire pins, label nets — with validation before anything is written: wiring that would collide with a pin, overlap a junction, or run diagonally is refused, and every edit returns warnings about floating pins or dangling labels. A netlist converts to a working schematic in one step; a session's edits can be reverted. Plain netlists (.cir/.net) get the same operations at text level, plus a static validation pass that catches malformed cards before a simulation is spent.

Sweeps and Monte Carlo. Multi-dimensional parameter sweeps and Monte Carlo with per-component tolerances, .MODEL process variation, and Pelgrom W·L device mismatch. Per-measurement statistics are aggregated across runs, and any single run can be pulled out and analyzed like a standalone simulation.

Jobs and trust. Simulations run as cancellable jobs with timeouts and a concurrency cap; long runs return a job ID immediately and job state survives a server restart. Results report facts, not verdicts: a completed run carries the simulator's own warnings, measurements that produced nothing, and extreme node values as structured observations. Judging whether a result is trustworthy is left to the model reading it.

Supported simulators

Configuration

Works with defaults out of the box. To customize, copy ltspice-mcp.example.toml to ltspice-mcp.toml; any setting can be overridden with an LTSPICE_MCP_-prefixed environment variable, and --config PATH or LTSPICE_MCP_CONFIG picks the file. Key options:

[simulator]
default = "ltspice"      # ltspice, ngspice, qspice, xyce (null = auto-detect)
path = ""                # explicit executable path (required on WSL)

[security]
allowed_paths = ["."]    # sandbox: only these directories are accessible

[simulation]
max_parallel = 4
timeout = 300.0          # seconds

[tools]
profile = "full"         # or "agentic"

[state]
persist_jobs = true

See src/ltspice_mcp/config.py for the full option list ([analysis], [schematic], [logging], ...).

On WSL, LTspice.exe runs via Windows interop (not Wine), and spicelib can't auto-detect it across the WSL boundary. Set the Windows-side path explicitly:

[simulator]
path = "/mnt/c/Program Files/ADI/LTspice/LTspice.exe"

Simulation output is automatically redirected to a Windows temp directory: LTspice's .MEAS results go through SQLite .db files that fail on UNC paths (\\wsl.localhost\...), and without the redirect measurement data silently disappears from the logs.

.asy symbol paths for .asc editing are auto-detected on Windows and WSL; override with [schematic] symbol_paths or LTSPICE_MCP_SYMBOL_PATHS.

Tool profiles

The agentic profile drops netlist-editing wrappers and library session management — work a capable agent does through direct file edits — and keeps simulation lifecycle, binary .raw parsing, batch orchestration, and the .asc geometry tools. The skills/ directory (skills/ltspice/SKILL.md, skills/ngspice/SKILL.md) contains the domain knowledge that pairs with it: copy the relevant skill into your client's persistent-instructions location.

Under the hood: the tool-level loop

What the assistant actually does for "design a 1 kHz RC low-pass and verify it". It writes the netlist (R=1k, C=159.155n → fc = 1 kHz):

* rc.cir — RC low-pass
V1 in 0 AC 1
R1 in out 1k
C1 out 0 159.155n
.ac dec 50 1 1Meg
.end

then drives three tools:

validate_netlist(path="rc.cir")
  → OK: directives valid, element arities check out — safe to simulate

run_simulation(netlist="rc.cir")
  → {"job_id": "sim_a3f1", "status": "completed", "raw_file": ".../rc.raw", ...}

bode_metrics(raw_file=".../rc.raw", signal="V(out)", mode="filter")

and gets back scalars, not a plot:

{
  "signal": "V(out)",
  "filter_type": "lowpass",
  "passband_gain_db": 0.0,
  "passband_ripple_db": 0.02,
  "cutoff_low_hz": null,
  "cutoff_high_hz": 1000.4,
  "stopband_rejection_db": 59.97,
  "rolloff_slope_db_per_decade": -19.9,
  "estimated_order": 1,
  "warnings": []
}

(abridged — the full response also includes passband bounds and transition bandwidth)

Off-target → set_component_value, re-run, re-measure. Long simulations return a job ID instead of blocking; check_job/cancel_job manage them. Job metadata persists in per-circuit sidecars ({dir}/.ltspice-mcp/jobs/ — add .ltspice-mcp/ to your .gitignore), and MCP resources (ltspice://results/..., ltspice://netlists/..., ltspice://config) expose jobs, signals, measurements, and config for browsing.

Every tool declares MCP annotations (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); data-returning tools declare an outputSchema for structuredContent introspection.

Development

uv sync                        # install runtime + dev dependencies
uv run pytest tests/ -v        # tests
uv run pyright                 # type checking
uv run ruff check src/ tests/  # lint
uv run ltspice-mcp             # run the server (stdio)

More: docs/DESIGN.md (scope, architecture, non-goals) and docs/spice_lex.md (SPICE parser internals).

License

GPL-3.0