spicebridge

spicebridge is an MCP server (and CLI) that lets an AI generate SPICE netlists and run ngspice simulations from natural-language/templated circuit descriptions. It supports AC/transient/DC analyses, measurement extraction, spec comparison, Monte Carlo/worst-case tolerance analysis, exporting (KiCad, schematic viewer), and optional cloud deployment via Cloudflare Tunnels.

Evaluated Mar 30, 2026 (21d ago)
Repo ↗ Ai Ml mcp-server ngspice spice eda ai-circuit-design automation circuit-simulation analog-electronics
⚙ Agent Friendliness
50
/ 100
Can an agent use this?
🔒 Security
47
/ 100
Is it safe for agents?
⚡ Reliability
29
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
70
Documentation
70
Error Messages
0
Auth Simplicity
55
Rate Limits
0

🔒 Security

TLS Enforcement
65
Auth Strength
55
Scope Granularity
20
Dep. Hygiene
55
Secret Handling
40

Security posture is partially evidenced: cloud setup implies an API key and Cloudflare OAuth-based tunnel setup. However, the README does not describe transport/auth details (e.g., TLS-only enforcement, API key handling, rotation), authorization boundaries, or fine-grained permissions. Running ngspice and accepting natural-language inputs also increases the importance of robust input validation and sandboxing, which is not documented here.

⚡ Reliability

Uptime/SLA
0
Version Stability
45
Breaking Changes
40
Error Recovery
30
AF Security Reliability

Best When

You want an agent-driven workflow for iterative analog design and verification using ngspice, ideally with local execution or a controlled deployment.

Avoid When

You require a well-defined, standards-based public REST API/SDK with strong authz controls and explicit rate-limit policies, or you cannot install/run ngspice on the host.

Use Cases

  • AI-assisted analog circuit design loops (template → simulate → verify)
  • Automated spec checking (e.g., bandwidth/gain/DC levels, PASS/FAIL)
  • Tolerance analysis for robustness (Monte Carlo and worst-case)
  • Rapid netlist generation and validation for SPICE circuits
  • Exporting simulation-driven designs to KiCad and a web viewer

Not For

  • Safety-critical hardware certification workflows without human validation
  • Production-grade, multi-tenant hosted services without additional hardening
  • Environments where exposing circuit design requests to a cloud tunnel is unacceptable

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: Cloudflare OAuth during setup-cloud (wizard step) API key (generated by setup-cloud for authentication to the MCP endpoint)
OAuth: Yes Scopes: No

README indicates an API key is generated for authentication in the cloud setup wizard, but does not describe fine-grained scopes or token lifetime/rotation.

Pricing

Free tier: No
Requires CC: No

No pricing information provided; appears to be self-hosted via Python package and local ngspice.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Simulation failures may occur due to invalid netlists/model issues; retry strategy is not documented.
  • Stateful circuit IDs: agents must track circuit_id across calls and avoid mixing IDs between conversations.
  • ngspice must be available on PATH; cloud deployments require additional environment/config.
  • Monte Carlo/worst-case runs may be computationally expensive; no controls or limits are documented.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for spicebridge.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered