{"id":"clanker-lover-spicebridge","name":"spicebridge","af_score":49.5,"security_score":47.0,"reliability_score":28.8,"what_it_does":"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.","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.","last_evaluated":"2026-03-30T15:37:49.533251+00:00","has_mcp":true,"has_api":false,"auth_methods":["Cloudflare OAuth during setup-cloud (wizard step)","API key (generated by setup-cloud for authentication to the MCP endpoint)"],"has_free_tier":false,"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."],"error_quality":0.0}