Index / MCP servers / MagicON RF Design Engines

MagicON RF Design Engines MCP server

MagicON RF Design Engines is a remote MCP server that gives an AI agent 18 tools, among them check_grounding, compare_rf_chains, design_patch_antenna. It answers at https://api.pcbgenerator.com/mcp/ over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 1 October 2026; the last check, on 16 November 2026, succeeded.

Status
Answering
Tools
18
Reliability
4 of 4 checks
Response time
210 ms
Transport
streamable HTTP
Last checked
16 November 2026

TX/RX/T-R chains, OTA link, radar, PCB filters, patch antennas, stackup, thermal, PDN, compliance.

Description as the publisher wrote it.

The 18 tools MagicON RF Design Engines offers

ToolWhat it does
check_groundingCheck a draft passage against the engine results computed in THIS session. It returns every figure no engine produced, and every claim it checks that the results do not support or contradict (for example a solver score called a loss), each
Inputs: text
compare_rf_chainsMulti-objective RF chain comparison: designs the primary chain with the convergent orchestrator, generates alternative chains by swapping components, scores every variant on cost / size / performance / DC power, and returns the ranked list
Inputs: frequency, target_output_power, application, weights, max_chains, user_request
design_patch_antennaDesign a rectangular microstrip patch antenna (and, when both nx and ny are given, a uniform planar array of it) using the Balanis cavity/transmission-line + array-factor model — the SAME engine behind POST /api/antenna/patch/design and the
Inputs: frequency_ghz, dk, df, h_mm, material, nx
design_rf_chainDesign a complete RF transmitter chain with the convergent orchestrator: selects the driver, PA, filter, and connector (the signal source is the user's input power by default — no VCO unless one is explicitly the generator), matches drive p
Inputs: frequency, target_output_power, input_power_dbm, application, bandwidth, internally_matched_only
design_rf_receiverDesign or analyse a superheterodyne RECEIVER. Selects catalog parts for each slot (limiter, LNA, image filter, mixer, LO, IF filter, IF amp, step attenuator) and returns the frequency plan (image, half-IF, LO leakage), the cascaded noise fi
Inputs: rfFrequencyHz, bandwidthHz, requiredSnrDb, ifHz, loSide, application
design_tr_moduleDesign a T/R (transmit/receive) module that shares ONE antenna between a transmitter and a receiver. Designs both chains through the existing engines, selects the shared front end (a T/R switch, or a circulator with a receive-path limiter),
Inputs: frequencyGhz, targetOutputPowerDbm, topology, application, main_board_input_voltage, prfHz
find_components_by_specFind real parts in the validated catalog that meet a spec: a part type, an operating frequency in GHz, and optional limits (noise figure, gain, P1dB, Psat, OIP3, insertion loss, temperature grade or range). Returns the matching parts, best
Inputs: category, frequency_ghz, max_noise_figure_db, min_gain_db, min_p1db_dbm, min_psat_dbm
lookup_component_by_mpnLook up an RF component in the validated catalog by manufacturer part number: the catalog's summary of its headline figures, not the full datasheet. Returns the frequency, power and gain ranges, package, datasheet link, and the headline fig
Inputs: part_number, user_request
run_compliance_analysisAudit the solved stackup against PCB standards (IPC-2221, IPC-6012, IPC-4101, MIL, UL-94, RoHS, REACH): per-rule pass/fail with severities and remediation. Layers are derived from the solved stackup and standards default to IPC-2221 + IPC-6
Inputs: standards, layers, stackup_config, rf, user_request
run_glass_weave_analysisRecommend PCB glass-weave (fiber-weave) styles for the current design: ranks catalogued styles by impedance variation and cost for the design frequency and marks the cheapest one meeting the impedance tolerance. Reuses the Phase-24 engine b
Inputs: frequency_ghz, impedance_tolerance_pct, trace_width_mm, is_differential_pair, user_request
run_link_budgetCompute a cascaded RF link budget. For the chain just designed, call with NO arguments — the server derives stages and input power from the design (after a receiver it returns that receiver's own cascade; a T/R module keeps no stage list, s
Inputs: inputPowerDbm, claims, bandwidthHz, requiredSnrDb, stages, user_request
run_ota_linkCompute a one-way over-the-air link budget — EIRP, free-space path loss (Friis), received power, link margin against receiver sensitivity, a closes/marginal/fails verdict, and the maximum range — using the SAME engine behind POST /api/ota-l
Inputs: txPowerDbm, txPowerW, txGainDbi, rxGainDbi, frequencyGhz, distanceM
run_pdn_analysisRun a PDN (power delivery network) impedance analysis: interplanar plane-pair capacitance, multi-cap decoupling impedance vs. target impedance, violations, and recommended decoupling caps. Inputs are derived server-side from the solved stac
Inputs: plane_pairs, decoupling_caps, target, user_request
run_planar_filterSynthesize a passive planar (copper-on-PCB) filter from analytical formulas: stepped-impedance / open-stub low-pass, or parallel-coupled / hairpin band-pass, Chebyshev or Butterworth. Returns per-section line impedances (Z0e/Z0o for coupled
Inputs: filter_class, topology, response, order, ripple_db, fc_ghz
run_radar_performanceCompute radar performance — the monostatic range equation (received power, SNR vs range, maximum detection range, coherent/non-coherent integration gain) and pulsed-waveform relations (duty cycle, unambiguous range/velocity, range resolutio
Inputs: peakPowerW, peakPowerDbm, gainTxDbi, gainRxDbi, frequencyGhz, rcsM2
run_sparam_cascadeCascade a chain's parts from the makers' own .s2p files: S21/S11/S22/S12 at the design frequency, 2x and 3x, plus a sweep (match between parts, harmonic rejection). Small-signal only. A part with no file is named in leftOut and left out, ne
Inputs: partNumbers, frequencyGhz, user_request
run_stackup_solverRun the impedance-aware stackup constraint solver to find optimal PCB configurations. Use when the user wants ranked material/thickness/copper solutions for a given layer count and frequency. Returns scored and ranked feasible stackups. Eac
Inputs: layer_count, frequency_ghz, impedance_ohms, fixed_dielectric, topology, impedance_targets
run_thermal_analysisPCB thermal analysis: via array Rth, junction-to-ambient stack, Kennedy spreading, Coffin-Manson barrel stress, Timoshenko warpage, and resin-flow estimation. Call with no arguments once a design exists: the server takes power_w from the de
Inputs: analysis_input, via_config, stackup_layers, theta_jc_c_per_w, case_temp_c, heatsink

Add MagicON RF Design Engines to your AI client

Every block below points at https://api.pcbgenerator.com/mcp/. Pick your client and copy.

Claude Code: one command in your terminal
claude mcp add --transport http magicon-rf-design-engines https://api.pcbgenerator.com/mcp/
Claude Desktop: claude_desktop_config.json
{
  "mcpServers": {
    "magicon-rf-design-engines": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://api.pcbgenerator.com/mcp/"]
    }
  }
}
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json in a project
{
  "mcpServers": {
    "magicon-rf-design-engines": {
      "url": "https://api.pcbgenerator.com/mcp/"
    }
  }
}
VS Code and GitHub Copilot: .vscode/mcp.json
{
  "servers": {
    "magicon-rf-design-engines": {
      "type": "http",
      "url": "https://api.pcbgenerator.com/mcp/"
    }
  }
}
Zed: Zed settings.json
{
  "context_servers": {
    "magicon-rf-design-engines": {
      "url": "https://api.pcbgenerator.com/mcp/"
    }
  }
}
Windsurf: ~/.codeium/mcp_config.json
{
  "mcpServers": {
    "magicon-rf-design-engines": {
      "serverUrl": "https://api.pcbgenerator.com/mcp/"
    }
  }
}
JetBrains AI Assistant: Settings, Tools, AI Assistant, MCP, New MCP Server, as JSON
{
  "mcpServers": {
    "magicon-rf-design-engines": {
      "url": "https://api.pcbgenerator.com/mcp/"
    }
  }
}
Continue: .continue/mcpServers/neuronto.yaml
name: MagicON RF Design Engines
version: 0.0.1
schema: v1
mcpServers:
  - name: MagicON RF Design Engines
    type: streamable-http
    url: https://api.pcbgenerator.com/mcp/
Gemini CLI: ~/.gemini/settings.json
{
  "mcpServers": {
    "magicon-rf-design-engines": {
      "httpUrl": "https://api.pcbgenerator.com/mcp/"
    }
  }
}
Codex CLI: MCP server config
{
  "mcpServers": {
    "magicon-rf-design-engines": {
      "type": "http",
      "url": "https://api.pcbgenerator.com/mcp/"
    }
  }
}
Warp: MCP servers, + Add, paste JSON
{
  "mcpServers": {
    "magicon-rf-design-engines": {
      "url": "https://api.pcbgenerator.com/mcp/"
    }
  }
}
Goose: a one-click extension link
goose://extension?url=https%3A%2F%2Fapi.pcbgenerator.com%2Fmcp%2F&type=streamable_http&id=magicon-rf-design-engines&name=MagicON%20RF%20Design%20Engines

Is MagicON RF Design Engines up right now?

It answered our last check on 16 November 2026 in 210 ms. Over 4 checks since 1 October 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.

MCP servers similar to MagicON RF Design Engines

Questions about MagicON RF Design Engines

How many tools does MagicON RF Design Engines have?

18, as returned by the server's own tools/list on 19 November 2026: check_grounding, compare_rf_chains, design_patch_antenna, design_rf_chain, design_rf_receiver, design_tr_module, find_components_by_spec, lookup_component_by_mpn, and 10 more.

Is MagicON RF Design Engines down?

It answered our last check on 16 November 2026 in 210 ms. Over 4 checks since 1 October 2026 it answered 4.

How do I add MagicON RF Design Engines to Cursor?

Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://api.pcbgenerator.com/mcp/. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.

Does MagicON RF Design Engines need an API key?

It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.

Where this comes from

Publisher: io.github.magiccadai. Endpoint host: api.pcbgenerator.com. ARD identifier: urn:air:io.github.magiccadai:mcp:magicon. First indexed 1 October 2026. The tools are exactly what the server returned; nothing on this page is inferred from its name. Ranking in Neuronto search is never for sale.

Is this your server? Get a message the day it stops answering or its tools change: monitoring, 14 days free. Or claim the domain to manage how it is listed.