Skip to main content
Glama
siliconsmith-mcp

siliconsmith-mcp

by RFingAdam

Related Servers

Alternatives to siliconsmith-mcp

No user-submitted related servers found.

    Related Servers

    • A
      license
      B
      quality
      B
      maintenance
      Enables AI agents to perform high-level HDL workflows including linting, simulation, synthesis, formal verification, FPGA bitstream builds, and waveform or netlist inspection over OSS CAD Suite tools.
      15
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables AI coding agents and IDEs to lint, compile, syntax-check, and simulate Verilog/SystemVerilog designs through structured, token-efficient MCP tools with isolated containerized toolchains.
      4
      21 npm
      Apache 2.0
    • A
      license
      Not graded
      quality
      B
      maintenance
      Gives coding agents structured access to an EDA toolchain so they can lint, simulate, formally verify, synthesize, place and route, program a board and read its UART. Returns parsed results (errors with file and line, timing per clock, utilization, inferred memories, counterexample traces) instead of raw logs, closing the run-simulate-fix loop without copy-paste.
      55 PyPI
      13
      AGPL 3.0
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables local AI coding assistants to operate remote Linux EDA clusters over persistent SSH/SCP for digital IC design, simulation, formal property verification, UVM testbench generation, static linting, and Git-backed workspace synchronization.
      1
      MIT
    • F
      license
      Not graded
      quality
      A
      maintenance
      Enables AI agents such as Claude Code, Cursor, and Codex to safely drive a locally installed Xilinx Vivado through 32 tools covering sessions, synthesis, implementation, timing, CDC, XDC, IP, waveforms, and device programming. Includes structured timing evidence with baseline comparison, offline VCD queries, evidence-driven workflow prompts, and one-command environment self-checks.
      -
    • A
      license
      A
      quality
      B
      maintenance
      Enables AI coding agents and IDEs to execute ASIC physical design flows including floorplanning, placement, clock tree synthesis, routing, and static timing analysis through the OpenROAD engine, returning concise low-token JSON metrics.
      6
      15 npm
      Apache 2.0

    TDQS

    A4.2/5.0

    Scored across 13 tools

    Disambiguation4/5

    Most tools target a clearly distinct stage of the chip design loop (spec, RTL, emit, sim, synth, waves, status) and the write_* family is separated by file kind. The main soft spots are emit_verilog vs. synthesize (both run the same lint/check pass) and run_tests(gl=True) vs. synthesize (the gate-level path re-runs synthesis), though the descriptions explicitly clarify the boundaries.

    Naming Consistency4/5

    The dominant pattern is verb_noun (create_project, list_files, read_file, write_rtl, write_test, write_spec, emit_verilog, run_tests, inspect_waves), which is predictable. The deviations are bare single words (synthesize, status, explain, toolchain_info) — still unambiguous but not a uniform pattern.

    Tool Count5/5

    13 tools is comfortably in the well-scoped range, and each maps to a real step (scaffold, edit, verify, synthesize, simulate, inspect, report). No obvious filler or redundant duplicates.

    Completeness4/5

    The full design loop is covered: project creation, file read/write, spec validation, Verilog emission and lint, RTL and gate-level simulation, synthesis sizing, wave inspection, and a status/coverage ledger. Minor gaps exist — no delete/rename/move file operation, no build-artifact listing without a flag, and spec approval and layout/PnR are intentionally outside the tool surface.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues