mcp-vcd
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-vcd show me the value changes for signal clk from 100 to 200 ns"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-vcd
A Model Context Protocol (MCP) server for analyzing VCD waveforms and GTKWave save files (.gtkw).
Give your AI assistant direct access to hardware simulation results — signal values, bus definitions, display formats, and signal groupings — without dumping entire files into the context window.
Tools
Tool | Description |
| Get all value changes of a signal from a VCD file. Supports optional |
| Parse a |
| Return the group hierarchy defined in a |
| Return the component signals of a named bus from a |
| Get signal values from a VCD, formatted according to |
Related MCP server: EDA Tools MCP Server
Installation
uv pip install mcp-vcdClaude Desktop
Add to your claude_desktop_config.json:
"mcpServers": {
"mcp-vcd": {
"command": "uv",
"args": [
"run",
"mcp-vcd"
]
}
}See Anthropic's MCP documentation for more info.
License
MIT
Available Tools
5 toolsget-bus-signalsA
Return the component signals of a bus defined in a .gtkw file
Inputs: bus_name (required), file_name (required).
get-signalB
Get all value changes of a signal in a VCD file
Inputs: file_name (required), signal_name (required), end_time, start_time.
get-signal-groupsB
Return the group hierarchy from a parsed .gtkw file
Inputs: file_name (required).
get-signal-with-formatC
Get signal values from a VCD file, formatted according to .gtkw display hints
Inputs: vcd_file (required), gtkw_file (required), signal_name (required), end_time, +1 more.
load-gtkwB
Parse a .gtkw file and return its full structure (metadata, signals, buses, groups)
Inputs: file_name (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Tools are generally distinct, but get-signal and get-signal-with-format overlap in purpose (both retrieve signal values from VCD), though the formatting difference is clearly described. Other tools target distinct aspects of GTKW structure.
All tool names follow a consistent lowercase hyphenated verb_noun pattern (get-*, load-*), making the naming predictable and easy to understand. The use of 'load' for gtwk parsing and 'get' for data retrieval is a consistent semantic distinction.
With 5 tools, the server is well-scoped for its purpose of reading and inspecting VCD/GTKW files. Each tool covers a necessary aspect without redundancy or bloat.
The toolset covers the core workflows: parsing GTKW structure, querying groups/buses, and retrieving signal values. A minor gap is the lack of a direct way to enumerate all signals from a VCD file without a GTKW file, but this matches the typical workflow where GTKW provides the signal hierarchy.
Maintenance
Related MCP Connectors
Turn datasheets into source-backed JSON contracts, pinout matrices, and KiCad CAD for AI agents.
Design circuits, simulate and verify embedded firmware, and lay out PCBs with AI agents.
Connect AI assistants to your GitHub-hosted Obsidian vault to seamlessly access, search, and analy…
Run, build, and validate firmware on virtual hardware from your AI agent. Hardware knowledge corpus.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables analysis of RTL waveform files (VCD, FST) through WAL (Waveform Analysis Language). Supports signal inspection, transition extraction, and advanced waveform queries for hardware design verification.16BSD 3-Clause
- AlicenseAqualityDmaintenanceEnables AI assistants to perform Electronic Design Automation (EDA) tasks including Verilog synthesis, simulation, ASIC design flows, and waveform analysis through a unified interface.6ISC
- FlicenseNot gradedqualityCmaintenanceAn MCP server that provides AI assistants with a persistent, sandboxed Python environment for waveform analysis, enabling loading and manipulation of VCD/FST/FSDB files and temporal pattern matching.9-
- AlicenseAqualityBmaintenanceLocal MCP server for querying VCD waveform files via SQLite; enables AI agents to ask precise questions about signal values, transitions, and clock cycles without dumping raw VCD text.182MIT