DEDUPEDWhat do you want to do?
4 use cases
-
Find the first divergence between pass and fail waveforms
Compare a passing and a failing run, then trace the first differing signal back to its drivers.
View prompt
Using the wave-mcp MCP server, call diff_waveforms on <pass_wave> and <fail_wave>, then call signal_fanin on the first diverging signal it reports. Return the first divergence time, the top diverging signals and their fan-in sources. Verify that the reported time matches a value change of that signal in <fail_wave>.
-
Trace an X value back to its root cause
Follow an unknown (X) value on a signal backward through its drivers to where it starts.
View prompt
Using the wave-mcp MCP server, run signal_values on <signal_path> to confirm an X value, then call trace_x on that signal at <time>. Return the driver chain from the output back to the earliest node that is X, with each node's value and source location. Verify that the earliest X node has a value of X in the FST at its reported time.
-
Review signal drivers and gating conditions before simulating
Read an RTL design's drivers, fan-in and hierarchy from source alone, with no waveform yet.
View prompt
Using the wave-mcp MCP server, call open_static_session with top <top_module> and filelist_path <filelist>, then call signal_drivers and signal_fanin on <signal_path>. Return every driver with its file, line and gating conditions, and list the signals that feed it. Verify that the line numbers match the source file.
-
Script waveform signal checks from the terminal
Run the same Wave MCP tools from shell scripts for CI or quick checks, without an agent.
- REPO
Tencent/wave-mcp - Software and DevOps
- Intermediate
View prompt
Using the wave-mcp CLI, run `wave-mcp query signal_values --session <session_dir> --paths <signal_path> --json` and parse the JSON output. Report whether the signal ever holds the expected value <expected> in the window you specify. Verify the exit code and that the JSON contains the queried path.
- REPO
Quick start with Wave MCP
- Check you have what it needs: Linux x86_64, where the Python dependencies ship as prebuilt wheels (other platforms need pylibfst built from source); Python 3.10 to 3.13; A simulation waveform (.fst or .vcd) and the same filelist used to run the simulation.
- Open Tencent/wave-mcp on GitHub and read the README and license.
pip install wave-mcpwave-session --fst sim/dump.fst --top top_tb --filelist rtl.f(run once for the passing waveform and once for the failing one, with different --fst paths and output directories)- Call the
diff_waveformstool with the pass and fail waveforms - Call the
signal_fanintool on the first diverging signal it reports
These steps come from our top use case, Find the first divergence between pass and fail waveforms, which also has a copy-paste agent prompt.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for Tencent/wave-mcp
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeWave MCP alternatives · Best AI repos for Software and DevOps
About this repo
- Who it is forHardware verification and RTL engineers who debug simulation failures, with or without an AI coding agent.
- Why it is hot249 stars
- LanguagePython
- Sourcegithub.com/Tencent/wave-mcp · Back to Hot repos
Requirements
- Linux x86_64, where the Python dependencies ship as prebuilt wheels (other platforms need pylibfst built from source)
- Python 3.10 to 3.13
- A simulation waveform (.fst or .vcd) and the same filelist used to run the simulation
- An MCP-capable agent such as Claude Code, Codex, Cursor or Gemini CLI, or a terminal for the CLI
Add this badge to your README
Maintain Wave MCP? Show readers where to find these use cases. 
Markdown
[](https://dedupedai.com/use-cases/tencent-wave-mcp/?utm_source=github&utm_medium=badge&utm_campaign=Tencent-wave-mcp)
HTML
<a href="https://dedupedai.com/use-cases/tencent-wave-mcp/?utm_source=github&utm_medium=badge&utm_campaign=Tencent-wave-mcp"><img src="https://dedupedai.com/badge/Tencent/wave-mcp.svg" alt="Use cases on Deduped" height="20"></a>
A static image, no tracking script. About the badge
Questions about Wave MCP
What is Wave MCP?
wave-mcp is an open-source, license-free MCP server and CLI that lets AI agents and engineers debug RTL simulation waveforms (FST, with VCD and FSDB converted automatically) against a SystemVerilog netlist. It is an open-source project on GitHub: https://github.com/Tencent/wave-mcp.
How do I use Wave MCP?
pip install wave-mcp; then wave-session --fst sim/dump.fst --top top_tb --filelist rtl.f (run once for the passing waveform and once for the failing one, with different --fst paths and output directories); call the diff_waveforms tool with the pass and fail waveforms. The use cases on this page give the full steps and a copy-paste agent prompt for each job.
Who is Wave MCP for?
Hardware verification and RTL engineers who debug simulation failures, with or without an AI coding agent.
What can I do with Wave MCP?
4 use cases so far, for example: Find the first divergence between pass and fail waveforms; Trace an X value back to its root cause; Review signal drivers and gating conditions before simulating. Each has steps and a copy-paste agent prompt.
What do I need to run Wave MCP?
Linux x86_64, where the Python dependencies ship as prebuilt wheels (other platforms need pylibfst built from source); Python 3.10 to 3.13; A simulation waveform (.fst or .vcd) and the same filelist used to run the simulation; An MCP-capable agent such as Claude Code, Codex, Cursor or Gemini CLI, or a terminal for the CLI.
What are alternatives to Wave MCP?
Other hot AI repos in Software and DevOps: Deep Infer, Harness2, Orca, Opencode, Graphify.
Is Wave MCP safe to run?
Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.