Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for hardware verification engineers who want an agent to answer 'what drives this signal' without a commercial debug license, for teams whose existing waveform debug MCP is license-seat-limited, and for anyone doing RTL bring-up who wants static netlist analysis before the first simulation.
Where this stands now
Tencent/wave-mcp ranks #991 of 2770 tracked Radar items by composite score (7.4 against a section median of 4.9). The section currently carries 1659 Bronze, 645 Gold, 466 Silver. RepoRadar has retained observations for this record since 2026-08-29 (35 days in the current window). Signal extremes versus the section: novelty at the 93th percentile.
Who should use it
Who should skip it
Pass on Tencent/wave-mcp if its scope or audience does not match what your team is building right now.
About this signal
Tencent/wave-mcp is tracked by RepoRadar as an MCP server in the Radar section. First seen 2026-08-29; the source record was last checked on 2026-08-29. The current verdict is 'watch' with a Silver tier and moderate setup difficulty. Tencent/wave-mcp leads on novelty (9.0) and open-source/build quality (8.4); its lowest signal is setup ease (6.0), so factor that in before investing setup time. This page summarizes the evidence RepoRadar captured from https://github.com/Tencent/wave-mcp.
How this item is evaluated
The Tencent/wave-mcp record combines a 7.4/10 composite score with separate popularity (100.0), risk (none), and setup (moderate) signals. See the scoring methodology for the current weights and evidence definitions.
Questions worth asking before you adopt this
Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.
Risk explanation
Version 0.1.1, first released 2026-08-25. This is an initial public release line with two tags, and the API should be expected to move; Linux x86_64 with glibc 2.28 or newer is the only environment that installs cleanly. macOS, Windows, and arm64 have no prebuilt pylibfst wheel and require a source build with cmake, gcc, and zlib. CentOS 7 / RHEL 7 (glibc 2.17) cannot use the pip path at all and needs either a container or the project's offline bundle with a self-compiled pyslang wheel; The validation table -- a hundred-plus test cases across a production chip project plus OpenTitan and XiangShan IPs, 2.25 million signal-level checks at 100% value-query correctness, 3.1 million tool calls -- is author-run and reported by the team that wrote the tool. The test corpora are public and named, which is more than most projects offer, but no third party has reproduced these numbers; The contributors API returns no entries for this repository, so per-author maintenance depth cannot be confirmed from the public API even though the commit history is real.