GoldenAnalysis runs on your own machine — the client starts it, so there is no endpoint to ping. 118 installs a week from pypi. Last commit 18 Sep 2026.
Read-only cross-cutting analysis, metrics, and reporting across the Golden Suite.
What the code does
We read the source, 21 h ago · rules 3dff92dd89df
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
std::fs::File::create(path).map_err(|e| format!("create {path}: {e}"))?,
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
result = subprocess.run(cmd, check=False)
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
"AGFzbQEAAAAB8gEiYAAAYAABf2ABfwBgAX8Bf2ABfwF+YAJ/fwBgAn9/AX9gAn9/BH9/f39gAn9/AX5gAn9/AW9gA39/fwBgA39/fwF/YAR/f39/AGAEf39/fwF/YAR/f39/BH9/f39gBX9/f39/AGAFf39/f38Bf2AFf39/f38Ef39/f2AGf39/f39/AGAGf39/f39/AX9gB39/f39/f38AYAR/f39+AGAFf39/fn8AYAR/f398AGADf39+AGAEf39+fgBgA39/fAR/f39/Y…
этот файл ставится пользователю, но в репозитории его нет
The worked example: a per-metric **2% gate on `match.recall_safe_bound`** catches a 0.97 → 0.89 recall drop that a global 10% gate would miss, exactly the kind of quiet quality regression a nightly pipeline should alert on.
result = subprocess.run(cmd, check=False)
sub.write_parquet(os.path.join(out, f"part-{k:02d}.parquet"))
m = __import__(mod, fromlist=[name])
… "ngram_min": 2, "ngram_max": 4, "lowercase": true, "boundary": "\u0002", "seed": 0}, "n_features": 128, "weights_b64": "bL+APH9Gh7y98qM939VWPKEhib39Ijk9eekmPuZz8j3+J7S9VfkhvuqOn71uRak7Ts2UvuwK4LwDeh++4HW7vY9Ui70Y8iG9PcFSPRRxBT6XnoO8RuguPjNKqr0h+TM90knnPYWJQDz4Vb69MvbrvQpbar3VeuE…
| `retrieve_similar` | Semantic retrieval (#1089): return the records in a CSV most similar to a free-text query, ranked by cosine similarity. Embeds the chosen column and the query with the zero-config in-house embedder (no cloud/torch by default) and runs ANN search. The read s…
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
A tool parameter here reaches a dangerous call
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add goldenanalysis -- uvx goldenanalysis{
"mcpServers": {
"goldenanalysis": {
"args": [
"goldenanalysis"
],
"command": "uvx"
}
}
}[mcp_servers.goldenanalysis]
command = "uvx"
args = ["goldenanalysis"]{
"mcpServers": {
"goldenanalysis": {
"args": [
"goldenanalysis"
],
"command": "uvx"
}
}
}{
"mcpServers": {
"goldenanalysis": {
"args": [
"goldenanalysis"
],
"command": "uvx"
}
}
}Alternatives to GoldenAnalysis
same job, measured the same wayRead-only access to your Reporting Ninja marketing and analytics data across 20+ ad platforms.
Read-only IBKR MCP: account, positions, brief, regime, stress, reporting, Edge, and risk.
An MCP server for analyzing startup financial health and generating metrics reports locally.
Google Analytics 4: reports, traffic sources, landing pages, events, realtime (read-only).
Native Weavatrix MCP: 43 read-only repository tools across 24 code and configuration surfaces.
Read-only source search and retrieval across configured GitHub repositories
Read-only access to your Nexly web analytics: traffic, pages, acquisition, events, and reports.
Aviation accident report parsing and prompt generation service under the SHELL framework.
GoldenAnalysis — questions
Answers built from our own checks of this server.