usage-report
Generate a usage report for MCP Gateway Registry by SSHing into the telemetry bastion host, exporting telemetry data from DocumentDB, and producing a formatted markdown report with deployment insights.
npx skills add agentic-community/mcp-gateway-registry --skill usage-report --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Export telemetry data from the MCP Gateway Registry's DocumentDB telemetry collector and generate a usage report showing deployment patterns, version adoption, and feature usage in the wild.
How it works
- The workflow is two-pass: Pass 1 generates a deterministic report by running render_report.py to substitute a fixed template with values from analyzer outputs, and generate recommendations via recommendations.py. Every number and table cell traces to a source file.
- Pass 2 augments the rendered markdown with analyst commentary using augment_with_commentary.py, which reads a manifest of <!-- COMMENTARY:section_id --> markers from the rendered markdown and produces 2-4 sentence paragraphs per section, inserting them back into the report without altering numbers, tables, or charts.
- The process is divided into run_report.sh (Half A) to export data, generate charts, and render, followed by finish_report.sh (Half B) to apply commentary and render HTML.
- Artifacts are organized under OUTPUT_DIR/YYYY-MM-DD/; charts, CSVs, and metrics are stored in the dated subfolder.
- The skill uses a fixed report template (report_template.md), a set of Python scripts (render_report.py, recommendations.py, augment_with_commentary.py), and guidance hooks for commentary markers.
When to use it
Use when you need a reproducible usage report for MCP Gateway Registry that captures deployment patterns, version adoption, and feature usage, with an analyst narrative added post-render.
What it can touch
- Executes: run_report.sh and finish_report.sh via the skill environment.
- Accesses: bastion SSH export, registry_metrics.csv, and various Python scripts in the usage-report folder.
- Outputs: a two-pass rendered markdown report, a commentary.json, and the final HTML via finish_report.sh.
Caveats
- Date math and paths are controlled within the scripts (e.g., yesterday date handling, search-dir base path).
- The only non-deterministic step is the analyst commentary generation by the LLM, which writes prose into pre-defined slots and cannot modify numbers or tables.
- The report content is governed by editable files: report_template.md, render_report.py, recommendations.py, and augment_with_commentary.py.
# Usage Report Skill Export telemetry data from the MCP Gateway Registry's DocumentDB telemetry collector and generate a usage report showing deployment patterns, version adoption, and feature usage in the wild. ## Two-pass report generation **Pass 1 (deterministic, Step 7):** `render_report.py` substitutes a fixed template with values pulled directly from the analyzer's JSON/CSV outputs. The Recommendations section is generated by rule-based triggers in `recommendations.py`. Every number and table cell traces back to a source file. The LLM is not in this path. **Pass 2 (LLM commentary, Step 8):** `augment_with_commentary.py` extracts a manifest of `<!-- COMMENTARY:section_id -->` markers from the rendered markdown. The skill hands the manifest to the LLM, which produces 2-4 sentence analyst paragraphs per section. The augmenter then substitutes the markers with the commentary text. The LLM only writes prose into pre-defined slots; it cannot modify numbers, tables, or charts. Together: deterministic data for everything quantitative, LLM voice for synthesis. Hallucination is prevented because the LLM never writes numbers; flat reports are prevented because the commentary layer adds
- Two-pass report generation
- Visualization Guidelines
- Prerequisites
- Input
- Orchestrated Workflow (primary path)
- Running it
- Script behavior worth knowing
- Detailed Workflow (per-step reference)
- Step 1: Get Bastion IP
- Step 2: Copy Export Script to Bastion
- Step 3: Run Export on Bastion
- Step 4: Create Dated Subfolder and Download the CSV
- Step 5: Install Python Dependencies and Generate Charts
- Step 5b: Generate Timeseries Chart
Half A: export -> charts -> analysis -> render -> extract manifest. Report date and OUTPUT_DIR both default; pass them explicitly to be safe. Half B: apply commentary -> pandoc HTML. cd terraform/telemetry-collector && terraform output -raw bastion_public_ip scp -o StrictHostKeyChecking=no -i ~/.ssh/id_ed25519 \ terraform/telemetry-collector/bastion-scripts/telemetry_db.py \ ssh -o StrictHostKeyChecking=no -i ~/.ssh/id_ed25519 \ mkdir -p $DATE_DIR Cumulative -- all customers ever Active-yesterday -- only customers that reported on the last complete day.
What does the usage-report skill do?
Generate a usage report for MCP Gateway Registry by SSHing into the telemetry bastion host, exporting telemetry data from DocumentDB, and producing a formatted markdown report with deployment insights.
How do I install it?
Run `npx skills add agentic-community/mcp-gateway-registry --skill usage-report --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From agentic-community/mcp-gateway-registry, a repository with 845 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.