Report Insight Lens

Live

Upload a PDF report and pull key numbers, tables and charts.

musemuse-report-insight-lens.vercel.appOpen

Get it

Connect it to any app that speaks MCP. It has 3 tools: extract_report_insights, answer_report_question, locate_figures. No sign-in.

Muse app: add this URL as a custom connector.
Claude Code: claude mcp add --transport http report-insight-lens https://muse-muse.vercel.app/api/mcp/report-insight-lens
Anything else: add it as a remote server over streamable HTTP.

Each line is what the check ran on, and no more.

This is a model's opinion, not proof.

Nothing here should be taken as tested.

Not checked Whether its answers are true
Not checked ChatGPT: only a person with an account can test it
Not checked Installing the Claude plugin or the Muse gadget pack on a real device
Not checked No Prove it run: nothing it comes with was run for real

Rebuild of a Meta developer video about pulling key numbers, tables and charts from PDF reports with page references, on current Muse models.

Muse Spark 1.3Reads the uploaded PDF directly and extracts key numbers, tables and question answers with page references as structured JSON
SAM 3.1Outlines charts, tables and figures on report page images from one short noun label per call

Rebuild fit: clean. Same demo as the video rebuilt on Spark 1.3 and SAM 3.1 without original footage, script or Llama code.
Large or scanned PDFs over about 4.5 MB must be shortened or compressed before upload.
Answers use only the uploaded PDF. No web search or outside data.
Figure boxes need simple prompts like chart or table. SAM can miss small or overlapping figures.
Saves stay in browser localStorage. No accounts or database.

Add it in the Muse app as a custom connector. It exposes 3 actions: extract_report_insights, answer_report_question, locate_figures.

Muse Code made 35 tool calls and 8 edits across 8 files (+562 −374).
npm run verify passed on the first try.
Screenshot judge: pass. Final screen shows summary with key numbers like $1,245,000 with page refs.
Built in 6 min for about $0.61 in model calls (est.).
How it was built: 122 tool calls, 28 edits touching 28 files { <read-skill-result name="meta-reasoning" status="ok"> <read-skill-result name="meta-sam" status="ok"> <read-skill-result name="product-ui" status="ok"> <read-skill-result name="verify" status="ok"> { {"items":6,"ok":true,"revision":1} { <read-skill-result name="bundled:python-env" status="ok"> { Edited `/tmp/make_fixtures.mjs` <read-skill-result name="bundled:taste" status="ok"> { {"items":6,"ok":true,"revision":2} Edited `app/api/actions/extract_report_insights/route.ts` Edited `app/api/actions/outline_report_charts/route.ts` Edited `app/page.tsx` Edited `app/layout.tsx` Edited `app/api/actions/extract_report_insights/route.ts`