- Access Metrics
- Choose Source
- Retrieve Data
Finance Toolkit MCP: Comprehensive Financial Metrics Library
A Python library offering 500 financial metrics for accurate data analysis, accessible both locally and remotely.
Via Hacker News · JerBouma ↗Operations & Finance
Agents that pull metrics from your tools, write the weekly or monthly report and explain what changed.
45 published use cases
A Python library offering 500 financial metrics for accurate data analysis, accessible both locally and remotely.
Via Hacker News · JerBouma ↗Learn how to schedule a daily report in Google Sheets using Apps Script triggers.
Via Bluesky · @apps-script.bsky.social ↗A Claude Cowork skill tracks diet and medical metrics in a spreadsheet, and meals told to Claude on mobile are logged in the daily record.
Original post ↗Commenters use Microsoft Scout to build a dashboard that persists across reboots and to document and troubleshoot support cases end to end.
Original post ↗In a workshop demo, a Manus agent scraped about 70 talks, extracted schedules, converted times to UTC, and built a dashboard with recommendations and calendar integration.
Original post ↗Claude computer use operated the desktop, handled logins and modals, and entered wallet numbers into a spreadsheet over 19 minutes.
Original post ↗A toolkit gives a coding agent a semantic layer and dashboard files so it can query data warehouses and publish in-depth reports and visualizations.
Original post ↗An n8n workflow scans emailed invoices, extracts supplier, amount, date and description, and feeds a real-time Google Sheets dashboard.
Original post ↗Miles Deutscher reportedly uses Claude to merge monthly bank statements into a dashboard, visualize spending, compute metrics and analyze portfolio allocation.
Original post ↗Manus turned a large lead CSV into a dashboard in about 20 minutes and charted coffee shop sales data with Python, though it sometimes looped and drained credits.
Original post ↗Author used ChatGPT for architecture and the Junie agent in WebStorm to build a dashboard aggregating PRs across four repos, flagging approvals, conflicts and comments, in about 3 hours.
Original post ↗A Rippling engineer's Cursor cron agent runs every two hours, reading Slack notes, GitHub PRs, Jira issues and mentions, deduplicating them and posting a dashboard.
Original post ↗Cognition's team uses a Devin variant called DANA to query their data warehouse, build dashboards and answer data questions, and Devin fills out report forms.
Original post ↗A non-coding media operator had Claude Code build a dashboard tracking newsletter performance across a network in about 30 minutes; a solo CFO built an expense system.
Original post ↗A backend engineer says their team uses Devin for internal dashboards and migration scripts, treating output as a starting point that saves about four hours of boilerplate.
Original post ↗The author runs OpenClaw on a dedicated machine, talks to it in Slack, keeps daily memory notes, and tracks its tasks and actions on a dashboard.
Original post ↗The poster uses Claude with Apple Health, nutrition and lifting app data, plus medication and bloodwork files, and has it maintain an HTML dashboard.
Original post ↗A user has agents handle pet import/export paperwork and forms, Airbnb pricing with weekly reports, and a commercial dispute they say was won, plus filing documents in Chrome.
Original post ↗Charlie Hills has Codex Computer Use open his Substack dashboard and collect figures for every published post, for apps lacking MCP connectors.
Original post ↗A poster describes months of driving desktop agents against real apps; in one task the agent misread a modal and kept reporting success while moving nothing.
Original post ↗Grok handled live chat, email, tickets, refunds, knowledge base, QA, reporting and escalations for an 8-person support company, per the author's account.
Original post ↗Built an agent that answers product and pricing questions, handles follow-ups, gives payment details, notifies admins of payment proof and hands off to humans via a dashboard.
Original post ↗The author built an autonomous support agent for a three-person team facing 847 waiting customers, reporting 500+ tickets a day and a 94% resolution rate (self-reported).
Original post ↗An n8n agent analyzes GA4, rank and SERP data, tracks competitor keywords, rewrites articles and saves performance reports.
Original post ↗A user had Replit Agent create a meeting app with dashboard, logic and analytics, and deploy it live without manual code changes.
Original post ↗A CLI tool built on Twilio gives terminal agents a voice to make calls, with a dashboard for questions they can't answer.
Original post ↗The poster pipes bank transaction data into ChatGPT and uses Claude for budget analysis, investment research, and summarizing and comparing financial reports.
Original post ↗Claude Code handles repetitive prospecting-adjacent workflows like lead research, reporting, CRM updates and enrichment.
Original post ↗Karpathy's agent scanned the home network, logged into Sonos, reverse-engineered APIs, mapped lights, HVAC, shades, pool and security, and built a dashboard.
Original post ↗An integration starts Codex CLI tasks against a Home Assistant config to diagnose failing automations, check dashboards for broken cards and create scripts.
Original post ↗Cowork reads a folder of bank statements, finds recurring charges and builds a dashboard of active and cancelled subscriptions and monthly savings.
Original post ↗Manus found 40+ Los Angeles dental offices with contact details across directories, then built a CRM app with dashboard, profiles and notes.
Original post ↗A non-technical user filters their inbox to emails needing replies, turned 15 homeschool PDFs into interactive narrated courses, and built a budget dashboard.
Original post ↗Claude in Chrome runs weekly to scrape Substack ranking data into a dataset, and Cowork analyzes it and writes a weekly report.
Original post ↗An agent loop reading a revenue dashboard ran 365 cycles, generating 394 interlinked SEO pages and a webhook inspection tool with landing page, docs and drafted outreach.
Original post ↗The writer had Claude audit their Home Assistant config, using the Chrome connector to click through the dashboard and paste config blocks into editors when the MCP couldn't edit directly.
Original post ↗The author tested six scheduled tasks: email briefings, file cleanup, Stripe reporting, invoice reconciliation, notes tidying and flight price tracking.
Original post ↗A surgeon runs about twenty scheduled Cowork tasks that triage email, prep meetings, flag stale deals and leave drafts ready in a dashboard.
Original post ↗The author uses Claude and its Chrome extension to file complaints and dispute charges, reporting ten wins and over $12,000 recovered, while still reviewing emails and making calls.
Original post ↗AT&T deploys Gemini-based voice and chat assistants with 60-day memory, reporting 20% more inquiries fully automated.
Original post ↗A reviewer had Manus find content for slide decks and produce a monthly marketing report in an uploaded PPTX template; editing tools were limited.
Original post ↗A technical writer uses Devin to explore code before documenting it, plus a Slack writing agent built on Devin, reporting about 20,000 lines of docs per month.
Original post ↗A low-coder used Replit Agent to build a 'Budget Buddy' with category budgets, a spending dashboard and expense log in about 20 minutes, using half their monthly credits.
Original post ↗A user had Muse use unused Southwest credits to book a flight, watch for better seats, handle OpenTable reservations and keep a trip dashboard for a visiting friend.
Original post ↗The author gave Cowork a day of busywork, including pulling numbers from three sources into a report that needed light editing and a scheduled weekly metrics report; screen-driving was slower and needed nudges.
Original post ↗Yes. The agent pulls numbers from your analytics, CRM or finance tools on a schedule, compares them with the previous period and writes a short narrative of what changed and why. You review the draft instead of assembling it.
Across the 45 published workflows on this page, the most used tools are Claude Cowork (7), Claude (5) and Manus (4). Each use case lists every tool it needs and the role it plays.
Open any use case to see the tools, the step-by-step setup and example prompts you can copy. Start with a beginner workflow, run it on a small batch and review the output before you automate it fully.