finance MCP Server
Autonomous AI customer success agent — 24/7 Email, WhatsApp & Web Form support. OpenAI Agents SDK + Groq LLaMA 3.3 70B + FastAPI + pgvector + Kafka. Hackathon 5 — CRM Digital FTE Factory Program.
Discovered via github-topic:mcp and last synced 3mo ago.
Install instructions not detected yet
Check the source repository for the latest setup steps.
`llama-3.3-70b-versatile` via Groq API
Neon PostgreSQL + pgvector
Twilio WhatsApp Sandbox
Purpose
Gmail API + Google Pub/Sub webhooks
Always called last — sends channel-appropriate reply
Count
Fetches cross-channel conversation history
Always called first — creates a ticket in PostgreSQL
Docker (Kafka), Kubernetes manifests included
`/support/ticket/{id}`
ngrok (local webhook exposure)
Endpoint
Platform
https://web-form-rouge.vercel.app
Technology
Semantic search over product docs via pgvector
Description
`/webhooks/whatsapp/status`
Routes to human agent with reason + urgency
--- ## Kubernetes Manifests included in `k8s/` for production deployment: ```bash kubectl apply -f k8s/namespace.yaml kubectl apply -f k8s/configmap.yaml kubectl apply -f k8s/secret.yaml kubectl apply -f k8s/deployment.yaml kubectl apply -f k8s/hpa.yaml ``` --- ## Key Engineering Decisions **Why Groq instead of OpenAI?** Free tier with `llama-3.3-70b-versatile` is fast enough for hackathon demo. The OpenAI Agents SDK works with any OpenAI-compatible API via `base_url` override. **Why Kafka for a prototype?** Decouples webhook response time from AI processing time. Webhooks return in <200ms; AI takes 5-20 seconds. Without Kafka, Twilio and Gmail would timeout waiting for the response. **Why Neon PostgreSQL?** Serverless, free tier, built-in pgvector support. No infrastructure to manage. **Why asyncpg over psycopg2?** Full async support for FastAPI and the worker's async Kafka consumer loop. --- ## Challenges & Fixes
Connect to Helium's MCP server for news research, media bias analysis, balanced perspectives, stock/options data, and semantic meme search across 3.2M+ articles and 5,000+ sources
Automate account reconciliation by matching transactions, identifying discrepancies, and generating variance reports
Create comprehensive business plans, financial projections, and strategic documents for funding or planning
Calculate cash runway, burn rate, and financial sustainability projections
TradingAgents: Multi-Agents LLM Financial Trading Framework
Build your autonomous hedge fund in minutes. AutoHedge harnesses the power of swarm intelligence and AI agents to automate market analysis, risk management, and trade execution.
💰 Double-entry bookkeeping made easy — plain-text accounting for humans and AI agents. Polished iOS & Android app built with React Native + Expo.
Pizzly, financial market analysis combining technical indicators with LLMs, featuring real-time data processing and AI-powered market insights ⚡️
Learn how to use the Financial Analyst Claude skill. Complete guide with installation instructions and examples.
Learn how to use the helium-mcp Claude skill. Complete guide with installation instructions and examples.
Learn how to use the Runway Calculator Claude skill. Complete guide with installation instructions and examples.