Skip to main content
Glama
alekhya2395

weekly-pulse MCP server

by alekhya2395
OverviewSchemaRelated ServersScoreDiscussions
Python
Hybrid

Milestone 3 — AI Agent with MCP

Weekly review pulse agent: ingest App Store / Play Store exports → synthesize themes and actions → publish to Google Docs and Gmail draft via Google Workspace MCP (no direct Google APIs).

Repository: github.com/alekhya2395/Milestone-3---AI-agent-MCP

Settings

Local setup from scratch (Windows / PowerShell):

# 1. Clone
git clone https://github.com/alekhya2395/Milestone-3---AI-agent-MCP.git
cd Milestone-3---AI-agent-MCP

# 2. Virtual environment
python -m venv .venv
.\.venv\Scripts\Activate.ps1

# 3. Install dependencies
pip install -r requirements.txt

# 4. Environment variables
copy .env.example .env
# Edit .env with your keys (Google OAuth, Alpha Vantage, etc.)

# 5. MCP setup (Cursor)
# Follow: phases/phase-01-mcp-setup/gcp-setup-checklist.md
# Then:  phases/phase-01-mcp-setup/runbook.md

# 6. Download reviews (Phase 2)
python phases/phase-02-review-ingestion/scripts/fetch-reviews.py --weeks 10
python phases/phase-02-review-ingestion/scripts/normalize-reviews.py

Step 5 details:

After step 6, review outputs are in data/raw/ (CSV) and data/reviews/reviews.json (filtered JSON).

Related MCP server: Google Business Profile Review MCP Server

Documentation

Doc

Purpose

docs/problemstatement.md

Goals and constraints

docs/architecture.md

System design

docs/implementationplan.md

Phase-wise plan

docs/eval.md

Milestone evaluation tracker

docs/decision.md

Architecture decisions

docs/deployment-railway.md

Deploy custom MCP server on Railway

Railway deployment

Deploy the weekly-pulse MCP server (review tools) to Railway:

railway up

Full guide: docs/deployment-railway.md

Google Gmail/Drive MCP remain on Google's servers — connect both from Cursor.

Project layout

├── .cursor/mcp.json          # Drive + Gmail MCP (secrets via env vars)
├── data/raw/                 # Store review exports
├── data/processed/           # Normalized reviews & pulse artifacts
├── docs/                     # Specs and per-phase eval.md
├── phases/                   # Phase work folders (runbooks, artifacts)
└── prompts/                  # Agent prompts (Phase 3+)

Current phase: 1 — MCP & foundation

  1. Complete GCP setup checklist

  2. Set env vars from .env.example

  3. Restart Cursor → Settings → Tools & MCP → Connect google-drive and google-gmail

  4. Run smoke tests per runbook

  5. Sign off Phase 1 eval

MCP config location

  • Project: .cursor/mcp.json (committed, no secrets)

  • Credentials: GOOGLE_OAUTH_CLIENT_ID and GOOGLE_OAUTH_CLIENT_SECRET in .env or system environment

References

This server cannot be installed

F
license - not found
-
quality - not tested
C
maintenance

How are these scores calculated?

Maintenance

–Maintainers
–Response time
–Release cycle
–Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/alekhya2395/Milestone-3---AI-agent-MCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server