Skip to content
Back to search

deploypilot

MCP server connecting AI assistants to a company’s internal systems (orders, tickets, knowledge base) with RAG, permissions, and safety controls. Built as a Forward Deployed Engineering project.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 18 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/devfahadmunir/deploypilot with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/devfahadmunir/deploypilot'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/devfahadmunir--deploypilot/badge.svg)](/listings/devfahadmunir--deploypilot)

HTML

<a href="/listings/devfahadmunir--deploypilot"><img src="/api/listings/devfahadmunir--deploypilot/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

# 1. Start the database
docker compose up -d

# 2. Create a virtual environment and install dependencies
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

# 3. Configure and seed
cp .env.example .env
python acme/db/seed.py

Expected output:

  customers      303
  products        38
  orders        1005
  order_items   2499
  refunds         40
  tickets        153
Done. Acme Store is open for business.

Re-running `seed.py` wipes and regenerates the same data.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 77 lines
  1. # DeployPilot
  2. **An MCP server that connects AI assistants to a company's internal systems, built the way a Forward Deployed Engineer would ship it for a client.**
  3. The client is **Acme Store**, a fictional e-commerce company. DeployPilot exposes Acme's order database, support tickets, and internal knowledge base to any MCP-compatible AI client, with safety controls for risky actions like refunds.
  4. > 🚧 Work in progress. Built phase by phase; see the roadmap below.
  5. ---
  6. ## Phase 0: Acme Store backend
  7. Acme's "systems" consist of:
  8. - **PostgreSQL database** (with pgvector) containing customers, products, orders, order items, refunds, and support tickets
  9. - **Knowledge base** of internal documents in `acme/knowledge_base/` (refund policy, shipping, returns, warranty, membership, support guidelines, FAQ)
  10. All data is synthetic and generated reproducibly with Faker (fixed seed).
  11. ### Setup
  12. ```bash
  13. # 1. Start the database
  14. docker compose up -d
  15. # 2. Create a virtual environment and install dependencies
  16. python -m venv .venv
  17. source .venv/bin/activate
  18. pip install -r requirements.txt
  19. # 3. Configure and seed
  20. cp .env.example .env
  21. python acme/db/seed.py
  22. ```
  23. Expected output:
  24. ```
  25. customers 303
  26. products 38
  27. orders 1005
  28. order_items 2499
  29. refunds 40
  30. tickets 153
  31. Done. Acme Store is open for business.
  32. ```
  33. Re-running `seed.py` wipes and regenerates the same data.
  34. ### Demo customers (planted edge cases)
  35. | Customer | Tier | Scenario |
  36. |---|---|---|
  37. | Sarah Khan (`sarah.khan@example.com`) | Standard | One order delivered 10 days ago (refundable) and one delivered 45 days ago (outside the 30-day window) |
  38. | Ali Raza (`ali.raza@example.com`) | Premium | Order delivered 50 days ago (still refundable under the 60-day premium window) and 3 open tickets (should be escalated) |
  39. | John Miller (`john.miller@example.com`) | Standard | Order shipped 12 days ago and not delivered (late) and an order already refunded |
  40. These cases test whether the AI applies business rules correctly, not just whether it can query data.
  41. ---
  42. ## Roadmap
  43. - [x] **Phase 0:** Acme backend (database, seed data, knowledge base)
  44. - [ ] **Phase 1:** MCP fundamentals: tools, resources, prompts
  45. - [ ] **Phase 2:** Database integration with validation and error handling
  46. - [ ] **Phase 3:** RAG over the knowledge base with pgvector
  47. - [ ] **Phase 4:** Remote transport, auth, permissions, and confirmation for risky actions
  48. - [ ] **Phase 5:** Custom agent client
  49. - [ ] **Phase 6:** Evals, cost tracking, Docker deployment
  50. ---
  51. ## Author
  52. **Fahad Munir**, AI/ML Engineer | Forward Deployed Engineer
  53. [LinkedIn](https://www.linkedin.com/in/devfahadmunir) · [GitHub](https://github.com/devfahadmunir)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.