Skip to content
Back to search

cgpa_mcp_server

PUCIT GPA Assistant - Assignment 3

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 21 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/ridaamir85/cgpa_mcp_server 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/ridaamir85/cgpa_mcp_server'

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/ridaamir85--cgpa-mcp-server/badge.svg)](/listings/ridaamir85--cgpa-mcp-server)

HTML

<a href="/listings/ridaamir85--cgpa-mcp-server"><img src="/api/listings/ridaamir85--cgpa-mcp-server/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

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 · 100 lines
  1. # PUCIT GPA Assistant - Assignment 3
  2. The GPA/CGPA assistant uses MCP tools, persistent SQLite memory, asynchronous execution, streaming, and interrupted-tool-call recovery. This GitHub repository contains the server files at its root; the full local assignment has separate `agent/` and `server/` folders.
  3. ## Deployment details
  4. - Hosted MCP server: https://cgpa-mcp-server.onrender.com/mcp
  5. - MCP authentication: Not required; the current endpoint is public and does not check an API key.
  6. - Server GitHub repository: https://github.com/ridaamir85/cgpa_mcp_server
  7. The Groq API key belongs to the separate agent application. This tool server does not require it.
  8. ## Available tools
  9. - `marks_to_grade_points`
  10. - `calculate_semester_gpa`
  11. - `calculate_new_cgpa`
  12. - `required_gpa_for_target`
  13. - `get_semester_courses`
  14. - `get_remaining_credit_hours`
  15. - `save_report`
  16. ## Test the hosted server
  17. ```powershell
  18. fastmcp list https://cgpa-mcp-server.onrender.com/mcp
  19. fastmcp call https://cgpa-mcp-server.onrender.com/mcp get_semester_courses semester=6
  20. ```
  21. Render's free instance may take time to wake after inactivity. The `/mcp` endpoint is intended for MCP clients; opening it directly in a browser may return a missing-session error.
  22. ## Connect the agent
  23. Set these values in the separate agent's `.env` file:
  24. ```text
  25. MCP_URL=https://cgpa-mcp-server.onrender.com/mcp
  26. FASTMCP_KEY=
  27. ```
  28. Keep the agent's existing `GROQ_API_KEY` configured locally. Never commit its `.env` file.
  29. ## Run locally
  30. The commands below run the server from this GitHub repository. In the full assignment folder, enter `server/` first.
  31. ```powershell
  32. python -m pip install -r requirements.txt
  33. python server.py
  34. ```
  35. Local MCP URL: `http://127.0.0.1:8000/mcp`. The server reads `PORT` when supplied by the hosting platform and otherwise uses port 8000.
  36. ## Run the full assignment agent
  37. From the full assignment folder, install its dependencies with `py -m pip install -r requirements.txt`. Copy `agent/.env.example` to `agent/.env` only if `.env` does not already exist. Add your Groq key and the hosted MCP settings shown above.
  38. ```powershell
  39. cd agent
  40. py agent.py
  41. ```
  42. Enter a name to select a `thread_id`. Commands are `/switch`, `/history`, `/forget`, and `exit`. The SQLite checkpointer preserves messages in `chats.db` in the working directory, so consistently run the client from `agent/`. SQLite may automatically create `chats.db-wal` and `chats.db-shm`.
  43. Streaming displays model text through `messages` and model/tool progress through `updates`. Recovery adds matching error ToolMessages for the supported case of an interrupted run ending with unanswered model tool calls.
  44. No local MCP server is needed when using Render. To test locally, run `server.py` in another terminal, change `MCP_URL` to the local endpoint, and restart the agent.
  45. ## Optional GUI from the earlier assignment
  46. The full local assignment also includes `agent/app.py`, the optional Streamlit interface carried over from the earlier GPA assignment. Keep the Streamlit dependency when including this file. The server-only GitHub repository does not contain the GUI or agent files.
  47. The main Assignment 3 interface is the `agent.py` terminal client. Demonstrate streaming and the `/switch`, `/history`, and `/forget` commands through that terminal client. The optional GUI does not provide the same terminal commands or live streaming display.
  48. To launch the GUI from the full assignment folder:
  49. ```powershell
  50. cd agent
  51. py -m streamlit run app.py
  52. ```
  53. Open the local URL printed by Streamlit, usually `http://localhost:8501`. It uses the MCP URL configured in `agent/.env`; when that URL points to Render, no local MCP server is needed. The GUI should be tested separately before submission.
  54. ## Render configuration
  55. - Runtime: Python
  56. - Build command: `pip install -r requirements.txt`
  57. - Start command: `python server.py`
  58. - Root directory: blank for this GitHub repository
  59. - Compute: Free
  60. ## Report storage
  61. `save_report` writes `.txt` reports into the server's `reports` directory and refuses to overwrite an existing filename. Reports are stored on the server, not downloaded to the client computer. Render's free filesystem is temporary, so reports may be lost after restarts or redeployments.
  62. ## Submission
  63. Submit `BCSF24M052_Assignment3.zip` containing the assignment's `agent/`, `server/`, dependency file, and README. Include `agent/.env.example`.
  64. Exclude real `.env` files, chat databases and their companion files, `__pycache__/`, virtual environments, and generated reports. The Streamlit interface and development test are optional; the terminal agent does not require them.

Ratings and comments

Sign in to rate this skill.

Sign in

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