# rajameta

- **Event:** [Meta Global AI Developer Hackathon](https://cerebralvalley.ai/e/meta-ai-developer-hackathon)
- **When:** Oct 26, 12:00 PM – Nov 4, 9:00 PM (EST)
- **Where:** Online
- **Team:** [rajagavaskar thangaraj](https://cerebralvalley.ai/u/rajagavaskar)
- **GitHub:** https://github.com/rajagavaskargithub/ASG-AI-SQL-Guard
- **Demo video:** https://youtu.be/b0wMEdcS9oQ
- **Gallery:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/134

Summary:
Build a gateway that sits between any AI agent and its MCP servers or tool endpoints, and enforces policy on every tool call before it executes. It adds three core controls: allowlists, argument validation, and human approvals. Developers drop it in front of an existing agent with minimal code changes.

Problem:
Agents are being given real tools (shell, databases, email, payments, cloud APIs), but there is no standard enforcement layer between “the model decided to call this” and “the call ran.”
* Prompt-level guardrails are advisory; the model can be tricked by prompt injection or just be wrong.
* Each framework has its own ad hoc permission handling, so teams reimplement it badly.
* Dangerous calls (DROP TABLE, rm -rf, sending email to an external domain, large refunds) look identical to safe ones at the protocol level.
* There is no audit trail of what an agent tried to do, only what it did.

Proposed Solution:
A transparent proxy/gateway that speaks MCP on both sides (agent-facing server, upstream-facing client), evaluates each tools/call request against a declarative policy, and then allows, denies, or pauses for approval.

## More from Meta Global AI Developer Hackathon

- [Moshimo Town](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/131)
- [Synthvale](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/132)
- [HeyWalk](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/133)
- [Baby Bust](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/135)
- [Earnova AI](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/136)
- [Vivek's Team](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/137)

---

Markdown version of https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/134. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt