What it does
The server pairs a hybrid prompt-injection check, based on Llama Guard 3, with masking of Brazilian personal data and secrets. It is listed as an MCP server, so it is meant to be connected to an MCP-compatible client.
Developers working with Brazilian personal data in prompts may look at it to screen inputs and mask sensitive values. Access is priced through x402, so running it involves a payment flow in USDC on the Base network.
Limitations and requirements
Use is paid through x402 in Base USDC, as stated in the publisher description. The source does not list other requirements.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 16 Nov 2026 · last seen 16 Nov 2026 · its page on the source
Agent Guard Prompt Injection & PII Firewall (x402)
Hybrid prompt-injection firewall (Llama Guard 3) & Brazil PII/secret masking via x402 Base USDC.
v2.2.0As shown on registry.modelcontextprotocol.io when we last read it