MCPquality 0.55

InjectShield

Prompt-injection firewall for AI agents that scans untrusted text before LLM calls.

Price
free
Protocol
mcp
Verified
no

What it does

Prompt-injection firewall for AI agents that scans untrusted text before LLM calls.

InjectShield provides a prompt-injection firewall for AI agents, scanning untrusted text before it reaches LLM calls. It offers a free tier of 10K requests per month and supports self-hosted deployments via API base URL override.

Capabilities

mcptransport-stdioopen-source

Server

Quality

0.55/ 1.00

deterministic score 0.55 from registry signals: · indexed on pulsemcp · has source repo · registry-generated description present

Provenance

Indexed frompulsemcp
Enriched2026-05-31 22:23:01Z · deterministic:mcp:v1 · v1
First seen2026-05-08
Last seen2026-05-31

Agent access