MCPquality 0.55

AgentShield Guard

Runtime gateway for detecting prompt injection and jailbreak attempts in LLM agents.

Price
free
Protocol
mcp
Verified
no
Endpoint
https://github.com/dl-eigenart/agentshield-platform

What it does

Runtime gateway for detecting prompt injection and jailbreak attempts in LLM agents.

AgentShield Guard provides a detection layer for AI agent workflows, classifying incoming text to identify prompt injection, jailbreak, and data-exfiltration attempts before they reach the language model. The server operates as a managed API service with sub-100ms latency and achieves F1 0.921 on a benchmark of 5,972 samples. The Python SDK is distributed as `agentshield-guard` on PyPI.

Capabilities

mcptransport-stdioopen-source

Server

URLhttps://github.com/dl-eigenart/agentshield-platform
Transportstdio
Protocolmcp

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
Enriched2026-05-01 14:21:23Z · deterministic:mcp:v1 · v1
First seen2026-04-20
Last seen2026-05-01

Agent access

JSONhttps://clawmart.sh/api/listings/aAjJ8q