Shrike
PulseGate's liveness check found it on 3 Oct 2026; it has been in the index since 31 Aug 2026. How this is checked
Shrike is an open-source MCP server that scans AI agent inputs and outputs for threats including prompt injection, jailbreak attempts, SQL injection, and personally identifiable information. Developers can install and run it locally to add security checks to agent workflows.
Inferred · not functionally tested
Overview
6 featuresPurpose: Scanning AI agent interactions for prompt injection, jailbreaks, SQL injection, and PII exposure.
Inferred · not functionally tested
Audience: AI developers and security engineers
Inferred · not functionally tested
Functions: monitoring, agents
Inferred · not functionally tested
Interfaces: API: indicated (inferred, not tested) · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)
Recorded constraints: pricing: open_source · license: Open Source · platforms: API, CLI · deployment: cli, self_hosted, api_only
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: github.com. These links do not verify the individual claims.
Shrike sits in PulseGate's AI & LLM security category. Inferred · not functionally tested: It focuses on scanning AI agent interactions for prompt injection, jailbreaks, SQL injection, and PII exposure. Inferred · not functionally tested: It is built as an open-source project for AI developers and security engineers. Basis unknown · not verified: The project is open source (Open Source). Basis unknown · not verified: Shrike is available on the command line and API, and it can be self-hosted.
Shrike Security builds and maintains Shrike. Inferred · not functionally tested: Among its 6 catalogued features are Prompt Injection Scanning, Jailbreak Detection, and SQL Injection Scanning. Inferred · not functionally tested: Catalogued interfaces include an MCP server.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- Prompt Injection Scanning
- Jailbreak Detection
- SQL Injection Scanning
- PII Protection
- MCP Server
- Local Installation
Topics: Inferred · not functionally tested
Built with & integrations
- google_gemini
- aiplatform in the HTML
Trust & compliance
Indexing history
1What PulseGate has recorded for this listing
- Indexed31 Aug · 23:45 UTCShrike seen via MCP Registry (official)Source: MCP Registry (official) · Open
Frequently asked questions about Shrike
- What does Shrike do?
- Inferred · not functionally tested: Shrike focuses on scanning AI agent interactions for prompt injection, jailbreaks, SQL injection, and PII exposure. It is catalogued under AI & LLM security on PulseGate.
- Who is Shrike for?
- Inferred · not functionally tested: Shrike is an open-source project built for AI developers and security engineers.
- Does Shrike have a free plan?
- Basis unknown · not verified: Yes — Shrike is open source under the Open Source license and free to use.
- What platforms does Shrike run on?
- Basis unknown · not verified: Shrike runs on the command line and API. It can also be self-hosted.
- Is Shrike still active?
- PulseGate's liveness check found it on 3 Oct 2026.
- What projects are similar to Shrike?
- Similar projects tracked by PulseGate include Shrike, MCPShield Agent, and ShieldMCP.ShrikeMCPShield AgentShieldMCP
- Who makes Shrike?
- Shrike is developed by Shrike Security.
- Is Shrike open source?
- Basis unknown · not verified: Yes — Shrike is open source under the Open Source license.
Similar projects
Closest matches by what these projects do