GEO Shield
Detects hidden AI prompt injection, AI recommendation poisoning, sneaky redirects and hidden spam.
Open the source (opens github.com) https://github.com/krishnagauss/mcp_websafe
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
What it is
MCP servers from io.github.krishnaGauss.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
npm package (stdio)
geo-shield-mcp@0.1.0
From the server's entry in the official MCP Registry
Settings it asks for
GEO_SHIELD_DB_PATH· SQLite file for stored scans (default ~/.geo-shield/geo-shield.db).GEO_SHIELD_RETENTION_DAYS· Days to keep stored scans (default 30, 0 = forever).GEO_SHIELD_ALLOWED_PORTS· Extra destination ports to allow besides 80 and 443, comma separated.
Related
-
Dante IX — Autonomous Brand & GEO Agency MCP
MCP servers9-Circle Brand Reputation, Social Listening & Multi-Model GEO Audit + Shield Forge (danteix.com).
dante-mcp@2.1.0 -
shields-mcp
MCP serversGenerate shields.io style badge URLs. No key required.
shields-mcp@1.0.0 -
graphql-dos-shield
MCP serversCloudflare Workers MCP server: graphql-dos-shield
-
Execute adversarial-prompt-shield-mcp
MCP serversPremium agentic endpoint for adversarial-prompt-shield-mcp.
-
Execute binary-exploitation-shield-mcp
MCP serversPremium agentic endpoint for binary-exploitation-shield-mcp.
-
Execute ddos-mitigation-shield-mcp
MCP serversPremium agentic endpoint for ddos-mitigation-shield-mcp.