MCPLow riskUnclaimed
injectshield
Prompt-injection firewall for AI agents — scan untrusted text before LLM calls.
bch1212bch1212/injectshield
server.json
{
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-09-29/server.schema.json",
"name": "io.github.bch1212/injectshield",
"description": "Prompt-injection firewall for AI agents — scan untrusted text before LLM calls.",
"repository": {
"url": "https://github.com/bch1212/injectshield",
"source": "github",
"subfolder": "packages/injectshield-mcp"
},
"version": "0.1.4",
"websiteUrl": "https://injectshield.dev",
"packages": [
{
"registryType": "npm",
"registryBaseUrl": "https://registry.npmjs.org",
"identifier": "@injectshield/mcp",
"version": "0.1.4",
"transport": {
"type": "stdio"
},
"environmentVariables": [
{
"description": "API key from https://injectshield.dev (free tier: 10K req/mo).",
"isRequired": true,
"isSecret": true,
"name": "INJECTSHIELD_API_KEY"
},
{
"description": "Override the API base URL for self-hosted deployments.",
"default": "https://api.injectshield.dev",
"name": "INJECTSHIELD_API_BASE"
}
]
}
]
}Permissions
DeclaredDetected
Runs code—
nodeInstalls—
npm:@injectshield/mcp@0.1.4Runs install scripts—None
NetworkNoneNone
Needs credentials
INJECTSHIELD_API_KEYINJECTSHIELD_API_KEYOutside the workspace—None
Agent tools—None
Checks
Low risk · Nothing worth a warning was found.
Not reviewed by a person · Checked by rules; the model review is not switched on yet.
Versions
- #10.1.4latestOct 7, 2026
injectshieldOpen in Codeg