Ingressward runs on your own machine — the client starts it, so there is no endpoint to ping. 31 installs a week from npm. Last commit 4 Jun 2026.
Block prompt injection, evasive spacing, and obscene content before it reaches your LLM.
Nothing serious here today
Today is the operative word: we check Ingressward every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mcp-server -e 'INGRESSWARD_API_KEY=<INGRESSWARD_API_KEY>' -- npx -y @ingressward/mcp-server{
"mcpServers": {
"mcp-server": {
"command": "npx",
"args": [
"-y",
"@ingressward/mcp-server"
],
"env": {
"INGRESSWARD_API_KEY": "<INGRESSWARD_API_KEY>"
}
}
}
}[mcp_servers.mcp-server]
command = "npx"
args = ["-y", "@ingressward/mcp-server"]
env = { INGRESSWARD_API_KEY = "<INGRESSWARD_API_KEY>" }{
"mcpServers": {
"mcp-server": {
"command": "npx",
"args": [
"-y",
"@ingressward/mcp-server"
],
"env": {
"INGRESSWARD_API_KEY": "<INGRESSWARD_API_KEY>"
}
}
}
}{
"servers": {
"mcp-server": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@ingressward/mcp-server"
],
"env": {
"INGRESSWARD_API_KEY": "<INGRESSWARD_API_KEY>"
}
}
}
}Put your own value in place of
<INGRESSWARD_API_KEY> (Your IngressWard API key. Get one at https://www.ingressward.com).
The author’s registry entry marks it as required.
Alternatives to Ingressward
same job, measured the same wayDetect prompt injection, jailbreaks, and code injection in untrusted text before it reaches an LLM.
Check an email before an AI agent sends it: send / ask a human / block. Detects prompt injection.
Prompt-injection detector for untrusted text before it reaches an LLM (RU/EN). BYO lovec.tech key.
Check text before your agent reads it: hidden instructions, invisible text and links that leak data.
Scans RAG content/scraped pages for indirect prompt injection
Scans RAG content/scraped pages for indirect prompt injection
Prompt-injection firewall for AI agents — scan untrusted text before LLM calls.
Security middleware for MCP. Blocks prompt injection, PII leakage, and resource exhaustion.
Ingressward — questions
Answers built from our own checks of this server.