Ingressward runs on your own machine — the client starts it, so there is no endpoint to ping. 22 installs a week from npm. Last commit 4 Jun 2026.
Block prompt injection, evasive spacing, and obscene content before it reaches your LLM.
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.
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 -- npx -y @ingressward/mcp-server
{
"mcpServers": {
"mcp-server": {
"args": [
"-y",
"@ingressward/mcp-server"
],
"command": "npx"
}
}
}
[mcp_servers.mcp-server]
command = "npx"
args = ["-y", "@ingressward/mcp-server"]
{
"mcpServers": {
"mcp-server": {
"args": [
"-y",
"@ingressward/mcp-server"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"mcp-server": {
"args": [
"-y",
"@ingressward/mcp-server"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
INGRESSWARD_API_KEY (Your IngressWard API key. Get one at https://www.ingressward.com.).
The author declared them in the registry entry; get the values from the project itself.
Detect 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.
Prompt-injection firewall for AI agents — scan untrusted text before LLM calls.
Security middleware for MCP. Blocks prompt injection, PII leakage, and resource exhaustion.
Classifies prompt injection, jailbreaks, and out-of-scope user input before agents act on it.
Draft, revise and review LinkedIn posts; a human approves each one before it goes live.
B2B prospecting from your Enginy workspace: find, enrich, and reach contacts and companies.
Answers built from our own checks of this server.