Suprawall MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 25 installs a week from npm. Last commit 13 May 2026.
SupraWall security gateway for AI agents. Provides deterministic guardrails for MCP agents.
Today is the operative word: we check Suprawall MCP 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 suprawall-mcp -- npx -y suprawall-mcp-plugin
{
"mcpServers": {
"suprawall-mcp": {
"args": [
"-y",
"suprawall-mcp-plugin"
],
"command": "npx"
}
}
}
[mcp_servers.suprawall-mcp]
command = "npx"
args = ["-y", "suprawall-mcp-plugin"]
{
"mcpServers": {
"suprawall-mcp": {
"args": [
"-y",
"suprawall-mcp-plugin"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"suprawall-mcp": {
"args": [
"-y",
"suprawall-mcp-plugin"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
SUPRAWALL_API_KEY (Your SupraWall API key).
The author declared them in the registry entry; get the values from the project itself.
Security guardrails for AI agent payments
AI writes. SPARDA proves. Deterministic, offline security gate for AI edits.
AI writes. SPARDA proves. Deterministic, offline security gate for AI edits.
AI Agent Guardrails MCP server - security layer
Deterministic authorization and security guard for AI agent actions with signed receipts.
Real-time semantic security for AI coding agents and MCP tools
Security gateway for AI agents: detects prompt injections, jailbreaks, and common vulnerabilities.
Security gateway for MCP agents: blocks prompt-injection-driven tool calls before they execute.
Answers built from our own checks of this server.