Intent Engineering runs on your own machine — the client starts it, so there is no endpoint to ping. 75 installs a week from npm. Last commit 29 Aug 2026.
Audit, scaffold, and triage agent intent specs against a 9-section template.
Today is the operative word: we check Intent Engineering 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 intent-engineering -- npx -y @swins/intent-engineering-mcp
{
"mcpServers": {
"intent-engineering": {
"command": "npx",
"args": [
"-y",
"@swins/intent-engineering-mcp"
]
}
}
}
[mcp_servers.intent-engineering]
command = "npx"
args = ["-y", "@swins/intent-engineering-mcp"]
{
"mcpServers": {
"intent-engineering": {
"command": "npx",
"args": [
"-y",
"@swins/intent-engineering-mcp"
]
}
}
}
{
"servers": {
"intent-engineering": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@swins/intent-engineering-mcp"
]
}
}
}
Toolbox for AI agent skills: scaffold, lint, pack, install, and serve SKILL.md skills
Scaffold, plan, update and extend projects from Templetry templates.
Scaffold Starter Series projects and check release, deployment, security, and agent instructions.
Trust-aware agent memory with evidence-backed recall, self-inspection, and audit history.
Intent-bound action authorization for AI agents: policy, human approval, and a signed audit trail.
Immutable audit trail for agent-to-agent interactions
List Documentero templates, inspect field schemas, and generate Word/PDF/Excel documents.
Prompt-injection shield for agents: read pages, scan content, audit MCP servers and skills. x402.
Answers built from our own checks of this server.