intent-engineering — Claude Code MCP server
Scores agent intent specs against a 25-item rubric, builds new ones from a nine-section template, and says how much an existing prompt needs reworking.
claude mcp add intent-engineering -- npx -y @swins/intent-engineering-mcpWhat intent-engineering does
Three tools come with the server. audit_intent_spec takes inline text or a file path and hands back a score out of 25, findings per section, anti-patterns it spotted and three fixes to make first. generate_intent_spec_scaffold writes a YAML skeleton for the chosen kind: blank, level-1-mvr or full-9-section. assess_retrofit_level reads an existing prompt or SKILL.md and picks L1, L2 or L3, with reasoning about complexity and how much autonomy the agent gets.
The rubric, the five fatal anti-patterns, the four autonomy levels and the nine-section layout all trace to the canonical intent-engineering skill. This is an adapter around it, not a fork. Every tool is read-only: nothing gets written to disk. Disk reads go through one guard — an extension allowlist, symlink resolution, confinement to a root, and a size cap. An earlier build would open whatever path it was given, so that guard closes a real disclosure bug.
You need Node 20+ and a client that speaks MCP. Transport is stdio only, which ties the server to a process-bound client and rules out cloud agents for now; the author plans SSE in version 1. Heading parsing is opinionated and its alias table is documented. One honest limit: the mapper recognizes an equivalent intent already in the text, it does not invent one.
What it helps with
- catch a vague objective before an agent acts on it
- get section-by-section findings instead of a single grade
- scaffold a new intent spec at the right level of detail
- decide whether an old prompt or
SKILL.mdis worth rewriting - check a spec for fatal anti-patterns
Example prompts for the agent
- Run
audit_intent_speconspecs/checkout-agent.md - Generate a scaffold with
generate_intent_spec_scaffold, kind level-1-mvr - Use
assess_retrofit_levelon thisSKILL.mdand tell me if it needs rework
How to install intent-engineering
Platform CLI
claude mcp add intent-engineering -- npx -y @swins/intent-engineering-mcpPlatform CLI
codex mcp add intent-engineering -- npx -y @swins/intent-engineering-mcpConfig file
{
"mcpServers": {
"intent-engineering": {
"command": "npx",
"args": [
"-y",
"@swins/intent-engineering-mcp"
]
}
}
}Config file
{
"servers": {
"intent-engineering": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@swins/intent-engineering-mcp"
]
}
}
}Platform CLI
gemini mcp add intent-engineering npx -y @swins/intent-engineering-mcpStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about intent-engineering
How do I install intent-engineering in Claude Code?
Run claude mcp add intent-engineering -- npx -y @swins/intent-engineering-mcp. The tools show up under intent-engineering in your next conversation.
What does intent-engineering do?
It audits intent specs on a 25-item checklist, scaffolds new specs by kind, and recommends a retrofit level for prompts you already have. Three MCP tools cover all of it.
Does the server modify my files?
No. File reads are guarded and no tool writes anything; the retrofit tool only recommends.
