
Intent Engineering
Exposes three tools that audit agent intent specs against a 25-item rubric derived from production agent research. Feed it a spec via `audit_intent_spec` and you get a score out of 25, detected anti-patterns like outcome-as-activity or missing stop rules, and concrete fix recommendations. `generate_intent_spec_scaffold` gives you paste-ready YAML templates for blank, level-1-mvr, or full 9-section specs. `assess_retrofit_level` triages existing prompts or SKILL.md files into L1/L2/L3 retrofit buckets based on blast radius and autonomy. Useful when you're about to hand a spec to an agent and want to catch underspecification before it ships something confidently wrong. The server itself scores 23/25 when audited by its own tool.
- tools
- 3
- transport
- STDIO
- last updated
- Jun 18, 2026
Tools
3 toolsPublic tool metadata for what this MCP can expose to an agent.
audit_intent_specAudits a spec (spec_text or file_path) and returns a score out of 25, per-section findings, detected anti-patterns, and top 3 recommendations.
Audits a spec (spec_text or file_path) and returns a score out of 25, per-section findings, detected anti-patterns, and top 3 recommendations.
No parameter schema in public metadata yet.
generate_intent_spec_scaffoldGenerates a paste-ready YAML scaffold of a chosen kind (blank, level-1-mvr, full-9-section) plus next-step actions.
Generates a paste-ready YAML scaffold of a chosen kind (blank, level-1-mvr, full-9-section) plus next-step actions.
No parameter schema in public metadata yet.
assess_retrofit_levelAssesses an existing prompt or SKILL.md and recommends a retrofit level (L1, L2, or L3) with blast-radius, complexity, and autonomy reasoning.
Assesses an existing prompt or SKILL.md and recommends a retrofit level (L1, L2, or L3) with blast-radius, complexity, and autonomy reasoning.
No parameter schema in public metadata yet.
Sponsors
Readme
intent-engineering
intent-engineering is an MCP server that exposes three tools — audit_intent_spec, generate_intent_spec_scaffold, and assess_retrofit_level — letting any MCP-aware client (Claude Desktop, Cursor, Anti-Gravity) review, scaffold, and triage agent intent specs against a 9-section unified template synthesized from production-agent research.
Most agent failures aren't reasoning failures — they're intent failures. The spec is vague, the stop rules are missing, the outcome is an activity disguised as a state. This server makes that gap auditable from inside the harness the agent already runs in. The full reasoning, the rejected alternatives, and what would break in v0 live in docs/EXPLANATION.md.
The trust surface, up front
Details
- Repository
- github.com/seanwinslow28/sw-mcp-intent-engineering
- Category
- AI & LLM Tools
- Package
@swins/intent-engineering-mcp- Transport
- STDIO
- Registry
- MCP registry, active