Skip to main content
PathmodePathmode
Our ApproachFor BuildersBlogDevelopersPricing
Cursor
+
Pathmode
Pathmode

Your agent writes fast.
Make it write right.

Cursor is powerful — but it only knows what's in the codebase. The judgment behind the work — which user pain matters, what done means — lives outside it. Pathmode carries it in: intent specs anchored to real user evidence, plus auto-generated .cursorrules.

.cursorrules

# Project Context (auto-generated by Pathmode)

## Current Intent: Redesign Account Settings

Objective: Users can update preferences without drop-off

Outcomes: 3 testable conditions

Constraints: 3 non-negotiable rules

Evidence: 5 items from user research

## Constitution Rules

- All database access via server actions only

- Input validation with Zod on every API boundary

Context isn't judgment

Cursor reads your code perfectly. But code doesn't say why it exists — which user pain matters, what done means, what must not break.

Cursor alone

  • ×Agent sees code patterns — not the user pain behind them
  • ×Requirements live in Notion, Slack, Jira, and your head
  • ×.cursorrules are hand-maintained and quickly stale
  • ×No way to know if the edit actually solves the problem
  • ×"Implement this feature" without success criteria leads to rework
Pathmode

Cursor + Pathmode

  • Every edit traces to real user friction, quotes, and metrics
  • Agent gets objective, outcomes, constraints, and edge cases via MCP
  • .cursorrules auto-generated from your workspace strategy
  • Dependency graph prevents breaking upstream flows
  • Success means outcomes met — not just code compiled

Two ways Pathmode powers Cursor

Use the MCP server for live context, or export static rules. Both keep your agent aligned.

MCP Server

Live context, always fresh

Cursor's agent mode calls Pathmode tools directly. It reads your active intent, checks dependencies, and gets structured execution prompts — all in real time.

  • 22 MCP tools for full context access
  • Dependency graph analysis built in
  • Agent marks intents as shipped when done
  • Constitution rules enforced on every edit

.cursorrules Export

Static context, zero config

Generate a .cursorrules file from your workspace. Includes your strategy, constitution rules, and active intent — no MCP setup required.

  • One-click export from Pathmode workspace
  • Includes strategy, constraints, and active intent
  • Works in every Cursor mode
  • Commit to repo so the whole team gets context

.cursorrules that write themselves

Stop hand-maintaining rules files. Pathmode generates them from your workspace strategy, constitution rules, and active intent — with real user evidence baked in. Prefer Cursor's newer AGENTS.md format? The MCP server exports that too.

Intent-aware context

Your agent knows the objective, outcomes, constraints, and edge cases — not just the code.

Constitution rules enforced

Architectural constraints like "server actions only" or "Zod validation on every boundary" are baked into the rules file.

Evidence-backed decisions

The agent sees the friction reports, user quotes, and metrics that justify the work.

Always current

Re-export whenever your intent changes. Via MCP, the agent fetches live context automatically.

Example auto-generated .cursorrules

markdown•.cursorrules
# Project Context (auto-generated by Pathmode)

## Workspace Strategy
Vision: Become the default way product teams communicate intent to AI agents.
Non-negotiables: Every feature must trace to user evidence. No spec ships without outcomes.

## Active Constitution Rules
- All database access via server actions only — no direct client queries
- Input validation with Zod on every API boundary
- Row-level security (RLS) enforced on all tables

## Current Intent: Redesign Account Settings
Objective: Users can update preferences without drop-off
Outcomes:
  - Settings save confirmation visible within 500ms
  - Password change completes in under 3 clicks
  - Drop-off rate on settings page below 30%
Constraints:
  - Must work on iOS Safari 15+
  - No full-page reloads on save
Evidence: 5 items — 3 friction reports, 1 user quote, 1 drop-off metric

22 tools. Full context.

Cursor's agent mode connects via Model Context Protocol and gets instant access to your entire Intent Layer.

Read

  • get_current_intent

    Active intent with full spec

  • get_intent

    Single intent by ID

  • list_intents

    All intents, filter by status

  • search_intents

    Keyword search across specs

  • query_evidence

    Search evidence by type, severity, text

Write

  • create_intent

    Create a new intent spec

  • update_intent

    Update spec content

  • create_evidence

    Log new evidence items

  • link_evidence

    Link evidence to intents

  • log_implementation_note

    Record technical decisions

  • record_implementation_finding

    Write back what the build contradicted

Analyze

  • analyze_intent_graph

    Critical path, bottlenecks, cycles

  • get_intent_relations

    Dependency graph for one intent

  • get_workspace

    Vision, principles, non-negotiables

  • get_constitution

    Mandatory constraint rules

  • get_agent_prompt

    Structured execution prompt

Act

  • verify_implementation

    AI-grade work against the spec

  • update_intent_status

    Mark shipped or verified

  • export_context

    CLAUDE.md, .cursorrules, intent.md

  • intent_save

    Save spec to intent.md (no API key)

  • intent_export

    Export as agent config (no API key)

  • sync_context

    Round-trip context into CLAUDE.md

What Cursor sees when it calls get_current_intent

json•intent response
{
  "objective": "Redesign account settings so users can update preferences without drop-off",
  "problemSeverity": "critical",
  "outcomes": [
    "Settings save confirmation visible within 500ms",
    "Password change completes in under 3 clicks",
    "Drop-off rate on settings page below 30%"
  ],
  "constraints": [
    "Must work on iOS Safari 15+",
    "No full-page reloads on save",
    "Respect existing RBAC permissions"
  ],
  "edgeCases": [
    { "scenario": "User loses connection mid-save", "expectedBehavior": "Draft persisted locally, retry on reconnect" },
    { "scenario": "Concurrent edits from two sessions", "expectedBehavior": "Last-write-wins with conflict toast" }
  ],
  "evidence": "5 items — 3 friction reports, 1 user quote, 1 drop-off metric"
}

Setup in under 2 minutes

One config file. One API key. That's it.

1

Get your API key

Go to Settings → API Keys in your Pathmode workspace and generate a key.

2

Add to your Cursor config

Paste this into ~/.cursor/mcp.json

json•~/.cursor/mcp.json
{
  "mcpServers": {
    "pathmode": {
      "command": "npx",
      "args": ["@pathmode/mcp-server"],
      "env": {
        "PATHMODE_API_KEY": "pm_live_..."
      }
    }
  }
}
3

Start building

Cursor now has full access to your Intent Layer. Use agent mode and ask it to implement your active intent.

Also available on the Cursor Directory · Works offline too — add --local to read intent.md files from your project directory.

Stop guessing what to build.
Start shipping intents.

Give Cursor judgment, not just context.

No credit card required · Free for solo builders

PathmodePathmode

The product judgment layer for builders making products with AI.

Product

  • For Builders
  • Solutions
  • Intent Compiler
  • Pricing
  • Changelog

Integrations

  • GitHub
  • Jira
  • Claude Code
  • Codex
  • Cursor
  • Developer Docs
  • All integrations

Learn

  • Blog
  • Answers
  • Playbook
  • Use Cases
  • Glossary
  • IntentSpec Standard
  • Pathmode vs. The Rest

Company

  • About
  • Product Philosophy
  • Trust Center
  • Support

Legal

  • Privacy Policy
  • Terms of Service
  • Text & Data Mining

© 2026 Pathmode Oy (FI35979677). All rights reserved.

Essential cookies only — no tracking. Learn more

hello@pathmode.io