# Room Assignment Decision AI Agent Connect > Room Assignment Decision MCP handles the math and logic behind splitting up a house. It looks at who is living there, what rooms are available, and what the specific rules are for rent or accessibility. Your AI client uses this data to suggest room layouts that actually make sense for everyone involved. ## Overview - **Category:** productivity - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_vdIybUMRtAJ2XZba3wbg3hkFGx7DmjjkN6CPnrEW/ai-agent-connect - **Tags:** fairness, room-assignment, budgeting, household, optimization ## Description Deciding who sleeps where in a shared house is usually a headache of arguments and compromises. This MCP changes that by turning room assignments into a logic problem instead of a social one. You give your AI client the room inventory and the resident profiles, and it handles the heavy lifting. It weighs hard constraints like accessibility requirements and budget limits against individual preferences. If you have specific fairness rules, like adjusting rent based on room features, the engine applies those rules to ensure no one feels cheated. You can use it to generate a full recommendation from scratch or just use it to double check a plan you already drafted to make sure it doesn't violate any household rules. ## Tools ### calculate_assignment_recommendation This tool generates a primary room plan by combining resident data, room features, and your specific fairness rules. ### get_resident_profiles Use this to pull the specific profiles and needs of everyone living in the household. ### get_room_values This tool provides a list of all available rooms and the specific features each one contains. ### validate_assignment_plan This tool checks a manual room assignment against your established household rules to ensure it is valid. ## Prompt Examples **Prompt:** ``` Recommend a bedroom assignment for household 'hh-123' using equal rent fairness rules. ``` **Response:** ``` The recommended assignment for household 'hh-123' is: Resident A to Room 1, Resident B to Room 2. This follows the equal rent rule and satisfies all budget and accessibility constraints. ``` **Prompt:** ``` Check if assigning Resident A to Room 1 and Resident B to Room 2 is valid for household 'hh-456' with feature-based rent. ``` **Response:** ``` The proposed assignment is valid. It satisfies all accessibility needs and adheres to the feature-based rent distribution. ``` **Prompt:** ``` What are the available rooms in household 'hh-789'? ``` **Response:** ``` Household 'hh-789' has three available rooms: Room 1 (Ensuite, $1200), Room 2 (Standard, $900), and Room 3 (Basic, $700). ``` ## Capabilities ### Constraint Satisfaction Your agent uses this to ensure accessibility needs and budget limits are never ignored. ### Preference Optimization The AI uses this to balance individual resident wishes with the available room inventory. ### Rule Validation Your agent runs this to confirm that a proposed plan doesn't break any household agreements. ### Data Synthesis The tool combines resident profiles and room features into a single actionable recommendation. ## Use Cases ### New Housemate Setup When a new group moves into a house, use the recommendation tool to assign rooms based on their initial preferences. ### Rent Adjustment Logic Use the engine to calculate how much each person should pay based on the specific features of their assigned room. ### Accessibility Compliance Ensure that residents with specific physical needs are assigned to the correct rooms without manual error. ### Conflict Resolution Run a validation check on a disputed plan to prove whether it meets the agreed-upon household rules. ## Benefits - Removes human bias from the room selection process. - Enforces budget and accessibility constraints automatically. - Provides a clear rationale for why specific rooms were assigned. ## How It Works The process moves from data gathering to a finalized, validated plan. 1. Connect the MCP to your preferred AI client via Vinkius. 2. Provide the AI with the resident profiles and room inventory. 3. Ask the agent to calculate a recommendation based on your fairness rules. 4. Review the generated plan and its rationale. 5. Use the validation tool to confirm the final plan is compliant. ## Frequently Asked Questions **How does this MCP ensure fairness?** It uses specific fairness rules, such as equal rent or feature-based pricing, to weigh room features against resident profiles. **Can I use my own rules for room assignments?** Yes, the engine synthesizes your custom fairness logic with the available room and resident data. **What happens if a resident has accessibility needs?** The engine treats accessibility as a hard constraint, meaning it prioritizes these needs during the recommendation process. **Can I check a plan I made myself?** Yes, you can use the validation tool to see if a manually proposed assignment meets all your household rules. **Which AI clients can use this MCP?** You can use this with any MCP-compatible client like Claude, Cursor, or Windsurf. **How does the tool handle accessibility needs?** Accessibility needs are treated as hard constraints. The engine ensures any resident with mobility or accessibility requirements is assigned a room that meets those specific needs before considering other preferences. **Can I verify a custom assignment I made myself?** Yes, you can use the `validate_assignment_plan` tool to check if your proposed mapping of residents to rooms satisfies all budget, accessibility, and fairness rules. **What happens if a resident's budget is exceeded?** The engine will not recommend an assignment that exceeds a resident's budget limit. If no valid assignment can be found within the budget constraints, the tool will return an error.