--- name: al-554-stop-rerunning-the-same-mls-search-for-every-buyer-save-e description: "A buyer's agent with several active clients can lose a whole afternoon each week rebuilding the same MLS searches and scanning photos. In Agent Intelligence issue #49 (May 15, 2026), Matt Spangler described a roughly 29-minute 'buyer concierge' build that connects the Flexmls MCP server (which links an agent's MLS account to Claude using their existing login) with Claude Memory, so each buyer's criteria is saved once. The agent then asks 'what's new for [buyer]' to get new active listings from the past 7 days ranked by fit with the top 3 explained, plus a weekly pass across all active buyers that flags homes two of their buyers might compete for (as summarised by Real Estate Use Cases). It only works if your MLS board has enabled the Flexmls MCP; otherwise you can paste a new-listings export instead. Keep saved criteria about the property and location only. Use when the user wants help with buyer new-listing concierge (sales) for a small business." --- # Stop rerunning the same MLS search for every buyer: save each buyer's criteria in your AI once, then ask "what's new for [buyer]" to get this week's new listings ranked by fit, with the top 3 explained A buyer's agent with several active clients can lose a whole afternoon each week rebuilding the same MLS searches and scanning photos. In Agent Intelligence issue #49 (May 15, 2026), Matt Spangler described a roughly 29-minute 'buyer concierge' build that connects the Flexmls MCP server (which links an agent's MLS account to Claude using their existing login) with Claude Memory, so each buyer's criteria is saved once. The agent then asks 'what's new for [buyer]' to get new active listings from the past 7 days ranked by fit with the top 3 explained, plus a weekly pass across all active buyers that flags homes two of their buyers might compete for (as summarised by Real Estate Use Cases). It only works if your MLS board has enabled the Flexmls MCP; otherwise you can paste a new-listings export instead. Keep saved criteria about the property and location only. ## Inputs to collect first Ask the user for anything below that they haven't already given you. Don't guess missing facts. - First name + initial - Beds, baths, must-haves, price range, areas, deal breakers - Buyer ## Instructions Do the task below with the user's inputs in place of each [bracket]. 1. Connect your MLS to your AI if your MLS offers a connector (e.g. Flexmls: Preferences > AI Settings > turn on MCP, then add it to Claude). If not, export this week's new listings as a CSV instead. 2. For each active buyer, tell your AI: "Save as 'Buyer: [first name + initial]'. Criteria: [beds, baths, must-haves, price range, areas, deal breakers]. Timeline: [date]." Keep it to property and location; never save or filter by protected characteristics. 3. Ask: "What's new for [buyer]? Pull new active listings from the last 7 days, rank them by fit to the saved criteria, and explain the top 3 in two sentences each, including any deal breaker you had to bend." 4. Weekly: "Run this for all my active buyers. Top 3 per buyer, and flag any home that fits two of my buyers so I can handle it fairly." 5. Check each listing's status and details in the MLS before sending anything, then send each buyer their shortlist yourself with a note on why each home made the cut. ## Safety checks (share these with the user) - Check every figure, price and total against your own records before anything is sent, posted or booked. A person approves refunds, discounts, payments and price changes. - Remove names, contact details, account numbers and other personal data the task doesn't need before you paste, and check your AI tool's data and training settings. - Read and edit the draft before it reaches a customer or goes public. If you later automate this prompt, start with "draft and notify me", not "send automatically". - Check names, dates, numbers and any claim against your own source material before you use the answer. AI can misread or invent details. - Say clearly which parts need a person to review or approve before anything is sent, paid, posted or filed. ## About this skill - Works with: Claude, Claude Memory, Flexmls MCP, MLS - Based on this real-world example: https://realestateusecases.com/u/buyer-concierge-flexmls-claude-memory/ - Free prompt from AgentPlaybook Real Estate: https://agentic-library.netlify.app/prompt/al-554-stop-rerunning-the-same-mls-search-for-every-buyer-save-each/ - To install in an agent that supports Agent Skills, save this file as SKILL.md in a folder with the same name as `name` above (for example in your skills directory). Install steps for Claude.ai, Claude Code, Cursor and Codex: https://agentic-library.netlify.app/skills/