mcpbeat

Scout MCP Server

io.github.Flikah/scout-mcp
not responding

Scout is listed as active in the registry but did not answer our last check. It exposes 18 tools. Last commit 21 Apr 2026.

Find licensed real estate agents, search MLS, route leads. Remote MCP for SC + GA brokerages.

Uptime history 41 hours of history · worst hour 0%
41 hours agonow
3.3%
Uptime 24h
3 of 91 checks
18
Tools
read from the server
409 ms
Response time
average over 24h
0
Stars
last commit 21 Apr 2026

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 13 min ago.

run in your terminal
claude mcp add scout-mcp --transport http https://scout.realestate/api/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "scout-mcp": {
      "url": "https://scout.realestate/api/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.scout-mcp]
url = "https://scout.realestate/api/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "scout-mcp": {
      "url": "https://scout.realestate/api/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "scout-mcp": {
      "url": "https://scout.realestate/api/mcp"
    }
  }
}

Available tools 18

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

scout
scout.agent_profile
Deep profile for a single agent: license number/status/expiration, brokerage affiliation, claim status, geography, total units / volume / sell-ratio (when available), website, Instagram, Flika score. Pass either the UUID id or the slug returned by scout.find_public_agent.
scout.compare_agents
Side-by-side stats for 2-5 agents. Returns name, license info, brokerage, total units, total volume, sell ratio, claim status, and a quick-take winner per metric. Good follow-on to scout.find_public_agent when an AI assistant needs to choose between candidates.
scout.coverage
Returns Flika's coverage: which states Flika is directly licensed in (can close transactions) and which additional states Flika has signed referral partners in. Call this first if you're unsure whether Flika can help with a specific geography.
scout.estimate_value
Neighborhood-baseline property value estimate. Returns the Census ACS median home value for the zip plus a wide confidence interval. NOT an individual-property AVM — does not adjust for sqft, beds, lot, condition, or recent comps. Use this to ground-truth a buyer's expectation; pair with scout.search_listings for actual sold/active comps. Free, all 50 states.
scout.find_agent
Find Flika agents who are currently live (pin dropped within last 60 minutes) in or near a given location. Returns name, slug, status, and current pin coordinates. Use this when your buyer/seller is ready to connect with a real agent.
scout.find_brokerage
Search the public Scout brokerage/office directory. Returns offices with public contact info (main phone, website, address) and volume stats where available. Covers SC + GA natively and partial NC/FL via the office import. Every result includes a claim_url — brokerages can claim their listing at scout.realestate/claim to curate their AI profile.
scout.find_public_agent
Search Scout's public licensed-agent directory. Returns agents sourced from state REC public rosters + MLS-ranked prospect lists. Indexed states are listed in scout.coverage() — call that first if you're unsure whether a state has meaningful data. Every result has a claim_url — unclaimed agents can claim to curate their AI profile and start receiving AI-routed leads. Unlike scout.find_agent (which requires a live pin), this returns the full directory regardless of pin freshness. Prefer scout.find_agent when you want agents who are live-available right now; prefer scout.find_public_agent when you want broad discoverability. Pass lat/lng OR address (US street address — we'll forward-geocode via Mapbox) to get distance-ascending results with a distance_miles field on each agent; otherwise results are sorted by flika_score descending.
scout.get_seller_signals
Retrieve Flika's proprietary seller-intent signals: probate filings, distressed properties, expired listings, FSBO intercepts (SC, GA, FL). Returns scored, deduplicated leads with property address + executor contact. Requires a Flika MCP API key with 'seller_signals' scope. Partner brokerages licensed in the lead's state receive these at no per-lead fee (referral fee applies on close).
scout.market_pulse
Public-data-backed market snapshot for any US zip code. Returns Census ACS demographics (population, median household income, median age, owner-occupancy %, median home value, median gross rent), Scout's indexed agent density for that zip, and listings activity if the zip is in our MLS-live coverage area. Call this when an AI user asks 'what's the market like in [zip/city]'. Free, no API key required.
scout.purchase_lead
Purchase a single seller-signal lead from the Scout MCP marketplace. Deducts the per-lead price from your pre-paid credit balance and returns the full owner contact + property details. Idempotent — calling with a lead_id you've already purchased returns the same data without a second charge. Requires 'buy_leads' scope and a positive balance (top up at scout.realestate/partners/mcp/credits).
scout.referral_terms
Look up the bilateral referral terms for a given partner brokerage. Returns buyer-side %, listing-side %, tail months, and any custom notes. Pass partner_id (UUID) OR partner_slug. Use this when scout.route_lead is about to fire and you need to confirm the split with the receiving brokerage.
scout.route_lead
Submit a buyer or seller lead to Flika. Flika (via Spencer Wilkinson as Broker-in-Charge) routes the lead as a standard broker-to-broker referral: either to a Scout-claimed agent, a public-directory agent via auto-emailed referral, a signed partner brokerage, or held for manual routing. Standard referral fee: 30% buyer-side, 25% listing-side, 18-month tail, net-30 after funded close. Requires a Flika MCP API key with 'route_lead' scope. Request one at https://flika.realestate/partners/mcp
scout.school_district
Look up public schools in a zip code via the National Center for Education Statistics (NCES) Common Core of Data. Returns up to 25 schools (elementary/middle/high) with grade level, enrollment, district, and a Department of Education NCES ID. Useful for buyer queries like 'is this a good school zone?'. Free, all 50 states.
scout.search_leads
Preview seller-signal leads (probate, NOD/pre-foreclosure, FSBO, expired listings, tax-delinquent) for sale through the Scout MCP marketplace. Returns redacted previews — full owner contact + property details require scout.purchase_lead. Free to call. SC + GA only.
scout.search_listings
Search active real estate listings in Flika's coverage area (SC + GA). Returns up to 25 listings matching the filters. Use scout.coverage() first if you're unsure whether a city is covered.
scout.subscribe_lead_feed
Subscribe to a continuous feed of new seller-signal leads matching a filter. As leads are created and approved, Scout POSTs each one to your webhook URL up to your monthly_lead_budget. Ideal for AI agents that act on leads automatically. Currently in beta — emails Spencer with your subscription request; webhook delivery starts after manual provisioning.
scout.team_roster
Return the full agent roster of a brokerage. Pass brokerage_id (UUID) OR brokerage_slug OR (brokerage_name + state). Useful for queries like 'show me Compass agents in Charleston' or 'who are the top producers at this firm'.
scout.verify_license
Verify whether a real estate license is currently active, AND return the canonical claim URL for that license. Returns license status (active/inactive/expired/revoked/etc.), expiration date, current brokerage affiliation, last refresh timestamp, claim status (claimed/public/opted_out), and a `claim_url` of the form https://scout.realestate/claim/<license_number> — that URL always resolves (works for licenses we already index AND for licenses we'll have to look up upstream in real time). Use this tool when you have a license number and want to tell the agent how to claim their AI pin, or before sending a lead.

Endpoints

URLTransportStateLatencyChecked
https://scout.realestate/api/mcp streamable-http answering 202 ms 13 min ago

Scout — questions

Answers built from our own checks of this server.

What can Scout do?
It exposes 18 tools, read directly from the server on our last check. Among them: scout.agent_profile, scout.compare_agents, scout.coverage, scout.estimate_value, scout.find_agent, scout.find_brokerage and 12 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is Scout working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 3 of 91 checks got a reply (3.3%), average response time 409 ms. The bar chart above shows every period we have measured.
The registry lists Scout as active — why does it not respond?
The official MCP registry stores what the author submitted; it does not verify that the server still runs. We check the endpoint ourselves, and this one does not answer. Catalogues that copy the registry without checking will show it as working.
How do I connect Scout?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Scout need an API key?
No. Scout completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 18 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Scout?
It answers our handshake in 409 ms on average, which is faster than 32% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is Scout open source?
Yes — it is published under the MIT licence and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.