com.hasdata/redfin
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@com.hasdata/redfinSearch for 3-bedroom homes for sale in Austin, TX under $500k"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Redfin MCP Server
A hosted Model Context Protocol (MCP) server that gives Claude, Cursor, Windsurf and any other MCP client two read-only Redfin tools. Search for-sale, for-rent and sold listings with the filter set Redfin shows a visitor, and read one property page in full, both as structured JSON, with no MLS licence and nothing to host.
It reads public Redfin pages that a signed-out visitor can see.
1,000 free credits every month, no card required, which is 200 Redfin calls at the 5-credit rate.
https://mcp.hasdata.com/api/mcp?apis=redfin
Contents
Related MCP server: Zillapi - Zillow Property Data
What you need
An MCP client and a HasData API key from the dashboard, free to create with no card, and the free tier covers about 200 calls a month at the 5-credit rate. This is a remote server, so the simplest path is a URL and an x-api-key header, with no container to run. A client that only speaks stdio reaches it through a thin launcher, published as @hasdata/redfin-mcp on npm and hasdata-redfin-mcp on PyPI, shown below.
Quick start
The server URL is the same for every client. We run it hands-on in Claude Code and Claude Desktop. The other blocks follow each client's own documented format for a remote server.
Field | Value |
URL |
|
Transport | HTTP, streamable |
Auth header |
|
Clients with OAuth support can add the same URL as a connector and sign in without putting a key in a config file.
claude mcp add --transport http redfin "https://mcp.hasdata.com/api/mcp?apis=redfin" \
--header "x-api-key: HASDATA_API_KEY"Settings, then Connectors, then Add custom connector, then paste https://mcp.hasdata.com/api/mcp?apis=redfin and sign in.
For the config-file route, Claude Desktop loads only local (stdio) servers, so it reaches a remote server through a stdio launcher. The @hasdata/redfin-mcp package is that launcher, and it reads the key from the environment. Add this to claude_desktop_config.json:
{
"mcpServers": {
"redfin": {
"command": "npx",
"args": ["-y", "@hasdata/redfin-mcp"],
"env": { "HASDATA_API_KEY": "YOUR_KEY" }
}
}
}For Python instead of Node, swap the launcher for the PyPI package, which uvx runs without a manual install:
{
"mcpServers": {
"redfin": {
"command": "uvx",
"args": ["hasdata-redfin-mcp"],
"env": { "HASDATA_API_KEY": "YOUR_KEY" }
}
}
}~/.cursor/mcp.json for every project, or .cursor/mcp.json for one:
{
"mcpServers": {
"redfin": {
"url": "https://mcp.hasdata.com/api/mcp?apis=redfin",
"headers": { "x-api-key": "HASDATA_API_KEY" }
}
}
}~/.codeium/windsurf/mcp_config.json. Windsurf calls the field serverUrl, not url:
{
"mcpServers": {
"redfin": {
"serverUrl": "https://mcp.hasdata.com/api/mcp?apis=redfin",
"headers": { "x-api-key": "HASDATA_API_KEY" }
}
}
}.vscode/mcp.json in the workspace:
{
"servers": {
"redfin": {
"type": "http",
"url": "https://mcp.hasdata.com/api/mcp?apis=redfin",
"headers": { "x-api-key": "HASDATA_API_KEY" }
}
}
}Example prompts
Each of these lands on one tool, or on two in sequence when the second needs the URL the first returns.
Find three-bedroom houses for sale in 78741 under $500,000 and sort them by price per square foot.
What sold in Austin in the last three months, and how does that compare with what is listed now?
Pull the full property page for this Redfin URL and summarise the condition from the description.
Which rentals in Austin allow dogs and include in-unit laundry?
Show me for-sale homes in the Austin Independent School District where the assigned elementary school rates 8 or better.
Find fixer-uppers built before 1970 in this zipcode that have been on Redfin more than 30 days.
A prompt that names a market goes to the search tool. A prompt that hands you a Redfin URL goes straight to the property tool. Searching for a full street address is a third case, covered below, because it answers with one property rather than a list.
Tools
Two tools, 5 credits per successful call.
Get Redfin real estate listings
hasdata_redfin_listing_getRealEstateListings
A page of listings for a location, or one property when the location is a single address.
Two parameters are required, and the rest of the schema mirrors Redfin's own filter panel.
Parameter | Type | Required | Notes |
| string | yes | A zipcode, city, neighborhood, school, school district, apartment building name, or a full street address |
| string | yes |
|
| string |
| |
| number | Result page, starting at 1 |
The filters are named after the nested structure Redfin uses internally, flattened with underscores, so they have to be passed exactly as the schema spells them. price_min_ and price_max_ are the price band, beds_min_ and beds_max_ the bedroom count, monthlyPayment_interestRate_ a mortgage assumption. A doubled underscore marks an array.
The ones worth knowing:
Parameter | Type | Notes |
| number | Price band |
| number | Bedroom count |
| string | Minimum baths, |
| array |
|
| array |
|
| array |
|
| string |
|
| string | Sold window, from |
| string | A year from a fixed ladder, |
| string | Floor area from a fixed ladder, |
| string |
|
| number | Maximum monthly HOA fee |
| string |
|
| array |
|
| string |
|
| string | Free text against the listing description |
| number | Minimum GreatSchools rating, 1 to 10 |
| number | Minimum walk score, 1 to 100 |
| array |
|
| array |
|
| string |
|
A market search returns searchInformation with totalResults, a properties array of 40, and pagination with currentPage, nextPage and an otherPages map. A for-sale or sold property carries id, mlsId, url, homeType, status, price, beds, baths, area, yearBuilt, daysOnSite, addressRaw, a parsed address, latitude, longitude, description, atAGlanceFacts and photos.
{
"id": 31625298,
"mlsId": "2190201772333567097",
"url": "https://www.redfin.com/TX/Austin/1721-Deerfield-Dr-78741/home/31625298",
"homeType": "House",
"status": "FOR_SALE",
"price": 675000,
"beds": 3,
"baths": 2,
"area": 1667,
"yearBuilt": 1963,
"daysOnSite": 0,
"addressRaw": "1721 Deerfield Dr, Austin, TX 78741",
"address": { "street": "1721 Deerfield Dr", "city": "Austin", "state": "TX", "zipcode": "78741" },
"latitude": 30.231372,
"longitude": -97.734893,
"atAGlanceFacts": [
{ "factLabel": "Property Type", "factValue": "Single-family" },
{ "factLabel": "Year Built", "factValue": "1963" },
{ "factLabel": "Price/Sq.Ft.", "factValue": "$405" }
]
}A rental is a building rather than a home, so type: forRent returns a different shape. price, beds, baths and area each become a { min, max } object across the available units, and the entry adds propertyName, availableUnits, agentEmail and agentPhone while dropping mlsId, homeType, yearBuilt and daysOnSite.
{
"id": "31510362",
"propertyName": "The Sonata",
"status": "FOR_RENT",
"availableUnits": 12,
"price": { "min": 745, "max": 1300 },
"beds": { "min": 1, "max": 2 },
"baths": { "min": 1, "max": 2 },
"area": { "min": 474, "max": 976 },
"addressRaw": "1070 Mearns Meadow Blvd, Austin, TX 78758"
}Get Redfin property details
hasdata_redfin_property_getPropertyDetails
One property page in full, by its Redfin URL.
Parameter | Type | Required | Notes |
| string | yes | The Redfin property URL, as the search tool returns it |
Returns a property object. On top of everything the search result carries, it adds propertyDetails, schools, nearby, agentInfo, viewsActivity, openHouseSchedule, updatedAt, a geo object and the full photos collection, which ran to 61 images on the property below.
propertyDetails is the specification block, grouped into parking, interior, exterior, utilities and publicFacts. Each group is an array of labelled sections, and each section is an array of label and value pairs, so it reads as the page presents it rather than as a typed object. Look up a fact by its label instead of by position.
schools.assignedSchools carries the catchment schools with greatSchoolsRating, parentRating, distanceInMiles and a servesHome flag, which is the field that says whether the school actually serves this address.
{
"id": 31625298,
"homeType": "Single Family Residential",
"status": "COMING SOON",
"price": 675000,
"beds": 3,
"baths": 2,
"area": 1667,
"yearBuilt": 1963,
"geo": { "latitude": 30.231372, "longitude": -97.734893 },
"updatedAt": "Sep 9, 2026 4:04 AM",
"viewsActivity": { "views": 98, "favorites": 5 },
"agentInfo": {
"agentName": "Lilly Rockwell",
"agentPhoneNumber": "512-413-1975",
"brokerName": "Compass",
"brokerPhoneNumber": ""
},
"propertyDetails": {
"parking": [{ "parkingInformation": [{ "label": "Has Garage", "value": "yes" }] }],
"utilities": [{ "utilitiesInformation": [{ "label": "Has Air Conditioning", "value": "yes" }] }]
},
"schools": { "assignedSchools": [{ "greatSchoolsRating": 6, "parentRating": 5, "servesHome": true }] }
}Errors and failure paths
Plan for these rather than assuming a happy path.
soldWithinOption is currently broken and silently returns for-sale homes labelled SOLD. Passing any of its values puts the value straight into the Redfin filter, Redfin does not recognise it, and the response is the active for-sale list with status stamped as SOLD. Every listing came back identical to the plain for-sale search in our checks. Leave the parameter off. type: sold on its own works correctly and covers the last three months, which is Redfin's own default window.
The search tool returns three different shapes, and which one you get depends on the keyword. A market keyword answers with searchInformation, properties and pagination. A full street address or a named building answers with a single property object and no properties array, no searchInformation and no pagination. A rental search answers with the range-shaped entries shown above. Branch on the presence of properties before you iterate it.
totalResults tops out at 350, and that is a ceiling rather than a count. Austin and New York both report 350 while a single zipcode reports 168 and a small town 57. Pagination stops at nine pages of 40. To enumerate a large market, slice it by zipcode, price band or home type instead of paging, because there is no page ten.
Sold search does not give you sold prices as a separate field. price holds whatever the page shows for that status, so a for-sale price and a sold price arrive in the same field. Read status alongside it every time.
There is no price history, tax history or Redfin Estimate in the property response. Those sit on the page but are not in what the tool returns today. What you get instead is propertyDetails.publicFacts, which carries the assessor-style facts as label and value pairs.
nearby.pointsOfInterest is nearby places, not comparable sales. Its categories come from a third-party places dataset and are frequently wrong, so a title loan office can arrive tagged as a bar. Use the names and coordinates, and do not trust the category.
openHouseSchedule can be an array holding an empty object when the page has the section but no dates in it. Test the contents, not the length.
brokerPhoneNumber and other agent fields come back as empty strings rather than null. Treat empty string as absent.
Results that carry data also carry a requestMetadata.id worth quoting in support.
Pricing, free tier and limits
Each Redfin tool costs 5 credits per successful call. Response size does not change the price, so a 40-listing page and a single property cost the same.
The free tier is 1,000 credits every month with no card, which is 200 Redfin calls at the base rate. It renews with the billing cycle, so a low-volume agent runs on the free tier indefinitely.
Paid plans start at $49 a month for 200,000 credits, which is 40,000 calls. The unit price falls with volume, from $1.23 per 1,000 calls on the entry plan to $0.50 on Business, $0.42 on Growth and $0.37 on the largest high-volume plans.
Your plan also sets concurrency. The free tier allows 1 request at a time, Startup 15, Business 30, Growth 50, and the high-volume plans run from 200 to 1,500. Handle the overflow case defensively in anything unattended, because an agent that walks a list of properties will reach the ceiling before you do.
A request that comes back non-200 is not billed. A successful call that finds nothing is still a call.
Tool selection
Start from what the prompt gives you. A market, a zipcode or a school district goes to the search tool. A Redfin URL goes straight to the property tool. Spending a search call to reach a URL you already have is the most common waste.
Then pick by depth. The search result is enough for ranking, price sweeps and market summaries, and it already carries price, beds, baths, area, year built and days on site. The property tool is the only one that returns the specification block, the assigned schools and the listing agent, and it is worth one call per property you actually care about rather than one per row.
Filter server-side. The schema mirrors Redfin's filter panel precisely, so a query like "three beds, under $500k, built before 1970, in this zipcode" is one call with four parameters, not a page sweep followed by local filtering.
How it compares
There is no public Redfin API, so the real alternative is an MLS or IDX feed.
MLS or IDX feed | This server | |
Eligibility | A licensed brokerage or an agent relationship | An API key |
Setup | Per-MLS application, contract and compliance review | One header |
Coverage | One MLS per feed, hundreds nationally | Whatever Redfin publishes, in one place |
Sold data | Full history where the MLS permits it | The recent window Redfin shows |
Rentals | Often a separate feed or absent | The same tool, with a range shape |
Redistribution | Contractually restricted | Your responsibility to check |
Cost | Setup fees plus monthly, per MLS | Paid past the free tier, 5 credits a call |
The row that decides it is eligibility. An MLS feed is the authoritative source and it needs a licence you cannot buy as a developer, which rules it out for research, prototypes and anything an agent does on your behalf. When you are a brokerage with a feed already, the feed is more complete and more current, and you should use it.
FAQ
Is there an official Redfin MCP server?
Redfin does not publish one, and it does not publish a public API either. This one is maintained by HasData and reads public Redfin pages.
What is a Redfin MCP server?
An MCP server exposes tools an AI client can call. This one turns Redfin search results and property pages into JSON an agent can reason over, without a browser or a scraping library in your stack.
Do I need an MLS licence or a Redfin account?
No. The only credential is your HasData key.
Why does searching an address return one property instead of a list?
Because Redfin resolves a full street address to that property's page rather than to a result set. The tool passes that through, so the response holds a single property object in the same shape the property tool returns. It is a useful shortcut when you have an address but not a URL.
How do I pull every listing in a city?
You cannot, in one sweep. Redfin caps a result set at 350 across nine pages, so a large market has to be cut into smaller queries by zipcode, price band or home type, and the slices stitched together.
Can I filter sold listings by date?
Not reliably right now. type: sold works and returns Redfin's default three-month window, but soldWithinOption is not being translated into a filter Redfin accepts, and passing it returns active listings labelled SOLD. Leave it off until that is fixed.
Does it cover rentals?
Yes, through type: forRent. Expect the range shape rather than the single-home shape, because a rental result is a building with several available units.
Can I use this together with other HasData APIs?
Yes. One key covers everything, and one endpoint serves them all through the apis parameter. Point a client at ?apis=redfin,zillow to get both tool sets in one connection, or at mcp.hasdata.com/api/mcp for the full catalogue.
Is HasData affiliated with Redfin?
No. HasData is an independent service and is not affiliated with, endorsed by, or sponsored by Redfin. Redfin is a trademark of its respective owner. The tools work with publicly available data only, and you are responsible for using the results in line with Redfin's terms and the law that applies to you.
Compliance and personal data
Listings carry agent contact details. A for-sale property returns agentInfo with a name and a direct phone number, and a rental returns agentEmail and agentPhone. Those belong to identifiable people, published in a professional capacity, which does not take them out of scope of the GDPR or the CCPA. Marketing to them is regulated separately again, and real estate agents are a common target of exactly that, so check your obligations before you build a contact list. Market analysis does not need those fields at all.
HasData links
Redfin Scraper API, the REST endpoints behind these tools
Other HasData MCP servers: Google Search, Google Maps, Google Trends, Google Flights, DuckDuckGo, YouTube, TikTok, Instagram, Amazon, Shopify, Yelp, Zillow, Airbnb, Booking.com, Indeed.
Development
The launcher is a thin stdio bridge to the remote server, so there is nothing to build.
npm install
HASDATA_API_KEY=your_key_here npm testThe tests in test/ assert the tool contract, the part that can break without a commit here. They check that ?apis=redfin returns the expected tool count, that no name changed, that every tool still declares its required parameters and carries a description, that the filter enums this README documents are still the ones the schema offers, and that the key in use is actually accepted. That last check calls a tool for real and costs 5 credits, which is the price of a canary that can fail for the right reason.
The contract suite also runs weekly on a schedule, because the upstream tool list can change without anyone touching this repository.
Contributing
A tool table, a response sample or a documented behaviour that does not match reality is worth an issue. There is a template for exactly that. Pull requests are welcome for the same, and for anything in the launcher.
License
MIT, see LICENSE.
Available Tools
2 toolshasdata_redfin_listing_getRealEstateListingsredfin_listing: GET /AInspect
Get Redfin Real Estate Listings
Searches Redfin for-sale, for-rent, or sold listings with pagination. The location accepts a zipcode, city, neighborhood, school, school district, apartment-building name, or a full street address. Returns each listing with address, Redfin URL, list price, beds/baths, square footage, lot size, year built, days on market, status, coordinates, photos, MLS number, and HOA; an address or building returns a single property card instead. Use for real-estate market research, lead generation for agents, price/DOM trend analysis, and feeding URLs into the Redfin Property endpoint for deep-dive details.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | The page number of the results to retrieve. | |
| sort | No | The sorting option for the search results. | |
| type | Yes | The type of listing. | |
| baths | No | The minimum number of bathrooms. | |
| pets__ | No | An array of pet types allowed. | |
| keyword | Yes | The location to search for listings. Accepts a zipcode (`33321`), a city (`Austin` or `Austin, TX`), a neighborhood (`East Austin`), a school (`BASIS Austin`), a school district (`Austin Independent School District`), an apartment building by its name (`Maizon Brickell`), or a full street address (`5805 Woodview Ave, Austin, TX 78756`), including a single unit (`221 SW 12th St Unit 1716, Miami, FL`). An address or a building returns a single property card instead of a list of listings, and the `type` parameter does not apply to it. | |
| beds_max_ | No | The maximum number of bedrooms. | |
| beds_min_ | No | The minimum number of bedrooms. | |
| cost_hoa_ | No | The maximum monthly Homeowners Association (HOA) fee. | |
| moveInDate | No | The desired move-in date in MM/DD/YYYY format. | |
| price_max_ | No | The maximum price of the listing. | |
| price_min_ | No | The minimum price of the listing. | |
| homeTypes__ | No | An array of home types to filter the listings. Allowed values depend on the listing `type`. | |
| lotSize_max_ | No | The maximum lot size. | |
| lotSize_min_ | No | The minimum lot size. | |
| stories_max_ | No | The maximum number of stories. | |
| stories_min_ | No | The minimum number of stories. | |
| timeOnRedfin | No | How long the listing has been on Redfin. | |
| yearBuilt_max_ | No | The maximum year the property was built. | |
| yearBuilt_min_ | No | The minimum year the property was built. | |
| statusOptions__ | No | An array of listing statuses. | |
| soldWithinOption | No | Filter sold listings by how recently they were sold. | |
| rentalAmenities__ | No | An array of rental amenities to filter the listings. | |
| cost_priceReduced_ | No | Filter listings by when the price was reduced. | |
| rentalOtherTerms__ | No | An array of additional rental terms. | |
| monthlyPayment_max_ | No | The maximum monthly payment. | |
| monthlyPayment_min_ | No | The minimum monthly payment. | |
| schools_schoolType___ | No | An array of school types. | |
| forSaleSquareFeet_max_ | No | The maximum square footage for for-sale listings. | |
| forSaleSquareFeet_min_ | No | The minimum square footage for for-sale listings. | |
| homeFeatures_basement_ | No | The basement type. | |
| homeFeatures_poolType_ | No | The type of pool. | |
| cost_acceptedFinancing_ | No | The accepted financing type. | |
| cost_excludeLandLeases_ | No | If set to true, listings with land leases will be excluded. | |
| cost_pricePerSqft__max_ | No | The maximum price per square foot. | |
| cost_pricePerSqft__min_ | No | The minimum price per square foot. | |
| homeFeatures_options___ | No | An array of home feature flags to filter the listings. | |
| listingType_category___ | No | An array of listing categories. | |
| onlyWithDealOrPromotion | No | If set to true, only listings with a deal or promotion will be included. | |
| exclude55PlusCommunities | No | If set to true, 55+ communities will be excluded. | |
| forRentSquareFootage_max_ | No | The maximum square footage for for-rent listings. | |
| forRentSquareFootage_min_ | No | The minimum square footage for for-rent listings. | |
| schools_greatSchoolRating_ | No | The minimum GreatSchools rating (1-10). | |
| transportScores_bikeScore_ | No | The minimum bike score (1-100). | |
| transportScores_walkScore_ | No | The minimum walk score (1-100). | |
| cost_maxPropertyTaxPerYear_ | No | The maximum property tax per year. | |
| homeFeatures_keywordSearch_ | No | A free-text keyword search applied to listing descriptions. | |
| openHouseAndTour_openHouse_ | No | Filter listings with an open house. | |
| openHouseAndTour_videoTour_ | No | If set to true, only listings with a video tour will be included. | |
| homeFeatures_garageSpotsMin_ | No | The minimum number of garage spots. | |
| monthlyPayment_interestRate_ | No | The mortgage interest rate (percent) used to calculate the monthly payment. | |
| monthlyPayment_mortgageTerm_ | No | The mortgage term used to calculate the monthly payment. | |
| monthlyPayment_insuranceRate_ | No | The home insurance rate (percent) used to calculate the monthly payment. | |
| transportScores_transitScore_ | No | The minimum transit score (1-100). | |
| listingType_excludeShortSales_ | No | If set to true, short sales will be excluded. | |
| schools_includeUnratedSchools_ | No | If set to true, unrated schools will be included. | |
| listingType_redfinListingsOnly_ | No | If set to true, only Redfin-listed properties will be included. | |
| monthlyPayment_downPaymentAmount_ | No | The down payment as an absolute amount. | |
| monthlyPayment_downPaymentPercent_ | No | The down payment as a percentage of the home price. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the disclosure burden. It discloses pagination, the accepted keyword forms, the full set of returned listing fields, and the important behavioral exception that an address/building returns a single property card and ignores `type`. Rate-limit and error behavior are absent, but the core behavioral surface is well covered.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Four dense, front-loaded sentences with no filler: action and pagination first, then location semantics, return fields/exception, and use cases. It is well sized for a 59-parameter tool because the schema carries the detailed filter documentation.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite no output schema and no annotations, the description compensates by naming the main returned fields and explaining the single-property-card case. For a large search tool, the use cases and sibling routing make it reasonably complete, though it omits pagination-count/default behavior and error-handling expectations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The narrative mostly re-states the `keyword` semantics and the `type` exception that already exist in the schema, and it adds no new information about `page`, `sort`, or the other filter parameters. It therefore earns no bonus beyond the well-documented schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific, verb-driven statement: 'Searches Redfin for-sale, for-rent, or sold listings with pagination,' and enumerates the location forms and return fields. This makes the listing-search scope unmistakable and differentiates it from the single-property sibling endpoint.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It gives concrete use cases ('real-estate market research, lead generation for agents, price/DOM trend analysis') and points to the 'Redfin Property endpoint' for deep-dive details, effectively routing an agent to the sibling after this search step. It does not phrase this as a hard when-not-to-use rule, but the guidance is unambiguous enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
hasdata_redfin_property_getPropertyDetailsredfin_property: GET /AInspect
Get Redfin Property Details
Fetches the full Redfin property page by URL. Returns address, list/sold price, price history, Redfin Estimate, beds/baths, square footage, lot size, year built, property type, HOA, days on market, school ratings, tax history, listing agent, full description, photos, walk/transit/bike scores, and nearby comparables. Use for CMA reports, investor due-diligence, valuation models, listing enrichment, and powering buyer-assistant agents with verified property facts.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The URL of the property on Redfin. Must be a valid Redfin property URL. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavioral traits. It only says it 'fetches' and returns data, but does not address authentication, rate limits, error behavior, or what happens with invalid URLs. This leaves the agent without operational expectations beyond the basic return field list.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with the core action and includes no filler. The list of returned fields and use cases is lengthy but informative; however, it could have been trimmed slightly without losing essential guidance, so it does not earn a perfect score.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple one-parameter fetch tool with no output schema, the description covers the input, the returned data, and common use cases, which is largely sufficient for correct invocation. It falls short of complete because behavioral caveats such as rate limits and error handling are missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single parameter 'url' is fully described in the schema with 100% coverage, so the schema already provides the needed semantics. The description adds no further format, examples, or constraints beyond what the schema states, justifying the baseline score of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states a specific action and resource: 'Fetches the full Redfin property page by URL' and lists the many fields it returns. However, it never explicitly contrasts itself with the sibling listing tool, so the distinction is left to inference rather than stated outright.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly lists use cases: 'Use for CMA reports, investor due-diligence, valuation models, listing enrichment, and powering buyer-assistant agents.' This gives clear context for when the tool is appropriate, but it does not mention when not to use it or point to the sibling tool as an alternative.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
2 tool updates
v1.0.0- First observed
hasdata_redfin_listing_getRealEstateListings - First observed
hasdata_redfin_property_getPropertyDetails
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: one searches for listings, the other fetches details for a specific property. An agent would not confuse them because they operate on different resource types and return different data.
Both tools follow the hasdata_redfin_<resource>_get<Detail> pattern, which is consistent. The first tool's name is slightly redundant ('listing_getRealEstateListings') but still predictable and aligned with the second tool.
With only two tools, the server feels minimal but not unreasonable. It covers the two most common Redfin needs (search and property details), yet the surface is thin compared to typical MCP servers that include more resource endpoints.
The pair covers the essential workflow: search listings, then dive into property details. Missing operations like agent search or market stats are non-critical, and the property details endpoint includes comparables and price history, so there are no obvious dead ends.
Maintenance
Related MCP Connectors
Redfin listings, sale-comps, and neighborhood market data via natural-language queries.
Zillow for-sale, for-rent and sold listings, and full property details, as structured JSON.
RealEstateAPI MCP — property search, detail, and skip-trace (realestateapi.com)
Property Records MCP — address-level US property records (sales history,
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables users to search Airbnb listings with advanced filtering options and retrieve detailed property information through an MCP server interface.22,043MIT
- AlicenseNot gradedqualityBmaintenanceREST API and MCP server for Zillow property data: Zestimates, rent estimates, tax records, listing search, price history, photos, and 300+ fields. 4 tools with OAuth 2.1 + PKCE. Free tier: 100 credits.6MIT No Attribution
- AlicenseAqualityAmaintenanceEnables natural language access to Redfin real estate data, including property search, details, photos, market reports, price history, climate risk, and saved homes/searches, by routing requests through your own signed-in browser session.216393MIT
- AlicenseNot gradedqualityBmaintenanceUnofficial MCP server that exposes PropertyGuru Singapore & Malaysia property listing search as MCP tools, returning detailed listing data without an API key.MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/HasData/redfin-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server