Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Neighbourhood and home evidence for England, London in depth: prices, rents, schools, crime, travel.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://getcloseknit.com/mcpRun this in your terminal
claude mcp add --transport http close-knit https://getcloseknit.com/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"close-knit": {
"url": "https://getcloseknit.com/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"close-knit": {
"type": "http",
"url": "https://getcloseknit.com/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
ChatGPT connects only to servers on the internet:
https://getcloseknit.com/mcpMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Tool names and descriptions exactly as the server reported them on Nov 6, 2026. The maker wrote them, not us; we show them as plain text.
find_areasShortlist neighbourhoods in England (London in depth) for a household: budget, bedrooms, weighted priorities (crime, station access, price level, official deprivation decile, noise, disorder, energy rating, leasehold share, good primaries) and optional stations or local authoriti
open_shared_searchOpen a search the user shared from the Close Knit site (a link with #profile=v1., v2. or v3.): their budget, priorities, places (gym, work, schools…), liked and ruled-out areas and private notes, re-ranked now with the same shortlist as find_areas. Use it when the user pastes suc
find_similar_areasNeighbourhoods like one the user liked (crime, deprivation, income, price level and station access percentiles), optionally only cheaper ones (cheaper_by_percent lower £/m², crime no more than 10 points worse) and within max_budget for bedrooms: 'like this but cheaper / elsewhere
get_area_overviewMoved: use get([id]). Answers until 2026-11-30.
assess_listingCheck one listing the user found against local evidence: asking price vs the same home type's recorded £/m² (with floor area or a bedroom-based ballpark) or median price, the LSOA then its MSOA (all types only as indicative-only), typicalPrice, a flood line, turnover, growth, the
describe_dataThe map of Close Knit's data; call it first, and whenever you are unsure of a metric, path or category name. No arguments: a summary (themes with metric counts and 2-3 headline metrics, Census in one line, places in one line, the entity kinds). theme='crime' lists that theme's me
getEverything about 1-10 things by typed id: uk:lsoa:E01…, uk:msoa:E02…, uk:lad:E09…, uk:rgn:E12…, sector:e17-4, pc:E17 4PP, uprn: , school: , place:osm:n123 (search_places finds ids from names), or a guide article, guide:crime, in a call of its own (describe_data(kind: 'guide') lis
queryAnalyse many areas or schools with a JSON query (never SQL). kind='area' (default): level lsoa, msoa, lad or rgn; scope england, london, a region or typed area ids; filters by value {metric, min, max}, percentile in scope {metric, pct_min}, vs the scope's reference {metric, vs: a
get_placesThe places themselves (2.58 m: shops, gyms, cafes, parks, pubs, GPs, ... in 234 categories) near a typed id or {lat, lon} (radius_m 100-3000) or inside an area, by category (describe_data(kind: 'place') lists them) and brand (PureGym, Waitrose). Each: name, category, brand, metre
list_metricsMoved: use describe_data(). Answers until 2026-11-30.
search_areasMoved: use search_places(q). Answers until 2026-11-30.
get_area_metricMoved: use get([id], select: ["layers. "]). Answers until 2026-11-30.
rank_areas_by_metricMoved: use query(saved: "metric: "). Answers until 2026-11-30.
get_address_historyMoved: use get(["uprn:…"], select: ["history"]). Answers until 2026-11-30.
get_home_pricesMoved: use get(["uprn:…"]). Answers until 2026-11-30.
match_areasScore every area against a household's ordered criteria (preference-profile.v2: budget, ranges on any map layer, places, where zones, own criteria; must = filter). Returns a match-pack.v2 with the best top_n (default 20, max 100) areas as a list with score, rank and percentile pe
get_market_depthMoved: use get([id], select: ["market"]). Answers until 2026-11-30.
get_nearby_sales_summaryMoved: use get(["uprn:…"], select: ["nearby-sales"]). Answers until 2026-11-30.
get_area_evidence_packMoved: use get([id], sections: ["pack"]). Answers until 2026-11-30.
search_placesResolve a place the user mentions (station, borough, neighbourhood, postcode, street) to ids. Station lookup forgives spelling (Kings Cross, St James Park, Elephant and Castle) and knows London codes and nicknames (KX, TCR, LST, E&C, ally pally). Returns stations (osm:…, with TfL
get_commuteDoor-to-door minutes from one neighbourhood to the user's places on a weekday morning, by public transport (R5 on TfL timetables), bike (at the speed Santander Cycles riders reach; checked against TfL), car (typical morning traffic, no parking) and walking, each with a range. Pla
get_flood_riskMoved: use get([pc | uprn | id], select: ["flood"]). Answers until 2026-11-30.
get_rent_levelsMoved: use get([id], select: ["rents"]). Answers until 2026-11-30.
get_listing_search_linksPre-filtered searches on Rightmove, Zoopla, OnTheMarket (and OpenRent for rentals) for the postcode districts of shortlisted areas, filtered by bedrooms, price and property_type (house, flat, bungalow). Links only: open them on the user's behalf to read listings; Close Knit itsel
list_custom_presetsMoved: use describe_data(kind: "custom"). Answers until 2026-11-30.
evaluate_custom_criterionMoved: use query(saved: "custom: "). Answers until 2026-11-30.
build_watch_specTurn a finished search into a watch: portal searches per postcode district, filters, a state file path for de-duplication and a ready prompt for a scheduled task in the user's Claude that reports only new listings. Stateless: nothing is stored on Close Knit.
send_feedbackSend feedback about Close Knit to the team: a bug, missing or wrong data, an idea, or what worked. Call it only after the user agrees: show them the message first. Describe the product and what happened, never the person: no names, contact details, addresses, family, budget or ot
rank_schoolsMoved: use query(kind: "school"). Answers until 2026-11-30.
list_school_measuresMoved: use describe_data(kind: "school"). Answers until 2026-11-30.
rate_answerRate a Close Knit answer by its callId (none: the last answer): rating 1-5, what was good, what was bad or missing, the fix you would want. Use it for the last answer in a conversation; earlier ones go in the next call's rate_previous. It describes the answer, never the user. Sto
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The publisher (getcloseknit.com) is not the repo owner (bmsdave); someone else may have listed it
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 397 ms (HTTP 200)
No sign-in needed
Read 31 tool descriptions and found no hidden instructions to the AI
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 2 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (2.0.8) reached the registry 7 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Spec Driven Development, Remote Desktop Commander, FactLot
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Cited CRE facts and deterministic calculators for agents: rent, CAM, debt sizing, IRR, parcel IDs.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Close Knit gives AI assistants evidence about neighbourhoods and homes in England, with London in depth, to help people choose where to live. It is a remote MCP server: recorded sale prices, rents, crime, schools, flood risk, commute times, noise and more, from official open data. Every tool answer is an evidence envelope with a value, a confidence, the evidence[] behind it, its sources[] (with licence) and caveats[]. Every neighbourhood and local authority in England is covered; London adds address-level sale history, door-to-door TfL commute times and London-only layers. Ranks and percentiles compare an area with its own region (rankScope names it). It is free, with no account or sign-in. Website: https://getcloseknit.com · Setup for every assistant: https://getcloseknit.com/agents.
https://getcloseknit.com/mcp
com.getcloseknit/close-knit| Group | Tool | What it does |
|---|---|---|
| Home search | find_areas | Shortlist neighbourhoods for a household: budget, bedrooms, places they travel to, weighted priorities. |
match_areas | Score every area against a household's ordered criteria. | |
find_similar_areas | Neighbourhoods like one the user liked, optionally only cheaper ones. | |
open_shared_search | Open a search shared from the Close Knit site (a #profile= link). | |
search_places | Resolve a station, borough, neighbourhood, postcode or street the user mentions. | |
get_commute | Door-to-door weekday-morning minutes from an area to the user's places (public transport, bike and more). | |
| Areas | search_areas | Resolve free text (area name, ONS code, postcode, street) to area ids. |
get_area_overview | One neighbourhood in detail: local market, schools, noise, price trend. | |
get_area_evidence_pack | One cited evidence pack for an area: market depth, crime, noise, schools and more. | |
list_metrics | Every area metric served, with unit, direction, periods and provenance. | |
get_area_metric | One metric for one area and month, with percentiles within its region and across England. | |
rank_areas_by_metric | Rank all areas, or one region's, by one metric and return the top N. | |
get_flood_risk | Flood bands for an area's land and, with a UPRN, for one home. | |
get_rent_levels | Median monthly rent by bedroom count. | |
| Homes and prices | get_home_prices | One home's recorded sales and the range of prices in its area today. |
get_address_history | Recorded sale prices for one address (HM Land Registry). | |
get_nearby_sales_summary | Counts and median £/m² of recorded sales in the same building and street. | |
get_market_depth | Local market depth: sales in the last 12 months, turnover, leasehold share. | |
| Listings | get_listing_search_links | Pre-filtered portal searches for the postcode districts of shortlisted areas. |
assess_listing | Check one listing's asking price and facts against local evidence. | |
build_watch_spec | Turn a finished search into a watch for new listings. | |
| Your own criteria | list_custom_presets | Ready-made criteria built from places on OpenStreetMap. |
evaluate_custom_criterion | Evaluate a criterion such as "more cafés than kebab shops" for every neighbourhood. | |
| Schools | rank_schools | Rank schools on weighted measures near a point, in one council, one region or England. |
list_school_measures | The school measures rank_schools can rank by. | |
| Feedback | send_feedback | Send feedback to the Close Knit team, only after the user agrees. |
Close Knit. Remote MCP server URL: https://getcloseknit.com/mcp. Click Continue.On Team and Enterprise plans an owner adds it under Organization settings > Connectors. Free plans allow one custom connector.
claude mcp add --transport http close-knit https://getcloseknit.com/mcp
Add to ~/.codex/config.toml and restart Codex:
[mcp_servers.close_knit]
url = "https://getcloseknit.com/mcp"
Close Knit. Under Connection, Server URL: https://getcloseknit.com/mcp.@ in the prompt box and select Close Knit.Custom MCP servers are available on ChatGPT web; which plans and workspaces allow them depends on your account and workspace settings.
gemini extensions install https://github.com/bmsdave/close-knit-mcp
This repository is a Gemini CLI extension: gemini-extension.json connects the remote server and GEMINI.md gives the model short guidance. Restart Gemini CLI after installing.
https://getcloseknit.com/mcp and click Next, then follow the on-screen steps.@ and select Close Knit.Google currently limits custom apps to people aged 18 or over in the US, signed in with a personal Google Account, with Keep Activity on.
The same install link in Cursor's own format:
cursor://anysphere.cursor-deeplink/mcp/install?name=close-knit&config=eyJ1cmwiOiJodHRwczovL2dldGNsb3Nla25pdC5jb20vbWNwIn0%3D
Or add it to mcp.json:
{
"mcpServers": { "close-knit": { "url": "https://getcloseknit.com/mcp" } } }
Or run MCP: Add Server from the Command Palette, choose HTTP, and enter https://getcloseknit.com/mcp. In .vscode/mcp.json:
{
"servers": { "close-knit": { "type": "http", "url": "https://getcloseknit.com/mcp" } } }
Close Knit. MCP Server URL: https://getcloseknit.com/mcp.closeknit. Server URL: https://getcloseknit.com/mcp.Adding a connector needs an administrator; on Free, Pro and Student plans the account owner is the administrator.
https://getcloseknit.com/mcp.On Business and Enterprise plans a team admin adds connectors first.
In the Cascade panel, open the ... menu, and in the MCPs section click Open MCP config file. Add:
{
"mcpServers": { "close-knit": { "serverUrl": "https://getcloseknit.com/mcp" } } }
Save the file.
Desktop: open Extensions in the sidebar, click Add custom extension, choose the Streamable HTTP type and enter https://getcloseknit.com/mcp.
CLI: run goose configure, choose Add Extension, then Remote Extension (Streamable HTTP), and enter the URL. For a single session:
goose session --with-streamable-http-extension "https://getcloseknit.com/mcp"
Or open the Program tab in the right-hand sidebar, click Install > Edit mcp.json, and add:
{
"mcpServers": { "close-knit": { "url": "https://getcloseknit.com/mcp" } } }
Answers from the live server, October 2026. Figures change with each data release.
"How much crime is there around Clapham Junction?" search_areas finds the neighbourhood (Wandsworth 012A, SW11) and get_area_metric(crime) answers: 74.4 recorded crimes per 1,000 residents in the 12 months to August 2026, a higher rate than 58% of London's neighbourhoods and 65% of England's; the largest categories are violence and sexual offences and anti-social behaviour. Source: police.uk street crime, Open Government Licence v3.0. Confidence high (observed, not modelled).
"Where in the North West are homes cheapest per square metre?" rank_areas_by_metric with region: "North West" puts three Blackpool neighbourhoods first at £970/m², tied. Confidence medium: they had too few sales of their own, so the figure is their MSOA's (quality: "fallback"). Source: HM Land Registry Price Paid with EPC floor areas.
"Help me find a 2-bed flat to buy in London under £600k, within 30 minutes of King's Cross." search_places resolves King's Cross, find_areas returns a ranked shortlist with each area's standing, what it meets ("4 of 5"), its commute and ballpark price, and an "Open in Close Knit" link to the same search on the map; get_listing_search_links then opens pre-filtered searches on the property portals.
Every tool, with its full input schema, is also listed in the server card: https://getcloseknit.com/.well-known/mcp/server-card.json.
The answers come from official open data, mostly under the Open Government Licence v3.0: HM Land Registry Price Paid Data and UK House Price Index, ONS Census 2021 and other ONS statistics, police.uk street crime, Ofsted and Department for Education school data, Environment Agency flood risk, Defra noise maps, Ofcom broadband coverage, MHCLG deprivation (IMD 2025) and planning data, Ordnance Survey OpenData, Transport for London open data ("Powered by TfL Open Data") and OpenStreetMap (© OpenStreetMap contributors, ODbL 1.0). Each answer lists its own sources and licences in sources[]; keep those attributions when you reuse the data.
The MIT licence in this repository covers the files in this repository only. The data served by the MCP server keeps its own licences.
No account and no personal data are needed. send_feedback only sends what you write, and only after you agree.
MIT