Agentic House Search

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

UK neighbourhood research from government open data: postcode reports, comparisons, 45 datasets.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Agentic House Search": {
      "url": "https://agentic-house-search.vercel.app/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (5)

• postcode_report read-only

  Full neighbourhood report for one UK postcode, assembled live from UK government open data. Covers eleven categories: demographics (Census 2021), crime (data.police.uk), deprivation (IMD/WIMD/SIMD/NIMDM), property prices (HM Land Registry), broadband and 5G (Ofcom), noise (Defra), transport, amenities (OpenStreetMap), schools (DfE register: name, phase and distance only, no Ofsted grades) and planning constraints (Planning Data platform, Environment Agency). Every figure carries the geography it describes (a postcode, an LSOA of ~1,500 people, or a whole local authority), the period it covers, and a benchmark where one exists. Read those: a crime count describes a 1 km square, and Ofcom mobile coverage describes an entire local authority, not the street. Args: - postcode (string): UK postcode, spaces optional - categories (string[], optional): subset to fetch; omit for all eleven - include_sources (boolean): append publisher and licence per category (default false) - response_format ('markdown' | 'json'): default 'markdown' Returns: Per category: a status, a one-paragraph summary, the facts (label, value, band, benchmark, geography, period, source id) and any caveats. Statuses that are normal rather than failures: - "out_of_coverage": the dataset genuinely does not cover this nation. Census tables are England & Wales; police.uk excludes Scotland; Planning Data, Defra noise and the DfE school register are England-only. The reason and the devolved equivalent are given. - "unavailable": a pre-built extract has not been generated for this area yet (noise, currently). - "partial": some sources answered and some did not; check notes. Examples: - "What's SW11 1AA like?" -> postcode="SW11 1AA" - "Is the broadband any good at M1 1AE?" -> postcode="M1 1AE", categories=["broadband","mobile"] - "Crime and schools near LA23 1AA" -> postcode="LA23 1AA", categories=["crime","schools"] Errors: - "No such postcode" with suggestions when the postcode does not exist - Terminated postcodes are reported with the year they were withdrawn Not a survey, valuation or conveyancing search. Check anything decision-critical against the source.

  Parameters:

  • postcode (required) — string — A UK postcode, with or without a space, e.g. "SW11 1AA" or "m11ae"
  • categories — array — Which sections to fetch. Omit for all eleven. Fetching only what you need is faster and much smaller — e.g. ["crime","schools"] for a family-safety question.
  • include_sources — boolean — Append the publisher and licence of each dataset used (default false)
  • response_format — string — 'markdown' to read, 'json' for the full structured facts

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• postcode_lookup read-only

  Resolve a UK postcode to its geography — coordinates, local authority, ward, constituency, LSOA/MSOA/output area, police force, rural-urban class and deprivation rank. One fast call with no downstream data fetching. Use it to check a postcode exists, to get the codes needed for other datasets, or when you only need where somewhere is rather than what it is like. Args: - postcode (string): UK postcode, spaces optional - response_format ('markdown' | 'json'): default 'markdown' Returns: Coordinates, administrative geography, statistical geography codes (LSOA/MSOA/OA — these are the keys most UK open datasets are published against), and the deprivation rank with the index it came from. Examples: - "Where is SW11 1AA?" -> postcode="SW11 1AA" - "What LSOA covers M1 1AE?" -> postcode="M1 1AE" - "Is XY1 2AB a real postcode?" -> postcode="XY1 2AB" (returns an error with suggestions) Don't use when: you want data about the area — use postcode_report instead. Note: deprivation ranks are NOT comparable between UK nations. Each nation ranks its own areas against its own index, over a different number of areas; the index and its size are returned so you do not compare them by mistake.

  Parameters:

  • postcode (required) — string — A UK postcode, e.g. "SW11 1AA"
  • response_format — string — 'markdown' to read, 'json' for the structured record

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• postcode_compare read-only

  Compare two to five UK postcodes on chosen categories, aligned measure by measure. Fetches each postcode's report concurrently and lines the facts up in a table, so you can answer "which of these is better connected / quieter / cheaper" in one call instead of several. Args: - postcodes (string[]): 2-5 UK postcodes - categories (string[]): 1-6 of demographics, crime, deprivation, prices, broadband, mobile, noise, transport, amenities, schools, environment - response_format ('markdown' | 'json'): default 'markdown' Returns: One row per measure with a column per postcode, each cell carrying the value, its band, and the category status for that postcode. Caveats collect anything that makes a row not strictly comparable. Comparability warnings you must respect, and which this tool surfaces: - Deprivation ranks from different UK nations are NOT comparable — different indices over different numbers of areas. - A measure missing for one postcode because the dataset does not cover that nation is not a low score; the cell says "out_of_coverage". - Ofcom mobile figures describe a whole local authority, so two postcodes in the same authority will always be identical. - Crime counts describe a 1 km square and depend on each police force submitting data; a very low count can be a gap rather than a quiet street. Examples: - "Which has better broadband, SW11 1AA or M1 1AE?" -> postcodes=[...], categories=["broadband"] - "Compare these three on crime and schools" -> categories=["crime","schools"] Don't use when: you have one postcode (use postcode_report) or want the underlying datasets (use postcode_search_datasets).

  Parameters:

  • postcodes (required) — array — Two to five UK postcodes to compare, e.g. ["SW11 1AA", "M1 1AE"]
  • categories (required) — array — Which categories to compare on. Keep it tight — comparing all eleven across five postcodes produces a very large answer.
  • response_format — string — 'markdown' for a side-by-side table, 'json' for the structured comparison

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• postcode_search_datasets read-only

  Search a curated registry of 45 UK open datasets and APIs for property and neighbourhood research. Each entry records the dataset's home page, its machine-readable endpoint, format, licence, geographic coverage, update cadence, and the concrete questions it can answer. Use it to find the right source for something this server does not report directly — EPC ratings, planning applications, flood risk, council tax bands, bus timetables, air quality, ground stability, land ownership. Args: - query (string, optional): free text over name, publisher, category, endpoint and questions - category (string, optional): category prefix, e.g. "Crime", "Transport", "Environment" - limit (number): 1-45, default 10 - offset (number): pagination offset, default 0 - response_format ('markdown' | 'json'): default 'markdown' Returns: { total, count, offset, has_more, next_offset, datasets: [{ id, dataset, publisher, category, api, licence, coverage, update_frequency }] } Examples: - "Where do I get EPC data?" -> query="EPC" - "What flood datasets are there?" -> query="flood" - "List every transport source" -> category="Transport", limit=20 Follow up with postcode_get_dataset for the full entry including API docs and the questions it answers.

  Parameters:

  • limit — integer — Maximum results (default 10)
  • query — string — Free text matched against dataset name, publisher, category, API endpoint and the questions each dataset answers. Omit to list everything.
  • offset — integer — Results to skip, for pagination
  • category — string — Filter by category prefix, e.g. "Crime", "Transport", "Environment"
  • response_format — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• postcode_get_dataset read-only

  Full registry entry for one dataset, by id. Returns everything needed to call the source yourself: its home page, machine-readable endpoint, API documentation, format, licence, geographic coverage, update cadence, and the concrete questions it can answer. Args: - id (string): registry id, e.g. "police-street-crime", "land-registry-ppd", "ea-flood" - response_format ('markdown' | 'json'): default 'markdown' Examples: - "How do I call the police API?" -> id="police-street-crime" - "What licence is Price Paid under?" -> id="land-registry-ppd" Errors: - Returns the closest matching ids when the id is not found.

  Parameters:

  • id (required) — string — Registry id, e.g. "police-street-crime" — find one with postcode_search_datasets
  • response_format — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.