MCP HeartbeatTHE MCP OBSERVATORY
Public workspace

Explore

Evidence for your next connection.

Independent measurements of remote MCP servers. Every observation has a timestamp.

Read-only probes

MCP server · Data access / search

BrickIntel

Greater London property statistics, Bank of England mortgage rates, and HM Land Registry sales for one postcode or street.

Checks passed
13 / 22

2 failed · 7 not measured

Median response
1458 ms

Median of successful probes over 7 days

30-day uptime
Not measured

Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.

Discovered tools
9

Tool definitions returned by this server

Independent monitoring

Health & checks

Status history

Responded

The server completed its last measured handshake. This is an observation, not a guarantee.

Last checked
Check summary by test group
Test areaPassedFailedUnmeasured
ConnectionCan a client connect and discover tools?
500
Reliability & speedDoes it respond consistently and quickly?
103
Access & authenticationWhat is required to use this server?
102
Tool qualityAre the tool definitions usable by an agent?
400
Publisher identityCan the publisher be traced to its source?
222

Unmeasured means there is not enough evidence to decide. How these checks work

Inspect individual checks 22 recorded

Core

  • Pass
    Reachable

    Latest probe returned HTTP 200 in 1552 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-06-18, serverInfo.name brickintel.

  • Pass
    Lists tools

    tools/list returned 9 tools.

  • Pass
    Current protocol

    Negotiated 2025-06-18. The bar is 2025-06-18 or newer.

  • Pass
    HTTPS

    The endpoint URL is https.

Performance

  • Not measured
    Fast (p50)

    Median latency 1458 ms over 2 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 1543 ms over 2 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.

  • Not measured
    Reliable (uptime)

    2 of 2 attempts returned a tool list in 30 days (100%). The bar is 99%. Need at least 30 samples.

  • Pass
    Stable tool list

    No tool was removed and no required parameter was added in the last 30 days.

Access

  • Pass
    Open access

    tools/list succeeded with no credential, and the record declares none.

  • Not measured
    Standard auth

    Auth is not required, so the OAuth metadata check does not apply.

  • Not measured
    Free tier cited

    No publisher quote has been checked.

Tools

  • Pass
    Tools described

    Every tool description is at least 20 characters.

  • Pass
    Valid input schemas

    Every inputSchema is a JSON Schema object.

  • Pass
    Parameters documented

    25 of 25 parameters have a description (100%). The bar is 80%.

  • Pass
    Safety hints

    Every tool sets readOnlyHint or destructiveHint.

Publisher

  • Fail
    Verified namespace

    Not listed in the Official MCP Registry. A manual seed is unverified.

  • Pass
    Website matches publisher

    The website host matches the reverse-domain namespace.

  • Fail
    Source repo linked

    No repository URL is on file.

  • Not measured
    Repo owner matches

    This namespace is not an io.github login, so the owner comparison does not apply.

  • Pass
    Recently updated

    Updated 2026-11-10T12:00:00.000Z, within 180 days.

  • Not measured
    Open-source licence

    No GitHub repository to ask about a licence.

Start using BrickIntel

Connect to this server

Choose your client, copy the configuration, then enable the server in your client’s MCP settings.

Run this command in your terminal, then restart Claude Code.

Claude Code

claude mcp add --transport http brickintel https://www.brickintel.ai/api/mcp

Capabilities

Tools 9

area_momentum

Price and volume change for an area versus 6 or 12 months earlier. Each end is twelve months of sales pooled together (a transaction-weighted average of monthly type-adjusted medians, the averaging the website uses for its rolling London trend), so incomplete recent months and one-off sales do not drive the answer. Sales volumes are returned as counts only, because recent months are under-registered. For area=london, also ranks boroughs by that price change so you can say which boroughs moved most. This is a backward-looking comparison of published sales, not a forecast. No addresses. Not financial advice. These figures are descriptive statistics and repayment arithmetic. They are not a mortgage offer, a valuation, or a recommendation to buy, sell, or borrow. BrickIntel is not authorised or regulated by the Financial Conduct Authority.

Discovered
area_snapshot

One-row summary for an area in the latest month that is reasonably complete for Greater London as a whole: median, type-adjusted median, sales count, flat and house medians, luxury share, and the price change versus the previous month. Use this for 'what is Camden doing now'. Recent months are still filling in with late registrations, so treat the figures as provisional. No addresses. Not financial advice. These figures are descriptive statistics and repayment arithmetic. They are not a mortgage offer, a valuation, or a recommendation to buy, sell, or borrow. BrickIntel is not authorised or regulated by the Financial Conduct Authority.

Discovered
area_trends

Monthly Greater London sale-price series for one area: median price, type-adjusted median, transaction count, 10th percentile price, flat median, and house median. Area is london, a borough, or a postcode district. Dates are sale months, not asking prices. Land Registry registrations lag, so the latest three to six months are incomplete and under-count new builds. type_adjusted_median is a flat and house blend weighted by that month's own sales, not a fixed-mix index. No street addresses and no individual transactions. Not financial advice. These figures are descriptive statistics and repayment arithmetic. They are not a mortgage offer, a valuation, or a recommendation to buy, sell, or borrow. BrickIntel is not authorised or regulated by the Financial Conduct Authority.

Discovered
data_freshness

How current the underlying tables are: newest London sale month, newest Bank Rate date, newest quoted mortgage-rate month, and newest EPC lodgement date the server can see. Call this before describing a figure as current. Land Registry months lag real-world completions.

Discovered
list_areas

List the 32 London boroughs and the City of London, with ONS codes. Use it when the user names a place you are unsure how to spell. Postcode districts are not listed; pass an outward code such as E8 or WC2 directly to the other tools. Does not return addresses or individual sales.

Discovered
mortgage_affordability

Repayment arithmetic. Give a price, or an area whose latest p10 (entry) or median price is used. Deposit is a percent of price (default 10). Rate defaults to the latest Bank of England 5-year fixed 75% LTV average when annual_rate_percent is omitted; with a deposit under 25% that rate is lower than most borrowers would be offered, so the payment is understated. Term defaults to 30 years. Also returns the gross household income implied by dividing the loan by an income multiple (default 4.5, the convention BrickIntel shows on the website). This is not a lending decision and not an offer. Not financial advice. These figures are descriptive statistics and repayment arithmetic. They are not a mortgage offer, a valuation, or a recommendation to buy, sell, or borrow. BrickIntel is not authorised or regulated by the Financial Conduct Authority.

Discovered
mortgage_rates

Bank of England published rates. series is bank_rate (official Bank Rate, daily), fixed_2y_75 (average quoted 2-year fixed at 75% LTV, monthly), fixed_5y_75 (5-year fixed, 75% LTV), or fixed_10y_75 (10-year fixed, 75% LTV). Mortgage series publish five to six weeks after the month ends. These are market averages, not a rate a specific borrower will be offered. Not financial advice. These figures are descriptive statistics and repayment arithmetic. They are not a mortgage offer, a valuation, or a recommendation to buy, sell, or borrow. BrickIntel is not authorised or regulated by the Financial Conduct Authority.

Discovered
price_per_sqft

Aggregate pounds per square foot for sales in a borough or postcode district (not Greater London as a whole) whose Land Registry address key matches an EPC certificate. Returns the median £/sqft, the median floor area, how many sales matched, and the match rate. It does not return addresses, certificate numbers, or individual homes. Floor area comes from EPC non-address fields. Floor area is from the latest certificate for the address, which may postdate the sale. Many sales have no match, so read match_rate before quoting the figure. Not financial advice. These figures are descriptive statistics and repayment arithmetic. They are not a mortgage offer, a valuation, or a recommendation to buy, sell, or borrow. BrickIntel is not authorised or regulated by the Financial Conduct Authority.

Discovered
recent_sales

Individual HM Land Registry sales in Greater London, newest first, for one full London postcode (for example E16 1RB) or for a London postcode district plus an optional street. Postcodes outside London return no sales. Other tools still reject full postcodes. Each sale includes SAON, PAON and street, price, property type, tenure, the new-build flag, EPC floor area in sqm and sqft from the latest certificate when the address matches one (roughly 60% of recent sales; read epc_match), £ per sqft, and the previous Price Paid sale of the same property when one exists. Category B (not full market value) is excluded. since defaults to three years ago. limit defaults to 25 and cannot exceed 100. Land Registry is about two months behind. Not financial advice. These figures are descriptive statistics and repayment arithmetic. They are not a mortgage offer, a valuation, or a recommendation to buy, sell, or borrow. BrickIntel is not authorised or regulated by the Financial Conduct Authority.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected1552 ms9
Connected1363 ms9