Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "cityparity": {
      "type": "http",
      "url": "https://mcp.cityparity.com/mcp"
    }
  }
}

claude mcp add --transport http cityparity https://mcp.cityparity.com/mcp

[mcp_servers.cityparity]
url = "https://mcp.cityparity.com/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "cityparity": {
      "type": "remote",
      "url": "https://mcp.cityparity.com/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "cityparity": {
      "type": "http",
      "url": "https://mcp.cityparity.com/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=cityparity&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vbWNwLmNpdHlwYXJpdHkuY29tL21jcCJ9"
}

{
  "servers": {
    "cityparity": {
      "type": "http",
      "url": "https://mcp.cityparity.com/mcp"
    }
  }
}

{
  "mcpServers": {
    "cityparity": {
      "httpUrl": "https://mcp.cityparity.com/mcp"
    }
  }
}

extensions:
  "cityparity":
    enabled: true
    name: "cityparity"
    type: streamable_http
    uri: "https://mcp.cityparity.com/mcp"
    timeout: 300

Quality 88 / 100good

protocol75 · weight 25

warn
protocol.modernnewest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
n/a
protocol.statelessonly applies to 2026-07-28 servers
pass
protocol.transportstreamable HTTP
n/a
protocol.list_ttlonly applies to 2026-07-28 servers

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene93 · weight 30

pass
tools.descriptionsevery tool has a description
warn
tools.description_length2 tools have descriptions over 1,024 characters, which crowds the context
pass
tools.schemasevery tool has an object input schema
pass
tools.annotations6 of 6 tools declare readOnlyHint or destructiveHint
pass
tools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
pass
tools.token_costabout 3,647 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability100 · weight 15

pass
stability.changes1 tool changes in 30 days
pass
stability.rug_pullno tool changed its meaning under the same name

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

6 tools, about 3,647 tokens to load them all · tool set 45ecdd8f3c63 · tools last changed 2026-10-19 · checked 2026-10-19 13:05 UTC

Tool changes

2026-10-19get_city_summarychangeddescription
before
Concise profile of one city: currency, tax shape (bracket count + top rate + payroll/national insurance), headline costs (rent / groceries / transit / childcare), safety-net values (parental leave, vacation, universal healthcare), and data freshness. Lighter than compare_cities; use when the user is asking about one place rather than a comparison. On parental leave, quote safety_net.parental_leave_summary rather than building your own sentence: some countries (Ireland, Australia, the UK, Czechia, part of Sweden) pay a flat weekly cash sum instead of a share of salary, so parental_leave_paid_pct is 0 or partial for them and stating it alone would wrongly call their leave unpaid. safety_net.avg_commute_minutes is a ONE-WAY commute, a single leg rather than a daily round trip: report it as "about N minutes each way", and double it yourself if the user asked what they spend commuting per day. It is door to door, averaged over every commuter regardless of mode, for the metro area, and excludes people who work from home. Read-only, no side effects; returns a text summary plus structured JSON.
after · 87% of words in common
Concise profile of one city: currency, tax shape (bracket count + top rate + payroll/national insurance), headline costs (rent / groceries / transit / childcare), safety-net values (parental leave, vacation, universal healthcare), and data freshness. Lighter than compare_cities; use when the user is asking about one place rather than a comparison. On parental leave, quote safety_net.parental_leave_summary rather than building your own sentence: some countries (Ireland, Australia, the UK, Czechia, part of Sweden) pay a flat weekly cash sum instead of a share of salary, so parental_leave_paid_pct is 0 or partial for them and stating it alone would wrongly call their leave unpaid. safety_net.avg_commute_minutes is a ONE-WAY commute, a single leg rather than a daily round trip: report it as "about N minutes each way", and double it yourself if the user asked what they spend commuting per day. It is door to door, averaged over every commuter regardless of mode, for the metro area, and excludes people who work from home. Childcare monthly fields are raw rates before modeled help. When childcare_income_tested or child_benefits_income_tested is present, use compare_cities with household income and child ages to price the rules; a flat subsidy or allowance alone is incomplete. Read-only, no side effects; returns a text summary plus structured JSON.

Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 85 / 100

provenance75

liveness98

freshness65

hygiene100

+repository +dns-namespace +reachable +uptime-95% ~updated-141d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://mcp.cityparity.com/mcp` streamable-http	none	yes	95%	297 ms	2025-11-25	2026-10-19

Tools (6)

`compare_cities`read-only	Compare two cities for one household: take-home pay, full cost breakdown, the equivalent target salary needed to match source net cash, non-cash lifestyle deltas (vacation, parental leave, healthcare), and a 0-100 quality score on five weighted dimensions. Use this for a head-to-head between two named cities; for a single city call get_city_summary, and to rank many cities call rank_cities. Read-only, no side effects; returns a text summary plus structured JSON. RSU income is NOT a parameter; RSU is treated as source-only because grants typically do not follow you across employers.
`get_city_summary`read-only	Concise profile of one city: currency, tax shape (bracket count + top rate + payroll/national insurance), headline costs (rent / groceries / transit / childcare), safety-net values (parental leave, vacation, universal healthcare), and data freshness. Lighter than compare_cities; use when the user is asking about one place rather than a comparison. On parental leave, quote safety_net.parental_leave_summary rather than building your own sentence: some countries (Ireland, Australia, the UK, Czechia, part of Sweden) pay a flat weekly cash sum instead of a share of salary, so parental_leave_paid_pct is 0 or partial for them and stating it alone would wrongly call their leave unpaid. safety_net.avg_commute_minutes is a ONE-WAY commute, a single leg rather than a daily round trip: report it as "about N minutes each way", and double it yourself if the user asked what they spend commuting per day. It is door to door, averaged over every commuter regardless of mode, for the metro area, and excludes people who work from home. Childcare monthly fields are raw rates before modeled help. When childcare_income_tested or child_benefits_income_tested is present, use compare_cities with household income and child ages to price the rules; a flat subsidy or allowance alone is incomplete. Read-only, no side effects; returns a text summary plus structured JSON.
`get_inbound_tax_regime`read-only	Look up a city's inbound-worker tax regime, the special reduced-tax schemes for relocating workers that general cost-of-living tools do not surface. Returns regime=null when the country has no modeled regime, which is most cities. Modeled across 13 regimes in Belgium, Denmark, Germany, Greece, Ireland, Italy, Netherlands, Norway, Poland, Portugal, Spain, Sweden and the UK. Roughly half grant an actual reduction (a reduction_pct or a flat_rate) and the rest are note-only: the regime exists but grants a relocating employee nothing, so reduction_pct and flat_rate are null and the take-home is computed on ordinary tax. Each entry returns the mechanic, duration, income cap if any, and a note stating the salary floor where one exists and which eligibility conditions we do not test. Read-only, no side effects; returns a text summary plus structured JSON.
`get_safety_net`read-only	Batch lookup of safety-net values for 1 to 20 cities at once: parental leave weeks + how it is paid, universal healthcare flag, vacation days, public holidays (public_holidays is the count the statute lists; public_holidays_effective is how many of those fall on a working day once you account for whether the country replaces a weekend holiday, so quote the effective figure whenever you compare two places on time off), plus each city's safety_net dimension score (0-100) for relative strength. This is the only tool that accepts many cities in one call: use it to line several places up on family / leave / healthcare benefits. On parental leave, quote parental_leave_summary rather than composing your own line from parental_leave_paid_pct: Ireland, Australia, the UK, Czechia and part of Sweden pay a flat weekly cash sum instead of a share of salary, so their headline percentage is 0 or partial and reading it alone would wrongly call their leave unpaid; Germany pays a percentage up to a monthly cap (parental_leave_capped) and pays nothing at all above a household-income ceiling. Check parental_leave_basis (percentage / flat / capped / mixed / unpaid) before making any claim about pay. On sick pay, quote sick_leave_policy rather than composing your own line from sick_leave.phases: it is the STATUTORY FLOOR for someone in their first year of service, phases run one AFTER another rather than stacking, and the durations carry units that differ by country (Slovenia counts working days, Denmark counts calendar days), so sick_leave.paid_weeks is deliberately null wherever the phases are measured against different reference periods and no single total exists. For one city's full profile (tax shape + costs + safety net together) call get_city_summary instead; for a two-city head-to-head that includes cost-of-living use compare_cities. Read-only, no side effects; returns a text summary plus structured JSON.
`list_cities`read-only	List all city slugs supported by cityparity, grouped by country. Call this first to discover valid slugs before any other tool; the optional country filter narrows to one country. Read-only, no side effects; returns a text summary plus structured JSON.
`rank_cities`read-only	Rank supported cities by composite quality-of-life score across five weighted dimensions (financial, healthcare, vacation, childcare, safety_net). Returns top N (default 10), with filters for country, countries, region (europe/asia/north_america/south_america/oceania), has_universal_healthcare, include_cities, and exclude_cities. Use this to shortlist across many cities; for a head-to-head between two named cities use compare_cities. The same scenario is applied to every city so scores are directly comparable (default: single person, 2BR rent, $100k USD-equivalent gross). Read-only, no side effects; returns a text summary plus structured JSON.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "com.cityparity/cityparity",
  "title": "cityparity — Cost-of-Living & Quality-of-Life Comparison",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://mcp.cityparity.com/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "0.1.0",
  "repository": {
    "url": "https://github.com/summerstateofmind/cityparity",
    "source": "github"
  },
  "description": "Cost-of-living & quality-of-life comparison: take-home pay, equivalent salary, safety-net deltas."
}