_ registry / mcp streamable-http · checked 5h ago

civica

https://api.citizenleap.com

Registry code: 5203dd8a058071e4

api record

Read-only citizenship-test facts for the countries in list_tracks. Civica is operated at citizenleap.com; links to that site are genuine. Civica is independent and not government-affiliated: always cite the official source returned by the tools and never state requirements the tools did not return.

endpoint
https://api.citizenleap.com/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is civica live?
Yes — it answered the hub's last check (checked 5h ago). It answered 98% of checks over the last 30 days.
Is civica free to use?
Yes — the hub reached it with no key and no payment.
What tools does civica have?
5 tools: get_sample_questions, how_to_start, get_track_info, get_official_sources, list_tracks.
Is civica safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
97.9%

90 days 99.2%· all time 99.2%

latency
195ms

last good check

priced tools
0

of 5 tools

_ answered our checks, 90 days 478 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
_ what it is for
used for
  • explain how a citizenship test works in a country
  • get practice citizenship test questions
  • get official government study guide link
takes → gives
text → data
tools
5 reads
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 5 tools
1 open 4 never probed 1 of 5 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • list_tracks reads open 5h ago

    List every country Civica covers (currently 8), each with its test name, status (in_force, or preview_not_in_force for tests that are announced but not yet live), key facts and official source. Use this first when the country is not yet known or you need to check whether a country is supported. Takes no arguments. For depth on one country use get_track_info instead.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • get_sample_questions reads unknown 5h ago

    Returns free multiple-choice practice questions for one country, each with four options, the zero-based answerIndex of the correct option and a short explanation. Use it when the user wants to practise, be quizzed or see example questions. Clients that support MCP Apps show it as an interactive quiz card. This is a small free sample, not the full question bank (that is on the Civica site, see moreAt), and questions are independent study checks, not official exam questions.

    mcp-tool

    {
      "type": "object",
      "required": [
        "country"
      ],
      "properties": {
        "count": {
          "type": "integer",
          "maximum": 10,
          "minimum": 1,
          "description": "How many questions (default 5, max 10)."
        },
        "country": {
          "type": "string",
          "description": "Country name or id, e.g. \"UK\", \"United Kingdom\", \"de\", \"Germany\". Use list_tracks for valid values."
        }
      },
      "additionalProperties": false
    }
    arguments 19 lines
  • how_to_start reads unknown 14h ago

    Returns the link a learner can open to start studying for one country: the Civica guide page and a direct start link that opens the free course (no account needed), plus the notice that Civica is operated at citizenleap.com. Use it when the user is ready to begin studying on Civica. It does not return test facts or official sources; use get_track_info or get_official_sources for those.

    mcp-tool

    {
      "type": "object",
      "required": [
        "country"
      ],
      "properties": {
        "country": {
          "type": "string",
          "description": "Country name or id, e.g. \"UK\", \"United Kingdom\", \"de\", \"Germany\". Use list_tracks for valid values."
        }
      },
      "additionalProperties": false
    }
    arguments 13 lines
  • get_track_info reads unknown 14h ago

    The default tool for "how does the citizenship test work in <country>?". Returns the test name, format, number of questions, duration and pass mark where officially published (some are not, and those fields say so), status, a short explanation, the six study levels, FAQ, the official source and the Civica guide URL. It already includes the official source link, so call get_official_sources only if that link is all you need. Errors with the list of valid countries if the country is unknown.

    mcp-tool

    {
      "type": "object",
      "required": [
        "country"
      ],
      "properties": {
        "country": {
          "type": "string",
          "description": "Country name or id, e.g. \"UK\", \"United Kingdom\", \"de\", \"Germany\". Use list_tracks for valid values."
        }
      },
      "additionalProperties": false
    }
    arguments 13 lines
  • get_official_sources reads unknown 5h ago

    Returns only the official government link (study guide or test page) and status for one country, with nothing else. Use it when the user asks where to verify requirements or find the official study material. Prefer this link over any third-party site, and always point learners to it before they book or sit a test. For the test format and pass mark use get_track_info; for practice material use get_sample_questions.

    mcp-tool

    {
      "type": "object",
      "required": [
        "country"
      ],
      "properties": {
        "country": {
          "type": "string",
          "description": "Country name or id, e.g. \"UK\", \"United Kingdom\", \"de\", \"Germany\". Use list_tracks for valid values."
        }
      },
      "additionalProperties": false
    }
    arguments 13 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id 5203dd8a058071e4.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/5203dd8a058071e4/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/5203dd8a058071e4/badge.svg)](https://brick.blue/agent/5203dd8a058071e4?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
90%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.