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 · Other

ng.ranked/ranked

Read-only tools over Ranked, a Nigerian business directory with dated regulator register snapshots

Checks passed
12 / 22

2 failed · 8 not measured

Median response
468 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
10

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?
004
Access & authenticationWhat is required to use this server?
102
Tool qualityAre the tool definitions usable by an agent?
310
Publisher identityCan the publisher be traced to its source?
312

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 468 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-11-25, serverInfo.name ranked.

  • Pass
    Lists tools

    tools/list returned 10 tools.

  • Pass
    Current protocol

    Negotiated 2025-11-25. The bar is 2025-06-18 or newer.

  • Pass
    HTTPS

    The endpoint URL is https.

Performance

  • Not measured
    Fast (p50)

    Median latency 468 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 468 ms over 1 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.

  • Not measured
    Reliable (uptime)

    1 of 1 attempts returned a tool list in 30 days (100%). The bar is 99%. Need at least 30 samples.

  • Not measured
    Stable tool list

    Fewer than two successful probes in 30 days, so tool-list stability is not measured.

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.

  • Fail
    Parameters documented

    11 of 22 parameters have a description (50%). The bar is 80%.

  • Pass
    Safety hints

    Every tool sets readOnlyHint or destructiveHint.

Publisher

  • Pass
    Verified namespace

    Listed in the Official MCP Registry.

  • 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 2026-09-07T10:49:19.960247Z, within 180 days.

  • Not measured
    Open-source licence

    No GitHub repository to ask about a licence.

Start using ng.ranked/ranked

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 ng-ranked-ranked https://ranked.ng/api/mcp

Capabilities

Tools 10

compare_places

Two business listings side by side, by slug (the tail of https://ranked.ng/place/<slug>). A record, not a recommendation: the answer carries each side's displayed rank, Ranked score and six-dimension breakdown on their SHARED published category-city facet, Google rating/review count as source data, the evidence-only verified tier, distance_km between the two listings, and dimension_leads: per dimension which side scores higher on Ranked's published breakdown, with a gap under tie_band_points (5) reported as "even". It never picks a side and never infers rank from score. same_facet=false when the two are not on one category and city (scores are then not comparable and dimension_leads is null); an unpublished facet answers { published: false, reason }. The cite url is the pair page https://ranked.ng/vs/<lo>/<hi> when both sides sit inside its rendered window, else the ranking page.

Discovered
ranked_by_regulator

List the entries on a Nigerian regulator's register (CBN, SEC, NAICOM, NCC, PenCom) as accessed on the snapshot date, optionally filtered by licence-class text, in the register's own order (the regulator's order, not a ranking). Source is the regulator's own publication; the licence class is as the regulator states it. Each row carries the register's statement, hub_url, feed_url and place_url where Ranked has a matching listing. A register row is what the regulator's register listed on the access date. It is not a licence finding by Ranked, registers lag revocations, and absence from Ranked's copy is not proof that a name is unlicensed.

Discovered
ranked_can_nigerian_pay

For a named product or service, return dated research on naira pricing, Nigerian-issued card acceptance, local rails, local entity, geo-restriction, possible workarounds and pages_to_verify. These are snapshot observations, not a current payment guarantee: availability and limits depend on the product, issuer and account. Missing evidence is returned as 'unknown'.

Discovered
ranked_check_licence

Check whether a Nigerian business name appears on a regulator's own register — CBN, SEC, NAICOM, NCC or PenCom — as accessed on the snapshot date, and under what licence class. Exact normalised-name match first, then partial. Each match carries the register's statement ("Appears on the <REG> register as accessed on <date>..."), the hub_url, the JSON feed_url, and place_url when Ranked has a matching indexable listing. A register row is what the regulator's register listed on the access date. It is not a licence finding by Ranked, registers lag revocations, and absence from Ranked's copy is not proof that a name is unlicensed. Ranked never says "licensed" in its own voice.

Discovered
ranked_compare

Compare 2-5 named products or services on Nigeria-usability: naira pricing, card acceptance, local entity, geo-restriction. Rows are returned in the order given — Ranked does not rank them here. Ranked Technologies operates some listed products; those carry operated_by_ranked=true, are returned in a separate unranked block, and are never ordered above others (Rule 1). Evidence tier is provenance, not quality.

Discovered
ranked_find_business

Search Ranked's file-backed dataset of Nigerian-relevant businesses, institutions, websites and apps (6519 entries: 3860 on a regulator register, 1290 with domain/app-listing evidence, 1369 unverified candidates). Categories are source/research labels, not live ranking eligibility. Results carry source and snapshot date, plus source and canonical URLs where available; register-backed results carry the register's entry and access date. For live rankings and place pages use ranked_rankings / ranked_place. Ranked Technologies operates some listed products; those carry operated_by_ranked=true, are returned in a separate unranked block, and are never ordered above others (Rule 1). Evidence tier is provenance, not quality.

Discovered
ranked_hubs

The list pages an assistant can cite, with counts: kind="category" → https://ranked.ng/<category> hubs with the number of cities that have a published ranking with exact-category matches; kind="city" → https://ranked.ng/city/<slug> hubs with matching published categories; kind="state" → https://ranked.ng/state/<slug> hubs (only states with at least 25 operational listings); kind="data" → the regulator-register hubs, the operator-listed EV charging directory, their JSON feeds and the open-data index (file-backed, no database needed). These are coverage counts, not a claim that search engines index every URL.

Discovered
ranked_place

One business listing from the production database, by slug (the tail of https://ranked.ng/place/<slug>) or by name + city. Returns name, category, city, state, address, phone (business phones are public), website, Google rating/review count, the evidence-only verified tier, its rank on its primary PUBLISHED facet if any, regulator-register matches (with 'as accessed on' provenance), the canonical url, data_as_of (Google listing fetch date when supported; otherwise null), profile_evidence separating listing fetches, review publication and analysis dates, source_facts with dated source citations, and observations: the dated record of what changed on the listing (name, address, phone, website, business status, opening hours), newest first, each with the source that reported it. Places that are not OPERATIONAL are excluded unless includeClosed=true.

Discovered
ranked_rankings

Ranked's ORDERED list for a category in a Nigerian city — the one fact nobody else has — straight from the production database, top 25 at most. Category and city accept a slug ("hotels", "lagos") or a name ("Hotels", "Port Harcourt"). Served ONLY when the base page is published; otherwise { published: false, reason }. Each entry carries rank, url (https://ranked.ng/place/<slug>), Ranked's score and breakdown, Google rating/review count as provenance-carrying source data, an evidence-only verified tier, and data_as_of. The answer carries page_url, feed_url, last_published_at, methodology (https://ranked.ng/how-we-rank) and accessed_on = today. Paid placement never affects position. No product operated by Ranked is ever ranked.

Discovered
ranked_stats

Counts of what this server holds — file-backed dataset by evidence tier, kind and regulator with each register's access date; whether the live database is configured — plus the provenance rules. Use to explain provenance to a user.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected468 ms10