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 · Payments & trading

Factline

Checks before an agent pays: payees, webshops, invoices, payment files, companies, sanctions, PEP.

Checks passed
12 / 22

2 failed · 8 not measured

Median response
2358 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
19

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?
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 2358 ms.

  • Pass
    Valid handshake

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

  • Pass
    Lists tools

    tools/list returned 19 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 2358 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 2358 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.

  • Pass
    Parameters documented

    43 of 49 parameters have a description (88%). The bar is 80%.

  • Pass
    Safety hints

    Every tool sets readOnlyHint or destructiveHint.

Publisher

  • Pass
    Verified namespace

    Listed in the Official MCP Registry.

  • Not measured
    Website matches publisher

    This namespace is not a reverse domain, so the website comparison does not apply.

  • Fail
    Source repo linked

    No repository URL is on file.

  • Fail
    Repo owner matches

    The GitHub repository owner does not match the namespace login.

  • Pass
    Recently updated

    Updated 2026-11-02T03:05:16.842161Z, within 180 days.

  • Not measured
    Open-source licence

    No GitHub repository to ask about a licence.

Start using Factline

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 factline https://factline.dev/mcp

Capabilities

Tools 19

buy_full_address_report

Returns a secure payment link (iDEAL or card, via Dodo Payments, EUR 2.95 incl. VAT) for the full English report on a Dutch address: crime vs national rate, noise and air quality, flood probability, ground height, monuments, permits, amenities, liveability breakdown and home-value trend. The report opens right after payment. Only use when the user wants the full report or asks to buy it.

Discovered
buy_full_vehicle_report

Returns a secure payment link (iDEAL or card, via Dodo Payments, EUR 1.95 incl. VAT) for the full English vehicle report: APK inspection history with defects, recall details, import/taxi/export history, specs and catalogue price. Only use when the user wants the full report or asks to buy it.

Discovered
eu_exchange_rates

Free. Use when the user needs an official euro exchange rate or a conversion for an invoice, contract or report: ECB euro reference rates (about 30 currencies), today or any working day in the last 90 days, with cross rates. Input: base (default EUR), symbols (e.g. USD,GBP), optional date YYYY-MM-DD and amount.

Discovered
eu_law_lookup

Free. Use when the user cites an EU regulation, directive or decision and you need its official title, date, whether it is still in force, and the EUR-Lex link to cite: by CELEX number (e.g. 32016R0679) or citation (e.g. Regulation (EU) 2016/679, Directive 2015/849).

Discovered
eudr_geo_check

Free. Use when the user has a supplier's EUDR plot file for a due diligence statement (from 30 Dec 2026): checks [longitude, latitude] order, at least 6 decimals, a point only for plots up to 4 ha, closed and non-crossing polygons, plots inside the country of production, area per plot. Returns looks_valid, check_warnings or fix_needed. Input: geojson (the file as text), optional country (ISO) and commodity.

Discovered
firm_check

Free. Use when the user asks whether criminals can send mail as their firm or whether lookalike domains of it exist: DMARC and SPF status of the firm's domain and registered lookalike domains (typos, swapped letters). Input: domain.

Discovered
get_trial_key

Free. Use when Factline's free calls for today are used up or the user wants more paid checks without a crypto wallet. Without an email it returns a starter key at once (100 credits, 14 days, no human step). With the user's work email it returns a trial key (2,000 credits a month, one per email); send email plus api_key to upgrade a starter key. Ask the user for the email; never invent one.

Discovered
mcp_server_check

Free. Use before connecting to or installing an MCP server you have not used before, or to re-check one: connects once (no tool is called), scans tool descriptions for prompt-injection wording and invisible characters, lists tools that write, send, pay or run commands, checks the domain and publisher, and returns tools_sha256 (send it next time to catch a changed tool list). Decision allow, review or deny. Input: url, optional tools_sha256.

Discovered
nl_car_model

Free. Use when the user asks how reliable a car model is, or which used car to buy: facts for the model in the Netherlands from RDW data: APK (MOT) defect rate vs the average of all models, the 10 most common APK defects, recalls with component and risk, share with an open recall, share with an illogical (rolled-back) odometer, cars registered. Covers ~450 common passenger-car models.

Discovered
nl_home_basic

Free. Use when the user mentions a Dutch address or asks about a home in the Netherlands: year built, floor area, use, neighbourhood residents and average home value, liveability percentile, in English. Accepts postcode + house number or free text. Sources: BAG, CBS, Leefbaarometer.

Discovered
nl_neighbourhood_summary

Free. Use when the user asks what a Dutch neighbourhood or postcode area is like, or whether it is safe: headline facts for a postcode: residents, average home value (WOZ) and the municipality's average sale price, share of owner-occupied homes, liveability percentile, crime per 1,000 residents vs the national rate, and distance to supermarket, GP, primary school and train station. Sources: CBS, Politie, Leefbaarometer.

Discovered
nl_schools_near

Free. Use when the user asks about schools near a Dutch address or postcode, or is moving with children: the nearest primary and secondary schools, with distance, denomination, pupils, the share of pupils reaching the target reading and maths level on the end-of-primary test (vs national), and secondary exam pass rates per track (vmbo/havo/vwo). Also the nearest daycare (0 to 4) and after-school care (4 to 12) with registered places. Sources: DUO, Landelijk Register Kinderopvang.

Discovered
nl_vehicle_basic

Free. Use when the user gives a Dutch licence plate or asks about a specific car in the Netherlands: make, model, age, fuel, Euro class, APK (MOT) expiry, insurance, open recall, RDW odometer verdict and a risk level. Source: RDW.

Discovered
payment_run_check

Free. Use before a payment run is sent to the bank: give the payment file as text (SEPA pain.001 XML or CSV with payee name and IBAN) and, best, last run's file or a vendor list as previous. Each line gets release, review or hold: invalid or changed IBAN, a payee name that imitates a known supplier, one IBAN under two names, new payee, duplicate, possible sanctions match. Up to 25 payments here; 100 with an API key over HTTP.

Discovered
supplier_card_verify

Free. Use before onboarding or paying a supplier that has a website: reads https://<domain>/.well-known/supplier.json (spec factline.dev/supplier-json), checks its VAT number in VIES and company number in the register against the name, and with iban says whether that IBAN is one of the supplier's own hashed accounts. Returns verified, review, invalid_card or no_card. Input: domain, optional iban.

Discovered
watch_alerts

Free. Use at the start of a session or on a schedule when the user has Factline watches (from watch_30_days or a key): lists the watches and any alerts (a new sanctions match, a company status, name or address change, APK or recall change). Input: token (wt_..., returned by watch_30_days) or api_key, optional since (YYYY-MM-DD).

Discovered
webshop_check

Free. Use before a shopping agent or the user pays an unfamiliar webshop: domain age, company and VAT number on the site (VAT checked in VIES), contact page, payment methods, prepayment-only or crypto-only, 70-99% discount lures. Returns looks_ok, caution or avoid and decision allow, review or deny. Input: url.

Discovered
x402_pay_guard

Free. Use right before paying an x402 seller: screens the payTo wallet against the OFAC list, checks that payTo is a wallet this seller lists in the x402 Bazaar or Circle catalogue (catches a swapped or injected payTo), looks up the seller's payer history, age and uptime, and checks the amount against the seller's listed price and your budget. Returns allow, review or deny with reasons and a signed verdict. Input: url of the resource, pay_to from its 402, optional amount_usd, max_usd, network, mode (strict: deny instead of review on a wallet mismatch or missing pay_to).

Discovered
x402_sellers

Free. Use when looking for an x402 API to pay for a task, or to see if a seller is used and up: sellers from the Coinbase x402 Bazaar ranked by unique payers (30 days), with Factline's daily check that their endpoints answer a valid 402, speed and networks. q is one word to filter (sanctions, weather) or plain words for what you need (an API for flight prices).

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected2358 ms19