Skip to content
Novarithm logo

Novarithm MCP server

Which MCP servers are Novarithm's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-29

← Back to Novarithm

Whose server it is
  • Registry namecom.novarithm.www/agent-hubverified in the MCP registry

The registry name sits under novarithm.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-29
  • Stateanswerschecked 2026-10-29
  • Tools61
  • Server calls itselfnovarithm-agent-hub
  • Server version1.1.0
  • Protocol version2025-06-18

On 2026-10-29 the server answered initialize and tools/list without a sign-in. First answer in 733 ms.

Should an agent connect itSkip it
  • Its tools do none of the product's use cases we checked: book appointments into the business calendar; find new prospects and manage the website and social accounts.
  • Checked on 5 of the 7 days it takes to judge reliability.

Once connected

  • Parameters are untyped or undescribed in 16 of 61 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 5, the first on 2026-10-29
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 5 so far
  • What an agent can do with it0 of 2 use cases
  • Answeredmeasuring5 of the 7 daily checks it takes to print a share
  • Median first answer718 ms
  • Space in an agent's context≈ 14,124 tokensthe definitions of all its tools (61), which an agent carries on every turn
  • Tool definitionsB · 79 of 100
  • Typed results0 of 61 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 16 of 61
  • Not saying whether it only reads or can destroy: 61 of 61

What an agent can do with it

  • not sure · answer customer calls and WhatsApp messages around the clock
  • cannot · book appointments into the business calendar
  • cannot · find new prospects and manage the website and social accounts

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers61 tools · read 2026-10-29
  • pricing

    Free. Lists every paid tool with its price per call (USDC, Base mainnet).

  • job_result

    Free. Reads the result of an async paid job (services: site-audit, deploy-proof, due-diligence-report). Pass the service and job_id returned by the paid tool.

  • site_audit_quick

    [PAID $5 USDC/call, x402, eip155:8453] Quick Bierus website audit (audit-live engine, 6 steps): reads the site, asks AI assistants (Google AI Mode/Overview, ChatGPT, an LLM), checks online reputation, Lighthouse mobile speed and security…

  • site_audit_full

    [PAID $25 USDC/call, x402, eip155:8453] Full Bierus v2 website audit: ~40 stable control ids (ok / ko / not measured / not applicable) with dated sources: reputation, checkout path (stops at the payment page), reviews and claims, AI…

  • test_website

    [PAID $5 USDC/call, x402, eip155:8453] Signed passive website proof: page reachable, TLS certificate, http→https, response time, title, mixed content, real 404, internal links sample, optional expected text. ok/ko/not_measured + EIP-712…

  • test_seo

    [PAID $5 USDC/call, x402, eip155:8453] Signed passive SEO proof: SEO module scores (technical, content, links, local, AI visibility), title/meta lengths, canonical, single h1, lang, JSON-LD, indexable, sitemap. ok/ko/not_measured +…

  • test_security_basics

    [PAID $5 USDC/call, x402, eip155:8453] Signed PASSIVE security basics: TLS 1.2+, certificate expiry, HSTS, CSP, framing, nosniff, referrer policy, version disclosure, cookie flags, known-vulnerable JS versions in script URLs, mixed…

  • test_checkout

    [PAID $25 USDC/call, x402, eip155:8453] Signed passive checkout-path proof for a store or product page: price/currency/availability, add-to-cart control, cart page, checkout links over https, payment provider, terms/returns/privacy/legal…

  • verify_delivery

    [PAID $99 USDC/call, x402, eip155:8453] Full signed delivery verification: website + SEO + security basics (+ checkout if store=true) + the client's acceptance criteria (expected texts, pages that must answer). One verdict…

  • check_provider

    [PAID $0.010 USDC/call, x402, eip155:8453] Trust decision (trust/caution/avoid + score) for one paid agent provider: x402 offer, MCP, A2A card, 3 unpaid availability probes, domain reputation, OFAC check of payTo, ERC-8004 identity and…

  • compare_quality

    [PAID $2 USDC/call, x402, eip155:8453] Compare 2-5 paid agent providers with the same measured checks and rank them (decision, budget, trust score, price, latency); returns the recommended provider and why.

  • vendor_report

    [PAID $9 USDC/call, x402, eip155:8453] Readable vendor due-diligence report: reputation, sanctions (OFAC/UN/EU/UK), product recalls, EU-Ready, email authentication, product offer; proceed/review/block, Markdown report, signed evidence…

  • us_geocode

    [PAID $0.003 USDC/call, x402, eip155:8453] Geocode one US street address with the U.S. Census Bureau: standardised address, lat/lon, state, county, census tract, block group, ZCTA, metro area, congressional district (official GEOIDs). No…

  • uk_postcode

    [PAID $0.002 USDC/call, x402, eip155:8453] UK postcode lookup (ONS Postcode Directory via postcodes.io): lat/lon, country, region, local authority, ward, parliamentary constituency, NHS ICB, police force, LSOA. Unknown postcode = not…

  • a2a_card_check

    [PAID $0.01 USDC/call, x402, eip155:8453] Fetch and validate a peer agent's A2A Agent Card (v1.0 / v0.3): fields, skills, interfaces, auth, signature, reachability. Score 0-100 + issues.

  • mcp_probe

    [PAID $0.01 USDC/call, x402, eip155:8453] Real MCP Streamable HTTP handshake (initialize + tools/list, no tool call): reachability, protocol version, tools, schemas, latency, OAuth metadata.

  • x402_probe

    [PAID $0.01 USDC/call, x402, eip155:8453] Pre-payment check of an x402 endpoint: one unpaid request, decodes the 402 offer (v1/v2): network, USDC or not, USD price, payTo, testnet, red flags.

  • agent_ready_score

    [PAID $0.010 USDC/call, x402, eip155:8453] Agent-ready score 0-100 (A-F) of a website or API: AI-bot access, llms.txt, A2A agent card, MCP manifest, x402 discovery, OpenAPI and agentic-commerce markup, with fixes ranked by impact.

  • clone_blueprint

    [PAID $49 USDC/call, x402, eip155:8453] Architecture plan + installation checklist for one AI-run business: clone=agency (AI sales-agent agency), trading-house (AI B2B trading house) or api-store (API store for AI agents). Components…

  • email_check

    [PAID $0.003 USDC/call, x402, eip155:8453] Validate one email address without sending mail: syntax, MX, disposable, free webmail, role account, SPF/DMARC. Returns deliverable/risky/undeliverable/invalid with score.

  • domain_email_health

    [PAID $0.01 USDC/call, x402, eip155:8453] Audit a domain's email authentication: MX, SPF, DMARC, DKIM (20 selectors), MTA-STS, TLS-RPT, BIMI and domain age. Returns an A-F grade with concrete fixes.

  • evaluate_deliverable

    [PAID $0.25 USDC/call, x402, eip155:8453] Evaluate a deliverable (text, JSON or URL) against a job spec (free text or JSON criteria): verdict pass/partial/fail, score, checked criteria, and a signed EIP-712 attestation whose digest is the…

  • verify_attestation

    [PAID $0.001 USDC/call, x402, eip155:8453] Verify an attestation token issued by evaluate_deliverable: recovers the EIP-712 signer, checks it is our evaluator, returns verdict, score, jobId and the bytes32 reason.

  • eu_ready_check

    [PAID $0.010 USDC/call, x402, eip155:8453] Before buying or selling a product in the EU: Safety Gate alerts (barcode or brand+words), GPSR manufacturer / EU responsible person on the page, seller sanctions (OFAC/UN/EU/UK) and price at the…

  • fragrance_check

    [PAID $0.15 USDC/call, x402, eip155:8453] Risk signals for a fragrance listing: sales channel, price per ml, listing words, seller domain and EU Safety Gate. Does not authenticate a physical bottle. Provide url, or brand and seller_domain.

  • fx_convert

    [PAID $0.002 USDC/call, x402, eip155:8453] Convert an amount between two currencies at the official ECB reference rate, today or any date since 1999, incl. CFA franc and Gulf pegs. Returns rate, amount, rate date.

  • fx_timeseries

    [PAID $0.005 USDC/call, x402, eip155:8453] Daily official ECB exchange rates for a currency pair over up to 366 days, with min, max, mean and % change. Useful for invoicing, hedging checks and reporting.

  • fx_latest

    [PAID $0.002 USDC/call, x402, eip155:8453] All official ECB reference rates for any base currency on the latest or a given fixing date, including pegged currencies (XOF, XAF, AED, SAR). One call, full rate table.

  • pre_purchase_check

    [PAID $0.010 USDC/call, x402, eip155:8453] Bundle before paying: verified price/stock (schema.org), seller trust score (RDAP, TLS, DMARC, policies, phishing lists) and recall status (CPSC, openFDA, RappelConso) for a product URL, with a…

  • price_availability

    [PAID $0.006 USDC/call, x402, eip155:8453] Verified price, currency, availability and seller of a product page URL from its schema.org JSON-LD / microdata / OpenGraph data. robots.txt respected; blocked or unpriced pages return…

  • recall_search

    [PAID $0.01 USDC/call, x402, eip155:8453] Search official recall notices (CPSC, openFDA food/drug/device, RappelConso FR) by product, brand or model; filter by market and period.

  • gtin_recall

    [PAID $0.01 USDC/call, x402, eip155:8453] Exact recall check for one EAN/UPC/GTIN barcode (check digit validated) across RappelConso, CPSC and openFDA.

  • sanctions_screen

    [PAID $0.01 USDC/call, x402, eip155:8453] Screen a person or company name against OFAC SDN, UN, EU and UK sanctions lists in one call (fuzzy, aliases). Returns matches with score, list, programs, countries.

  • sanctions_crypto_address

    [PAID $0.005 USDC/call, x402, eip155:8453] Check a crypto address (BTC, ETH/EVM, TRON, LTC, XMR, SOL and more) against OFAC SDN digital currency addresses. Returns listed true/false and the sanctioned entity.

  • seller_reputation

    [PAID $0.008 USDC/call, x402, eip155:8453] Trust score 0-100 for an online store domain or URL: domain age (RDAP), HTTPS, MX/SPF/DMARC, return policy and contact, Tranco rank, phishing lists, scam patterns. Short JSON with risk, advice…

  • seo_technical_audit

    [PAID $0.008 USDC/call, x402, eip155:8453] Technical SEO audit of a URL: HTTPS and redirects, www duplicate, canonical, noindex, title/meta/H1, viewport, hreflang, Open Graph, sitemap and robots.txt, soft 404, response time, compression…

  • seo_keywords_content

    [PAID $0.01 USDC/call, x402, eip155:8453] On-page keyword and content analysis: focus keyword (given or detected) placement in title/H1/meta/first 100 words/URL, density, top terms and phrases, headings outline, FAQ questions, word count…

  • seo_internal_links

    [PAID $0.008 USDC/call, x402, eip155:8453] Internal linking audit: crawls up to max_pages same-site pages (robots.txt respected, 30 s cap): broken internal links, orphan pages vs XML sitemap, click depth, dead ends, generic/empty anchors…

  • seo_local_presence

    [PAID $0.01 USDC/call, x402, eip155:8453] Local SEO / listings readiness from the website: phone (tel: links), postal address, e-mail, Organization/LocalBusiness JSON-LD (address, telephone, geo, hours, sameAs), Google Maps/Business and…

  • geo_ai_visibility

    [PAID $0.008 USDC/call, x402, eip155:8453] GEO audit - can ChatGPT, Claude, Perplexity, Gemini cite this site? AI search/user/training bots allowed in robots.txt, text readable without JavaScript, schema.org, metadata, llms.txt, sitemap…

  • seo_full_audit

    [PAID $0.010 USDC/call, x402, eip155:8453] Full SEO + GEO audit in one call: technical, keywords and content, internal links (12-page crawl), local presence and AI visibility, weighted 0-100 score and the 12 priority actions across all…

  • trust_trio

    [PAID $0.010 USDC/call, x402, eip155:8453] Trust Trio: A2A agent card + MCP server probe + x402 payment-offer check of one AI agent in a single call (no payment made to it). Returns trusted/partial/untrusted, a trust score and every issue.

  • verify_usdc_payment

    [PAID $0.002 USDC/call, x402, eip155:8453] Verify a USDC payment on Base: tx succeeded, USDC sent to the expected recipient (and from the expected sender), at least min_amount, enough confirmations. Returns verdict + decoded transfers…

  • usdc_balance

    [PAID $0.001 USDC/call, x402, eip155:8453] Current USDC balance of an address on Base or Base Sepolia (balanceOf on the official Circle contract).

  • vendor_due_diligence

    [PAID $0.5 USDC/call, x402, eip155:8453] Vendor due diligence in one call: seller domain reputation, legal-name sanctions screening (OFAC/UN/EU/UK), product recalls (barcode or keywords) and EU-Ready (Safety Gate, GPSR, ECB price)…

  • invoice_duplicate_check

    [PAID $0.005 USDC/call, x402, eip155:8453] Compare up to 1000 caller-supplied invoice records for repeated supplier/reference/document identity and conflicting amounts or currency. Exact decimal strings; no external calls, accounting…

  • migration_compare

    [PAID $0.010 USDC/call, x402, eip155:8453] Compare two supplied JSON exports using unique string key fields. Report additions, removals and changed fields, keeping missing/null/boolean/number distinct. No database access or writes; source…

  • incident_timeline

    [PAID $0.005 USDC/call, x402, eip155:8453] Order up to 1000 supplied agent events in UTC, preserve undated events, remove identical retransmissions and reject conflicting event IDs. Evidence links are references only; chronology does not…

  • data_freshness_check

    [PAID $0.003 USDC/call, x402, eip155:8453] Evaluate supplied observation timestamps against caller-declared TTL and the server clock, or an explicitly supplied historical reference. Return…

  • field_provenance_check

    [PAID $0.004 USDC/call, x402, eip155:8453] Inspect up to 1000 supplied product fields and sources: missing references, declared expiry, future or undated observations, and content identity hashes. References are never fetched; neither…

  • quote_cost_normalize

    [PAID $0.008 USDC/call, x402, eip155:8453] Normalize exact decimal quote amounts using supplied currency rates. Up to 1000 total line items. Missing shipping, tax or other costs stay unknown. Rank only complete quotes for identical…

  • renewal_cohort_check

    [PAID $0.006 USDC/call, x402, eip155:8453] Compute UTC monthly cohorts and one declared renewal cycle per supplied subscription. Eligible at supplied due date plus grace; a matching confirmation is a declaration, never proof of…

  • api_contract_diff

    [PAID $0.005 USDC/call, x402, eip155:8453] Diff two supplied OpenAPI 3.0.x/3.1.x documents: operations, parameters, response codes and a listed inline JSON-schema subset. At most 1000 operations/document, 12 schema levels and 4000…

  • declared_ingredient_diff

    [PAID $0.004 USDC/call, x402, eip155:8453] Compare two supplied dated ingredient lists for the same declared product: added/removed normalized names, order and exact declared percentage changes. Up to 1000 ingredients/list; Unicode…

  • demand_lot_match

    [PAID $0.005 USDC/call, x402, eip155:8453] Compare up to 100 supplied demand lines with 1000 supplied lots, at most 5000 same-item comparisons. Exact decimal quantity, same declared item ID/unit and exact required attributes; missing…

  • availability_intersection

    [PAID $0.004 USDC/call, x402, eip155:8453] Intersect supplied availability for 1-100 participants, up to 1000 total intervals. Explicit offsets and at most microsecond precision; optional IANA zone is an assertion that supplied offsets…

  • product_content_impact

    [PAID $0.004 USDC/call, x402, eip155:8453] Diff supplied snapshots of one declared product and trace changes through supplied content-to-field dependencies. Up to 1000 fields/snapshot, 1000 content records and 10000 dependency references…

  • stock_replenishment_scenarios

    [PAID $0.006 USDC/call, x402, eip155:8453] Simulate supplied daily demand and planned receipts with a declared reorder-point/order-up-to policy, lead time, minimum order and exact lot multiple. Up to 10 scenarios, 365 contiguous…

  • declared_order_delays

    [PAID $0.004 USDC/call, x402, eip155:8453] Reconcile up to 1000 supplied orders and 1000 uniquely identified delivery events at an explicit as-of time. Exact same-unit quantities, deadline, partial/completed delivery, overdelivery and…

  • reservation_record_check

    [PAID $0.005 USDC/call, x402, eip155:8453] Compare up to 100 supplied reservation confirmations with 1000 supplied registry rows, capped at 10000 resource comparisons. Exact reservation/resource IDs and UTC intervals; expose…

The first 60 of 61, as the server listed them.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "agent-hub": {
      "type": "http",
      "url": "https://gogeta2-u35175.vm.elestio.app/agents/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http novarithm https://gogeta2-u35175.vm.elestio.app/agents/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://gogeta2-u35175.vm.elestio.app/agents/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.