Skip to content
VaultRubric logo

VaultRubric MCP server

Which MCP servers are VaultRubric'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 2026-10-27

← Back to VaultRubric

Whose server it is
  • Registry namecom.vaultrubric/vaultrubricverified in the MCP registry

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

When we asked itchecked 2026-10-27
  • Stateanswerschecked 2026-10-27
  • Tools11
  • Server calls itselfvaultrubric
  • Server version1.0.1
  • Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 345 ms.

Should an agent connect itSkip it
  • Its tools do none of the product's use cases we checked: compare a dealer quote against a fair out-the-door price; draft counter-offer texts to send the salesperson; compare up to five cars before signing.
  • Checked on 6 of the 7 days it takes to judge reliability.

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: 6, the first on 2026-10-27
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 6 so far
  • What an agent can do with it0 of 3 use cases
  • Use1 GitHub stars
  • Answeredmeasuring6 of the 7 daily checks it takes to print a share
  • Median first answer135 ms
  • Space in an agent's context≈ 1,475 tokensthe definitions of all its tools (11), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results11 of 11 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • cannot · compare a dealer quote against a fair out-the-door price
  • cannot · draft counter-offer texts to send the salesperson
  • cannot · compare up to five cars before signing

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 offers11 tools · read 2026-10-27
  • list_categories

    List VaultRubric's public categories (high-yield savings, brokerages, crypto exchanges, hardware/software wallets) with platform counts and data URLs.

  • search_platforms

    Search tracked platforms by name and/or category; returns VaultRubric score, data coverage and pick eligibility.

  • get_platform

    Full sourced record for one platform: per-criterion scores with basis and source URLs, incidents, regulatory actions, as-of dates, and related page URLs.

  • compare_platforms

    Compare 2-6 platforms in one category with optional criterion weights. Applies VaultRubric's 75% coverage gate, 60% hack cap and too-close-to-call (<3 points) rules.

  • get_verdict

    Get the published verdict (direct answer, key facts, as-of date, URL) for a VaultRubric comparison page.

  • check_platform_safety

    Safety record for a platform: customer-funds hacks, incidents, regulatory actions and security score, with sources and the safety page URL.

  • calculate_savings_interest

    Project interest on a balance over N months at every high-yield savings account VaultRubric tracks, using sourced standard APYs (promos shown separately), minimum balances and monthly fees. Estimates, not advice.

  • estimate_fees

    Estimate annual cost at every brokerage or crypto exchange VaultRubric tracks from sourced fees (commissions, options per-contract, transfer-out; exchange taker fees). Unknown fees are flagged, never assumed.

  • get_market_movers

    Top crypto (24h, CoinGecko) or US stock (delayed, Yahoo/Nasdaq) gainers and losers, each with the latest sourced headline that names it. News and data only, not advice.

  • get_ipo_calendar

    Upcoming and recently priced IPOs (Nasdaq IPO calendar) with price ranges, exchanges and first-day results, plus the latest SEC EDGAR S-1/F-1 filings.

  • get_asset_news

    Delayed price and latest headlines (Google News, with source URLs) for a stock ticker or a top-250 crypto asset. Headlines are quoted as reported; no predictions.

How to connect

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

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

Add it

Claude Code, in a terminal

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

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://vaultrubric.com/mcp as a custom connector in the settings.

OpenAPI spec

8 paths, read 2026-10-27. Open the spec ↗

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.