mcpField
V
VaultRubric

VaultRubric

Remote
vaultrubric.comFinance1Updated 2w ago

About VaultRubric

VaultRubric is a free, public, read-only MCP server for comparing crypto exchanges, wallets, savings accounts, and brokerages. It returns sourced facts, scoring details, incidents, and comparison verdicts for people researching where to hold or invest money.

Key features

  1. 01List categories and platform counts
  2. 02Search platforms by query or category
  3. 03Retrieve sourced facts and scores
  4. 04Compare platforms with optional weights
  5. 05Check security incidents and regulatory actions

Use cases

  1. 01Compare crypto exchanges or wallets
  2. 02Review savings account and brokerage options
  3. 03Check a platform’s incident and safety record

MCP support

The hosted MCP server exposes read-only tools for category listing, platform search and details, comparisons, published verdicts, and safety checks. It requires no authentication and provides sources and attribution with responses.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://vaultrubric.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

11

This tool takes no parameters.

Details

From the project README

VaultRubric MCP server

smithery badge

VaultRubric

Free, public, read-only Model Context Protocol server for VaultRubric. VaultRubric publishes evidence-based comparisons of where to keep money: crypto exchanges, hardware and software wallets, high-yield savings accounts, and brokerages/IRAs.

The server is hosted by VaultRubric, so there is nothing to install. This repo only holds the listing metadata.

Tools

ToolWhat it returns
list_categoriesCategories and platform counts
search_platforms(query, category)Matching platforms with score and data coverage
get_platform(name)Sourced facts, per-criterion scores with basis and source URLs, incidents, as-of dates
compare_platforms(platforms, weights)2–6 platforms in one category with optional 0–10 weights. Applies the 75% coverage gate, the 60% hack cap and the too-close-to-call (<3 pts) rule
get_verdict(slug)Published answer for a comparison page, e.g. coinbase-vs-kraken
check_platform_safety(platform)Customer-funds hacks, incidents, regulatory actions, security score, with sources

Older names compare and is_safe still work as aliases. Every tool declares an outputSchema and returns matching structuredContent. Every response includes "attribution": "Source: VaultRubric (vaultrubric.com)" and the relevant page URLs. Scoring rules: https://vaultrubric.com/methodology

Connect

Claude (claude.ai / Desktop): Settings → Connectors → Add custom connector → https://vaultrubric.com/mcp Claude Code: claude mcp add --transport http vaultrubric https://vaultrubric.com/mcp ChatGPT (developer mode): Settings → Connectors → Create → MCP server URL https://vaultrubric.com/mcp, no authentication. For a custom GPT, import the OpenAPI spec as an Action. Cursor / other clients (mcp.json):

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

Raw request:

curl -s https://vaultrubric.com/mcp -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"check_platform_safety","arguments":{"platform":"Coinbase"}}}'

License and attribution

The data is free to use, cite and redistribute with attribution: "Source: VaultRubric (vaultrubric.com)", linking the page or data file used. See LICENSE. The data is informational only and is not investment, tax or legal advice. Facts carry as-of dates and can change.

Contact: [email protected]

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.