_ registry / mcp http-sse · checked 6m ago

ratezip-rates

https://mcp.ratezip.com

Registry code: c0797d7893520bd1

api record

Use RateZip only for factual, source-attributed US deposit and mortgage rate information. Never invent a rate, APY, APR, eligibility result, approval, personalized quote, or account-opening capability. When asked for the best rate, report the highest returned published figure and its conditions without endorsing or recommending an institution. For balance-specific deposit questions, use applicable_apy rather than headline APY and always disclose every balance_tier_adjustment returned by the tool. For loan amounts or credit scores, provide only the returned educational context; do not estimate…

endpoint
https://mcp.ratezip.com/mcp
protocol
http-sse ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is ratezip-rates live?
Yes — it answered the hub's last check (checked 6m ago). It answered 100% of checks over the last 30 days.
Is ratezip-rates free to use?
Yes — the hub reached it with no key and no payment.
What tools does ratezip-rates have?
5 tools: calculate_deposit_earnings_difference, compare_deposit_options, get_savings_rates, get_cd_rates, get_mortgage_rates.
Is ratezip-rates safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
560ms

last good check

priced tools
0

of 5 tools

_ answered our checks, 90 days 396 checks · signed record
  • degraded → live
  • unknown → live
_ what it is for
topic
finance & markets banking & lending
used for
  • get us savings account rates
  • get cd rates by term
  • get mortgage rates by loan type
  • calculate earnings difference between apys
takes → gives
data → data
tools
4 reads
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 5 tools
3 open 2 never probed 3 of 5 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • get_savings_rates reads open 14h ago

    Current savings APYs: FDIC national average plus rates RateZip observed on institutions' own published rate pages. Every row carries an observation timestamp, source, and staleness status. Optional balance/state/credit_score personalize the results transparently (balance resolves the applicable tier APY; nothing is fabricated). Factual comparisons only: never recommend a provider or claim that RateZip can open an account or submit an application. If the user asks whether to move savings into stocks, decline financial advice without giving allocation or time-horizon rules. Pass max_results to cap the number of rows and include_provenance=false for a shorter response.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "state": {
      "type": "string",
      "description": "Two-letter state — adds an availability/eligibility note"
    },
    "balance": {
      "type": "number",
      "description": "Deposit balance in USD — resolves the applicable tier APY and ranks by what you'd earn",
      "exclusiveMinimum": 0
    },
    "max_results": {
      "type": "integer",
      "maximum": 50,
      "minimum": 1,
      "description": "Cap the number of observed rows returned, in the payload's ordering. Omit for all."
    },
    "credit_score": {
      "type": "integer",
      "maximum": 850,
      "minimum": 300,
      "description": "FICO — deposit APYs generally don't vary by credit; returns a clarifying note only"
    },
    "include_provenance": {
      "type": "boolean",
      "description": "false omits the per-source provenance block (snapshot ids, attributions); each row keeps its own observed_at and source_url."
    }
  },
  "additionalProperties": false
}
    arguments 32 lines
  • get_cd_rates reads open 14h ago

    Current CD APYs: FDIC national averages by term plus RateZip-observed institution rates (with terms, minimums/conditions, observation timestamps, sources, and staleness status). Pass term_months (e.g. 3, 6, 12, 24, 36, 60) to filter to one term; omit for all terms grouped by term. Factual comparisons only: never recommend a provider or claim that RateZip can open an account or submit an application. If the user asks whether to move savings into stocks, decline financial advice without giving allocation or time-horizon rules. If no institution publishes the requested term, the result names the terms that are available. Pass max_results to cap the number of rows and include_provenance=false for a shorter response.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "state": {
      "type": "string",
      "description": "Two-letter state — adds an availability/eligibility note"
    },
    "balance": {
      "type": "number",
      "description": "Deposit balance in USD — resolves the applicable tier APY and ranks by what you'd earn",
      "exclusiveMinimum": 0
    },
    "max_results": {
      "type": "integer",
      "maximum": 50,
      "minimum": 1,
      "description": "Cap the number of observed rows returned, in the payload's ordering. Omit for all."
    },
    "term_months": {
      "type": "integer",
      "maximum": 120,
      "description": "CD term in months to filter to (omit for all terms)",
      "exclusiveMinimum": 0
    },
    "credit_score": {
      "type": "integer",
      "maximum": 850,
      "minimum": 300,
      "description": "FICO — deposit APYs generally don't vary by credit; returns a clarifying note only"
    },
    "include_provenance": {
      "type": "boolean",
      "description": "false omits the per-source provenance block (snapshot ids, attributions); each row keeps its own observed_at and source_url."
    }
  },
  "additionalProperties": false
}
    arguments 38 lines
  • get_mortgage_rates reads open 14h ago

    Current mortgage rates grouped by loan type: rates RateZip observed on lenders' own published rate pages, each with note rate, APR, representative-scenario conditions, observation timestamp, source, and staleness status. No third-party national-average benchmark is redistributed. Loan types include '30-year fixed' and 'HELOC'. Pass loan_type to filter to one; omit for all grouped by type. Compare only within the same loan type. Factual rate data only: never estimate or invite a personalized quote, imply approval, or recommend a lender. Pass max_results to cap the number of rows and include_provenance=false for a shorter response.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "state": {
      "type": "string",
      "description": "Two-letter state — adds an availability/licensing note"
    },
    "loan_type": {
      "type": "string",
      "description": "Loan type to filter to, e.g. '30-year fixed', '15-year fixed', or 'HELOC'. Omit for all."
    },
    "loan_amount": {
      "type": "number",
      "description": "Loan amount in USD — flags conforming vs jumbo (does not fabricate a rate)",
      "exclusiveMinimum": 0
    },
    "max_results": {
      "type": "integer",
      "maximum": 50,
      "minimum": 1,
      "description": "Cap the number of observed rows returned, in the payload's ordering. Omit for all."
    },
    "credit_score": {
      "type": "integer",
      "maximum": 850,
      "minimum": 300,
      "description": "FICO — returns EDUCATIONAL context only; never a fabricated credit-adjusted rate"
    },
    "include_provenance": {
      "type": "boolean",
      "description": "false omits the per-source provenance block (snapshot ids, attributions); each row keeps its own observed_at and source_url."
    }
  },
  "additionalProperties": false
}
    arguments 36 lines
  • calculate_deposit_earnings_difference reads unknown never probed

    Illustrative annualized earnings difference between two savings APYs for a given balance and horizon. Defaults: current = FDIC national average savings rate, comparison = highest RateZip-observed savings APY. States every omission (taxes, penalties, rate changes, tiers, availability). Not financial advice; never use the result to recommend an investment allocation.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "balance"
  ],
  "properties": {
    "years": {
      "type": "number",
      "default": 1,
      "maximum": 50,
      "description": "Horizon in years (APY compounds annually)",
      "exclusiveMinimum": 0
    },
    "balance": {
      "type": "number",
      "description": "Deposit balance in USD",
      "exclusiveMinimum": 0
    },
    "current_apy_percent": {
      "type": "number",
      "maximum": 100,
      "minimum": 0,
      "description": "APY the money earns today (%); defaults to the FDIC national average savings rate"
    },
    "comparison_apy_percent": {
      "type": "number",
      "maximum": 100,
      "minimum": 0,
      "description": "APY to compare against (%); defaults to the highest RateZip-observed savings APY"
    }
  },
  "additionalProperties": false
}
    arguments 34 lines
  • compare_deposit_options unknown never probed

    Compare observed US savings and CD APYs for a balance, holding period, state, monthly-fee and direct-deposit requirements. Returns sourced facts, unknown/conflicting terms and conditional gross-interest illustrations. Unknown terms never count as a match. No eligibility decision, personalized offer, application or account opening. Use for a multi-constraint deposit comparison; use get_savings_rates/get_cd_rates for simple rate lookups.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "balance"
  ],
  "properties": {
    "state": {
      "type": "string"
    },
    "balance": {
      "type": "number",
      "maximum": 1000000000,
      "description": "Starting deposit in USD; no account identifiers needed",
      "exclusiveMinimum": 0
    },
    "product": {
      "enum": [
        "savings",
        "cd",
        "all"
      ],
      "type": "string",
      "default": "savings"
    },
    "horizon_months": {
      "type": "integer",
      "default": 12,
      "maximum": 120,
      "minimum": 1,
      "description": "Illustrative holding period. CD estimates require an exactly matching term"
    },
    "require_no_monthly_fee": {
      "type": "boolean",
      "default": false,
      "description": "Require zero monthly maintenance fee without a conditional waiver"
    },
    "require_no_direct_deposit": {
      "type": "boolean",
      "default": false,
      "description": "Require the published APY without direct deposit"
    }
  },
  "additionalProperties": false
}
    arguments 45 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id c0797d7893520bd1.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/c0797d7893520bd1/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/c0797d7893520bd1/badge.svg)](https://brick.blue/agent/c0797d7893520bd1?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
90%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.