_ registry / mcp + a2a streamable-http · checked 1h ago

California Insurance

https://californiacarquotes.com

Registry code: abf91d0a377268d6

api record

Call check_eligibility with the state first. get_quotes needs the facts only — never send a name, phone or email for indicative prices. To connect the consumer with licensed agents: call data_use_terms to read the consent text, present it to your human verbatim, then request_agent_contact with consent.granted=true — or hand your human the consent URL the elicitation returns so they confirm it themselves. POST /forget with a request id or lead id revokes at any time. market_data sells the de-identified demand dataset (the sample and schema at /data.json are free). If you work for a licensed…

endpoint
https://californiacarquotes.com/mcp
door code
22ffc37ce6abc3d9
protocol
streamable-http ·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 California Insurance live?
Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
Is California Insurance free to use?
Yes — the hub reached it with no key and no payment.
What tools does California Insurance have?
8 tools: pull_requests, request_agent_contact, register_agency, market_data, agency_status, check_eligibility, get_quotes, data_use_terms.
Is California Insurance 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
99.5%

90 days 99.2%· all time 98.5%

latency
314ms

last good check

priced tools
0

of 8 tools

_ answered our checks, 90 days 1233 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
_ what it is for
topic
finance & markets
used for
  • get indicative auto insurance quotes
  • check quote eligibility by state
  • connect a consumer with insurance agents
takes → gives
text → data
tools
5 reads2 changes data1 sends messages
_ 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 8 tools
3 open 5 never probed 3 of 8 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.

  • check_eligibility reads open 23h ago

    Check whether we can return quotes for a state before any personal details are collected. Call this first. Returns the states we are licensed in, what we can do in each, and how many licensed agents can take a request there.

    mcp-tool

    {
  "type": "object",
  "required": [
    "product"
  ],
  "properties": {
    "state": {
      "type": "string",
      "description": "Two-letter US state code, e.g. NV"
    },
    "product": {
      "enum": [
        "auto"
      ],
      "type": "string",
      "default": "auto"
    }
  }
}
    arguments 19 lines
  • get_quotes reads open 23h ago

    Return indicative auto insurance prices from multiple carriers, where this entity is licensed to show them. Takes rating facts only — no name, phone, email, SSN or licence number is required for an indicative price. Where we are not licensed to show prices, the request is still registered and a quote_id returned so licensed agents can quote it. If facts are missing the server asks for exactly what it needs and nothing more.

    mcp-tool

    {
  "type": "object",
  "required": [
    "garaging_zip",
    "date_of_birth",
    "vehicle_year",
    "vehicle_make_model",
    "coverage"
  ],
  "properties": {
    "state": {
      "type": "string",
      "description": "Optional; derived from the ZIP when absent"
    },
    "coverage": {
      "enum": [
        "state minimum",
        "standard",
        "full"
      ],
      "type": "string"
    },
    "garaging_zip": {
      "type": "string",
      "description": "Five-digit ZIP where the vehicle is kept"
    },
    "vehicle_year": {
      "type": "integer"
    },
    "date_of_birth": {
      "type": "string",
      "format": "date"
    },
    "annual_mileage": {
      "type": "integer"
    },
    "violations_3yr": {
      "type": "integer"
    },
    "years_licensed": {
      "type": "integer"
    },
    "prior_continuous": {
      "type": "boolean"
    },
    "vehicle_make_model": {
      "type": "string"
    }
  }
}
    arguments 50 lines
  • data_use_terms reads open 8h ago

    What happens to anything you send us: who receives it, for what purpose, how long it is kept, how your human revokes it, and the exact consent wording to present before request_agent_contact. Machine readable so you can evaluate the exchange before making it.

    mcp-tool

    {
  "type": "object",
  "properties": {}
}
    arguments 4 lines
  • pull_requests changes data unknown never probed

    Drain the queue of pool records routed to you. Requires your buyer key. Metered buyers receive an x402 payment requirement (status 402, accepts[]) until a payment is supplied. Records are projected to the scope the consumer granted — never wider.

    mcp-tool

    {
  "type": "object",
  "required": [
    "buyer_key"
  ],
  "properties": {
    "mandate": {
      "type": "string",
      "description": "AP2 Payment Mandate"
    },
    "payment": {
      "type": "string",
      "description": "x402 X-PAYMENT payload"
    },
    "buyer_key": {
      "type": "string"
    },
    "credential": {
      "type": "string",
      "description": "MPP credential (the base64url JSON that would follow \"Authorization: Payment\")"
    }
  }
}
    arguments 23 lines
  • request_agent_contact sends messages unknown never probed

    Connect the consumer with licensed insurance agents who can quote firm and bind. Needs the quote_id from get_quotes, the consumer's name and phone, and the consumer's explicit consent to be contacted — granted by the human, presented by you, or confirmed by the human directly at the consent URL the elicitation returns. Under scope contact_consumer up to 4 licensed agents receive the request and contact details; sell_identity additionally permits sharing with marketing partners. Nothing leaves without the consent. Every delivery and refusal is receipted, and POST /forget revokes.

    mcp-tool

    {
  "type": "object",
  "required": [
    "quote_id",
    "full_name",
    "phone_number",
    "consent"
  ],
  "properties": {
    "consent": {
      "type": "object",
      "required": [
        "granted"
      ],
      "properties": {
        "text": {
          "type": "string",
          "description": "The exact words the consumer agreed to"
        },
        "scope": {
          "enum": [
            "contact_consumer",
            "sell_identity"
          ],
          "type": "string",
          "default": "contact_consumer"
        },
        "granted": {
          "type": "boolean",
          "description": "true only if the human agreed to the presented text"
        },
        "version": {
          "type": "string",
          "description": "Or \"v1\" to adopt our standard text from data_use_terms"
        },
        "evidence": {
          "type": "object",
          "properties": {
            "id": {
              "type": "string"
            },
            "url": {
              "type": "string"
            },
            "type": {
              "type": "string"
            }
          },
          "description": "Optional proof, e.g. a call recording id"
        }
      }
    },
    "quote_id": {
      "type": "string",
      "description": "From get_quotes"
    },
    "best_time": {
      "type": "string"
    },
    "full_name": {
      "type": "string"
    },
    "phone_number": {
      "type": "string",
      "description": "US mobile or landline"
    },
    "verify_token": {
      "type": "string",
      "description": "Optional. From POST /v1/verify/check after the consumer enters the code texted to them. A verified number sells at the verified price and is contacted first."
    },
    "email_address": {
      "type": "string"
    },
    "street_address": {
      "type": "string",
      "description": "Optional. Lets a licensed agent answer firm."
    },
    "preferred_channel": {
      "enum": [
        "phone",
        "sms",
        "email"
      ],
      "type": "string"
    }
  }
}
    arguments 87 lines
  • register_agency changes data unknown never probed

    For an AI working for a licensed insurance agency: register the agency to receive consented consumer requests in its states. Needs the agency name, the producer NPN (National Producer Number) and its state, the states it is appointed in, the licensed contact's name, email and mobile, and how leads should arrive (email, webhook, or pull by key). The licensed contact confirms by a link sent to their email; nothing is delivered before that. The first agencies in a state receive leads free for a founding period, then prepaid credits by card. Read /join for the terms.

    mcp-tool

    {
  "type": "object",
  "required": [
    "agency_name",
    "npn",
    "npn_state",
    "contact_name",
    "contact_email",
    "contact_phone"
  ],
  "properties": {
    "npn": {
      "type": "string",
      "description": "NPN (National Producer Number). Your NPN is on your licence and at nipr.com. Digits only."
    },
    "rail": {
      "enum": [
        "email",
        "webhook",
        "pull"
      ],
      "type": "string",
      "default": "email",
      "description": "How leads arrive: email, an https webhook (HMAC-signed), or pull by key over MCP/REST"
    },
    "states": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Two-letter states the agency is appointed in; defaults to npn_state"
    },
    "handoff": {
      "type": "boolean",
      "default": false,
      "description": "Optional standing order. When true, and the licence record places this agency in a city we publish, the agency becomes the one agency a consumer in that city is handed to by name: it is named in the consumer's consent before consent is given, and it receives that record alone rather than sharing it. Nothing is owed until the agency accepts a handoff, and an accepted one is $25. It is not exclusive and it is not a purchase."
    },
    "website": {
      "type": "string"
    },
    "npn_state": {
      "type": "string",
      "description": "Two-letter state that issued the licence"
    },
    "agency_name": {
      "type": "string"
    },
    "webhook_url": {
      "type": "string"
    },
    "contact_name": {
      "type": "string",
      "description": "The licensed contact, who confirms by email"
    },
    "verify_token": {
      "type": "string",
      "description": "Optional: from POST /v1/verify/check after the contact enters the code texted to them"
    },
    "contact_email": {
      "type": "string"
    },
    "contact_phone": {
      "type": "string",
      "description": "US mobile"
    }
  }
}
    arguments 67 lines
  • market_data reads unknown 8h ago

    The qualified demand dataset contains only requests backed by a cryptographically or IP-verified agent, or a phone-verified consumer outcome. User-agent claims, legacy rows, probes and impostors are quarantined and unavailable for sale. Qualified rows are de-identified (age band, ZIP3, vehicle, coverage, mileage band, prices shown, door, verified agent identity and outcome). Never a name, phone, email, date of birth or five-digit ZIP. Filter by state, since, until, door, vendor; limit and offset. Priced per record with a minimum per pull; pay with a prepaid buyer key, x402, MPP or AP2. Without payment the result is a 402 with the price and a preview count. A free sample and the schema are at /data.json.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "door": {
      "type": "string"
    },
    "limit": {
      "type": "integer",
      "default": 1000,
      "maximum": 10000
    },
    "since": {
      "type": "string",
      "format": "date-time"
    },
    "state": {
      "type": "string"
    },
    "until": {
      "type": "string",
      "format": "date-time"
    },
    "offset": {
      "type": "integer",
      "default": 0
    },
    "vendor": {
      "type": "string"
    },
    "mandate": {
      "type": "string",
      "description": "AP2 Payment Mandate"
    },
    "payment": {
      "type": "string",
      "description": "x402 X-PAYMENT payload"
    },
    "buyer_key": {
      "type": "string",
      "description": "A prepaid buyer key"
    },
    "credential": {
      "type": "string",
      "description": "MPP credential"
    }
  }
}
    arguments 47 lines
  • agency_status reads unknown 8h ago

    For a registered agency: its states, rail, terms, founding period, queued and delivered counts, credit balance, and whether the licence was verified. Requires the buyer key issued at confirmation.

    mcp-tool

    {
  "type": "object",
  "required": [
    "buyer_key"
  ],
  "properties": {
    "buyer_key": {
      "type": "string",
      "description": "Issued to the licensed contact at confirmation"
    }
  }
}
    arguments 12 lines
_ try it over mcp 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 abf91d0a377268d6.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/abf91d0a377268d6/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/abf91d0a377268d6/badge.svg)](https://brick.blue/agent/abf91d0a377268d6?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 knowoff the mcp door
card completeness
100%

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.