_ registry / mcp + a2a streamable-http · checked 2h ago

com.secondappraisal/total-loss-intake

https://secondappraisal.com

Registry code: 38c51edcc5698396

api record

SecondAppraisal helps vehicle owners whose insurer declared their car a total loss get a fair settlement.

Use `submit_total_loss_intake` when a user wants help with a total-loss offer: send at least a phone or email, plus whatever vehicle / loss / offer details you have. Read `customer_message` back to the user verbatim — it carries the confirm link and tells them we will call to confirm.

endpoint
https://secondappraisal.com/mcp
door code
20d718c2b5f518b1
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 com.secondappraisal/total-loss-intake live?
Yes — it answered the hub's last check (checked 2h ago). It answered 99% of checks over the last 30 days.
Is com.secondappraisal/total-loss-intake free to use?
Yes — the hub reached it with no key and no payment.
What tools does com.secondappraisal/total-loss-intake have?
5 tools: upload_valuation_report, get_preliminary_estimate, get_state_total_loss_rules, get_intake_status, submit_total_loss_intake.
Is com.secondappraisal/total-loss-intake 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
98.7%

90 days 98.9%· all time 99%

latency
617ms

last good check

priced tools
0

of 5 tools

_ answered our checks, 90 days 998 checks · signed record
  • degraded → live
  • live → degraded· HTTP 503
  • degraded → live
  • live → degraded· HTTP 503
  • degraded → live
_ what it is for
topic
iot & hardware vehicles & automotive
used for
  • submit a vehicle total loss claim for review
  • get a preliminary vehicle value estimate
  • look up state total loss rules
  • upload an insurer valuation report
takes → gives
text, documents → data, text
tools
3 reads2 changes data
_ 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

inferred, not observed

Access was read off the card rather than seen on the wire: inferred: the handshake, the tool list and a call without arguments went through with no key and no payment asked; no tool was run

_ what it can do 5 tools
5 never probed 0 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.

  • upload_valuation_report changes data unknown never probed

    Attach the insurer's Market Valuation Report (CCC / Mitchell PDF) to a submitted intake. We parse it (vehicle, mileage, offer, insurer, loss date) and refresh the preliminary. Allow up to two minutes.

    mcp-tool

    {
  "type": "object",
  "required": [
    "intake_id",
    "poll_token",
    "file_name",
    "file_base64"
  ],
  "properties": {
    "file_name": {
      "type": "string",
      "maxLength": 200,
      "minLength": 1,
      "description": "Original file name, e.g. valuation-report.pdf."
    },
    "intake_id": {
      "type": "string",
      "minLength": 1,
      "description": "The `intake_id` from a previous submission."
    },
    "poll_token": {
      "type": "string",
      "minLength": 1,
      "description": "The `poll_token` returned once on that submission."
    },
    "file_base64": {
      "type": "string",
      "minLength": 1,
      "description": "The PDF bytes, base64-encoded (standard or URL-safe alphabet). Up to 15 MB decoded."
    }
  },
  "additionalProperties": false
}
    arguments 33 lines
  • get_preliminary_estimate reads unknown 2h ago

    A no-commitment early market read for a vehicle: comparable listing prices near the customer (10th percentile / median / 90th), an odometer-adjusted mid, and the gap vs the insurer's offer. Not an appraisal. Nothing is stored about the customer.

    mcp-tool

    {
  "type": "object",
  "required": [
    "year",
    "make",
    "model"
  ],
  "properties": {
    "zip": {
      "type": "string",
      "pattern": "^\\d{5}(-\\d{4})?$",
      "description": "Preferred; searches comparables near here."
    },
    "make": {
      "type": "string",
      "maxLength": 60,
      "minLength": 1
    },
    "trim": {
      "type": "string",
      "maxLength": 80,
      "minLength": 1
    },
    "year": {
      "type": "integer",
      "maximum": 2100,
      "minimum": 1900
    },
    "model": {
      "type": "string",
      "maxLength": 80,
      "minLength": 1
    },
    "state": {
      "type": "string",
      "maxLength": 2,
      "minLength": 2,
      "description": "Two-letter state; used when no zip is given."
    },
    "odometer": {
      "type": "integer",
      "maximum": 2000000,
      "minimum": 0
    },
    "acv_offer_cents": {
      "type": "integer",
      "minimum": 0,
      "description": "Insurer's offer in cents, to report the gap."
    }
  },
  "additionalProperties": false
}
    arguments 52 lines
  • get_state_total_loss_rules reads unknown 2h ago

    State-specific total-loss facts: threshold and method, whether an independent appraiser must be licensed there, whether third-party appraisals are allowed, statute citations, must-know rights, common pitfalls, and the consumer hotline. For New York and Vermont, appraiser_license_required is null because we don't act as the appraiser there and state no license requirement either way; appraiser_note says so.

    mcp-tool

    {
  "type": "object",
  "required": [
    "state"
  ],
  "properties": {
    "state": {
      "type": "string",
      "maxLength": 40,
      "minLength": 2,
      "description": "Two-letter code (TX) or state name (Texas)."
    }
  },
  "additionalProperties": false
}
    arguments 15 lines
  • get_intake_status reads unknown 2h ago

    Fetch the current receipt for a submitted intake (status, confirm link while still confirmable, preliminary).

    mcp-tool

    {
  "type": "object",
  "required": [
    "intake_id",
    "poll_token"
  ],
  "properties": {
    "intake_id": {
      "type": "string",
      "minLength": 1,
      "description": "The `intake_id` from a previous submission."
    },
    "poll_token": {
      "type": "string",
      "minLength": 1,
      "description": "The `poll_token` returned once on that submission."
    }
  },
  "additionalProperties": false
}
    arguments 20 lines
  • submit_total_loss_intake changes data unknown never probed

    Submit a vehicle owner's total-loss situation to SecondAppraisal on their behalf. Minimum: one of customer.phone / customer.email, your `agent` self-identification, and a `consent.attestation`. Returns a receipt with `customer_confirmation_url` (one tap confirms), a relayable `customer_message`, an optional `preliminary` market read, `contact_policy` (we will email/text a welcome and a person will call to confirm the request came from the customer or their agent), and `pricing` — the consultation is free; if the owner wants more, Appraisal Research is $199 (paid up front, no guarantee) or the Appointed Appraiser Service (our Appraisal Research, appointment as the customer's appraiser under the policy's appraisal clause, determining the amount of loss with the insurer's appraiser, and the appraisal award letter) is $495 with a $25 discount for customers you send ($470; a card HOLD, not a charge). The guarantee applies once SecondAppraisal accepts the consultation and serves as the customer's appraiser: if the appraisal award, or a higher offer the insurer makes instead, is less than $1,000 above the insurer's offer on the day SecondAppraisal accepted, the fee is waived and the hold released. An umpire's fee, if one is needed, is separate. The $25 applies to the Appointed Appraiser Service (`representation`) only. You may quote `pricing` verbatim; payment always happens on our site by the customer's own click (`checkout` links appear once they have confirmed) — never collect card details. Read `customer_message` to the user verbatim.

    mcp-tool

    {
  "type": "object",
  "required": [
    "agent",
    "customer",
    "consent"
  ],
  "properties": {
    "loss": {
      "type": "object",
      "properties": {
        "zip": {
          "type": "string",
          "pattern": "^\\d{5}(-\\d{4})?$",
          "description": "US ZIP code (5 or 5+4). Used to search comparable vehicles near the customer."
        },
        "loss_state": {
          "type": "string",
          "maxLength": 2,
          "minLength": 2,
          "description": "State where the loss occurred / the policy is written."
        },
        "date_of_loss": {
          "type": "string",
          "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
          "description": "Calendar date, YYYY-MM-DD."
        },
        "insurance_path": {
          "enum": [
            "own",
            "at-fault",
            "unknown",
            "none"
          ],
          "type": "string",
          "description": "Whose insurance is handling it: own (customer's carrier), at-fault (the other driver's carrier), unknown, or none (no insurance claim — valuation only)."
        }
      },
      "description": "When and where the loss happened.",
      "additionalProperties": false
    },
    "agent": {
      "type": "object",
      "required": [
        "name",
        "platform"
      ],
      "properties": {
        "name": {
          "allOf": [
            {
              "type": "string",
              "maxLength": 120
            },
            {
              "type": "string",
              "maxLength": 120,
              "minLength": 1
            }
          ],
          "description": "Human-readable name of the agent or product submitting on the customer's behalf (e.g. \"OpenClaw\", \"Acme Claims Copilot\"). Shown to the customer."
        },
        "version": {
          "type": "string",
          "maxLength": 60,
          "minLength": 1,
          "description": "Agent / integration version string."
        },
        "platform": {
          "type": "string",
          "pattern": "^[a-z0-9][a-z0-9-]{0,59}$",
          "description": "Platform slug for attribution. Known values: openclaw, chatgpt, claude, gemini, copilot, perplexity, custom. Any lowercase slug is accepted."
        },
        "operator_url": {
          "type": "string",
          "format": "uri",
          "maxLength": 300,
          "description": "Homepage or documentation URL of the agent operator."
        }
      },
      "description": "Who is calling. Required — an intake without self-identification is refused.",
      "additionalProperties": false
    },
    "offer": {
      "type": "object",
      "properties": {
        "insurer": {
          "allOf": [
            {
              "type": "string",
              "maxLength": 120
            },
            {
              "type": "string",
              "maxLength": 120,
              "minLength": 1
            }
          ],
          "description": "Insurance company handling the total loss."
        },
        "acv_offer": {
          "type": "number",
          "maximum": 1000000,
          "minimum": 0,
          "description": "Insurer's Actual Cash Value offer in dollars. Converted to cents server-side."
        },
        "claim_number": {
          "type": "string",
          "maxLength": 60,
          "minLength": 1
        },
        "acv_offer_cents": {
          "type": "integer",
          "maximum": 100000000,
          "minimum": 0,
          "description": "Insurer's Actual Cash Value offer in cents. `acv_offer` (dollars) is also accepted."
        }
      },
      "description": "The insurer's position so far, if any.",
      "additionalProperties": false
    },
    "consent": {
      "type": "object",
      "required": [
        "attestation"
      ],
      "properties": {
        "mode": {
          "enum": [
            "customer_directed",
            "warm_handoff"
          ],
          "type": "string",
          "default": "customer_directed",
          "description": "customer_directed: the customer asked their agent to submit this. warm_handoff: a registered agent attests the customer asked to be contacted now (priority callback; requires an API key)."
        },
        "attestation": {
          "type": "string",
          "maxLength": 1000,
          "minLength": 20,
          "description": "The agent's attestation, in its own words, that the customer asked for this submission and knows SecondAppraisal will email/text and call to confirm. Stored verbatim on the intake."
        },
        "attestor_name": {
          "allOf": [
            {
              "type": "string",
              "maxLength": 120
            },
            {
              "type": "string",
              "maxLength": 120,
              "minLength": 1
            }
          ],
          "description": "Who is attesting (the agent, or the person operating it)."
        },
        "notify_customer": {
          "type": "boolean",
          "default": true,
          "description": "true (default): we send the customer our welcome email/text with the confirm link. false: you relay `customer_message` and `customer_confirmation_url` yourself and we send nothing until they confirm or we call."
        }
      },
      "description": "Consent basis. Attestation wording version 2026-09-16.1.",
      "additionalProperties": false
    },
    "vehicle": {
      "type": "object",
      "properties": {
        "vin": {
          "allOf": [
            {
              "type": "string"
            },
            {
              "type": "string",
              "maxLength": 17,
              "minLength": 11
            }
          ],
          "description": "Vehicle Identification Number. A full 17-character VIN lets us decode year/make/model/trim."
        },
        "make": {
          "allOf": [
            {
              "type": "string",
              "maxLength": 60
            },
            {
              "type": "string",
              "maxLength": 60,
              "minLength": 1
            }
          ]
        },
        "trim": {
          "allOf": [
            {
              "type": "string",
              "maxLength": 80
            },
            {
              "type": "string",
              "maxLength": 80,
              "minLength": 1
            }
          ]
        },
        "year": {
          "type": "integer",
          "maximum": 2100,
          "minimum": 1900
        },
        "model": {
          "allOf": [
            {
              "type": "string",
              "maxLength": 80
            },
            {
              "type": "string",
              "maxLength": 80,
              "minLength": 1
            }
          ]
        },
        "plate": {
          "type": "string",
          "maxLength": 12,
          "minLength": 1,
          "description": "License plate. Requires plate_state to resolve a VIN."
        },
        "odometer": {
          "type": "integer",
          "maximum": 2000000,
          "minimum": 0,
          "description": "Odometer reading in miles at the time of loss."
        },
        "plate_state": {
          "type": "string",
          "maxLength": 2,
          "minLength": 2,
          "description": "Two-letter US state code, e.g. TX."
        }
      },
      "description": "The vehicle. A VIN (or plate + plate_state) is best; year/make/model works too.",
      "additionalProperties": false
    },
    "customer": {
      "type": "object",
      "properties": {
        "email": {
          "type": "string",
          "format": "email",
          "maxLength": 254,
          "description": "Customer email address."
        },
        "phone": {
          "allOf": [
            {
              "type": "string"
            },
            {
              "type": "string",
              "pattern": "^[2-9]\\d{9}$"
            }
          ],
          "description": "US mobile or landline number. Punctuation and a leading +1 are tolerated."
        },
        "last_name": {
          "allOf": [
            {
              "type": "string",
              "maxLength": 80
            },
            {
              "type": "string",
              "maxLength": 80,
              "minLength": 1
            }
          ]
        },
        "first_name": {
          "allOf": [
            {
              "type": "string",
              "maxLength": 80
            },
            {
              "type": "string",
              "maxLength": 80,
              "minLength": 1
            }
          ]
        }
      },
      "description": "The vehicle owner. At least one of email / phone is required; everything else is optional.",
      "additionalProperties": false
    },
    "external_ref": {
      "type": "string",
      "maxLength": 120,
      "minLength": 1,
      "description": "Your reference id; echoed in every response."
    },
    "idempotency_key": {
      "type": "string",
      "maxLength": 255,
      "minLength": 1,
      "description": "Any unique string per logical submission; a replay returns the original receipt."
    }
  },
  "description": "Submit a vehicle owner's total-loss situation on their behalf.",
  "additionalProperties": false
}
    arguments 314 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 38c51edcc5698396.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/38c51edcc5698396/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/38c51edcc5698396/badge.svg)](https://brick.blue/agent/38c51edcc5698396?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
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.