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

recallsapi

https://api.recallsapi.com

Registry code: da75e1ed4b098c18

api record

US recall lookups. Use check_product first with whatever the user has (name and brand, barcode, model, NDC, lot); search_recalls for topics; check_vehicle for cars. Always show the source link. Get an API key at https://recallsapi.com.

endpoint
https://api.recallsapi.com/mcp
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 recallsapi live?
Yes — it answered the hub's last check (checked 2h ago). It answered 100% of checks over the last 30 days.
Is recallsapi free to use?
Not anonymously — it asks for a key or a login before it will serve. Whether that key costs anything is the operator's plan to say: the hub measured the door, not the pricing.
What tools does recallsapi have?
4 tools: search_recalls, get_recall, check_product, check_vehicle.
Is recallsapi 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
657ms

last good check

priced tools
0

of 4 tools

_ answered our checks, 90 days 149 checks · signed record
  • unknown → live
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts, and USDC settlements on base into the address this listing's priced doors name, read off the chain. Every caller and every payer counts the same; the chain total is counted from three payers. How it is counted.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

payers on base
2

distinct

settlements
5

last 2026-11-22

received on chain
0.042 USDC

counted from three payers (thin, concentrated)

_ what it can do 4 tools
4 auth-required 4 of 4 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.

  • search_recalls auth-required 19h ago

    Full-text search across recall records from 9 US agencies (CPSC, FDA, NHTSA, US Coast Guard, FAA and more), newest and most relevant first. Filter by category and date.

    mcp-tool

    {
      "type": "object",
      "required": [
        "query"
      ],
      "properties": {
        "limit": {
          "type": "integer",
          "default": 10,
          "maximum": 50,
          "minimum": 1
        },
        "query": {
          "type": "string",
          "description": "Words to search, e.g. \"listeria deli meat\" or \"Takata airbag\""
        },
        "since": {
          "type": "string",
          "description": "Earliest recall date, YYYY-MM-DD"
        },
        "category": {
          "enum": [
            "consumer_product",
            "food",
            "drug",
            "device",
            "vehicle",
            "vehicle_equipment",
            "tire",
            "child_seat",
            "meat_poultry",
            "boat",
            "aircraft",
            "manufactured_home",
            "respirator",
            "mine_equipment",
            "unclassified",
            "cosmetic",
            "tobacco",
            "biologic",
            "veterinary"
          ],
          "type": "string"
        }
      }
    }
    arguments 46 lines
  • get_recall auth-required 9h ago

    Full record for one recall id (for example "cpsc-24116", "fda-H-1339-2026", "nhtsa-26V631000", "fsis-001-2016"), with every identifier and the agency source link.

    mcp-tool

    {
      "type": "object",
      "required": [
        "id"
      ],
      "properties": {
        "id": {
          "type": "string"
        }
      }
    }
    arguments 11 lines
  • check_product auth-required 9h ago

    Is this product recalled? Give whatever you have: a product name and brand, a UPC/EAN/GTIN barcode, a model number, an NDC drug code or a lot code. Returns matching recalls from 9 US agencies (CPSC, FDA, NHTSA, US Coast Guard, FAA and more) with a confidence level (exact, strong, possible), the reasons for each match and the agency source link, plus early-warning signals from 5 sources (NHTSA investigations, CPSC violation notices, SEC filings, Prop 65 notices, SaferProducts.gov incident reports) that name the same model, vehicle or brand. A signal is not a recall.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "lot": {
          "type": "string",
          "description": "Lot or batch code"
        },
        "ndc": {
          "type": "string",
          "description": "National Drug Code, any dashed layout"
        },
        "upc": {
          "type": "string",
          "description": "UPC, EAN or GTIN barcode digits"
        },
        "name": {
          "type": "string",
          "description": "Product name or description, e.g. \"Hatch Rest sound machine\""
        },
        "brand": {
          "type": "string",
          "description": "Brand or manufacturer, e.g. \"Hatch\""
        },
        "model": {
          "type": "string",
          "description": "Model or part number"
        },
        "receipt": {
          "type": "boolean",
          "description": "true adds a signed receipt: a dated record of what recallsapi.com held for this check, stored for 400 days and fetchable at its verify_url. It is not a safety certification."
        }
      }
    }
    arguments 33 lines
  • check_vehicle auth-required 9h ago

    NHTSA recall campaigns for a vehicle, by 17-character VIN (decoded with NHTSA vPIC) or by make, model and year, plus live NHTSA consumer complaint counts for that make, model and year (not verified by NHTSA, not a safety determination). Give either vin, or make, model and year. Campaigns are filed for a make, model and year (model level); whether a campaign includes a vehicle, and whether its repair is done, is held in the vehicle maker's records, and any dealer of the make can check it with the VIN, free.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "vin": {
          "type": "string",
          "description": "17-character VIN. Give either vin, or make, model and year."
        },
        "make": {
          "type": "string",
          "description": "Vehicle make. Give either vin, or make, model and year."
        },
        "year": {
          "type": "integer",
          "maximum": 2100,
          "minimum": 1949,
          "description": "Model year. Give either vin, or make, model and year."
        },
        "model": {
          "type": "string",
          "description": "Vehicle model. Give either vin, or make, model and year."
        }
      }
    }
    arguments 23 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 da75e1ed4b098c18.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/da75e1ed4b098c18/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/da75e1ed4b098c18/badge.svg)](https://brick.blue/agent/da75e1ed4b098c18?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
80%

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.