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

recall-kitchen-mcp

https://app.recallkitchen.com

Registry code: e7df1436ae752d00

api record

Recall Kitchen searches government recall notices from U.S. CPSC, FDA food, FDA MedWatch, openFDA enforcement, USDA FSIS, and NHTSA, plus Health Canada / CFIA recalls and safety alerts.

Query syntax for search_product_recalls and watch patterns: unquoted words are AND, OR is or, -term excludes, "quoted words" are a phrase. Example: Generac Generator -Portable.

endpoint
https://app.recallkitchen.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 recall-kitchen-mcp live?
Yes — it answered the hub's last check (checked 2h ago). It answered 100% of checks over the last 30 days.
Is recall-kitchen-mcp 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 recall-kitchen-mcp have?
20 tools: lookup_product, search_product_recalls, search_recalls_by_identifier, search_product_recalls_by_upc, get_product_recall, search_product_recalls_from_image, mark_notification_read, add_watch_pattern, ….
Is recall-kitchen-mcp 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
99.6%

90 days 99.2%· all time 99.2%

latency
322ms

last good check

priced tools
1

of 20 tools

_ answered our checks, 90 days 485 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • degraded → live
  • live → degraded· timeout after 20000ms
_ what it is for
topic
government & legal public records & government
used for
  • search product recalls
  • check recalls by upc or lot code
  • identify recalled product from an image
  • watch for new recalls
  • list recall notifications
takes → gives
text, images → data
tools
11 reads8 changes data1 sends messages
_ 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. The address stands behind 2 doors on this origin, so the chain figures are the operator's. 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
3

last 2026-11-03

received on chain
0.075 USDC

counted from three payers (thin, concentrated)

_ what it can do 20 tools
1 paid14 auth-required 5 never probed 15 of 20 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_product_recalls_from_image reads 0.025 USDC paid 2h ago

    Photo (beta): identify products in a public HTTPS image URL, data:image/...;base64 URI, or MCP image content part. Local files are not supported. Each product includes match (upc, model, text, category) and confidence. Category matches omit recalls unless include_category_matches=true. Requires an API key or x402; not included in the free anonymous per-IP quota.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "alias for image_url"
    },
    "limit": {
      "type": "integer",
      "default": 3,
      "maximum": 100,
      "minimum": 1,
      "description": "number of recalls to return per product, 1-100, default 3"
    },
    "image_url": {
      "type": "string",
      "description": "photo (beta). HTTPS URL or data:image/...;base64 URI of a photo containing products. Local file paths are not supported."
    },
    "include_category_matches": {
      "type": "boolean",
      "description": "if true, attach keyword recalls for generic items such as cups; default false"
    }
  },
  "additionalProperties": false
}
    arguments 25 lines
  • mark_notification_read changes data auth-required never probed

    Mark a recall notification as read (default) or unread. Requires an API key.

    mcp-tool

    {
  "type": "object",
  "required": [
    "recall_id"
  ],
  "properties": {
    "read": {
      "type": [
        "null",
        "boolean"
      ],
      "description": "if true, mark read; if false, mark unread. Default true"
    },
    "recall_id": {
      "type": "string",
      "description": "recall id from list_recall_notifications"
    }
  },
  "additionalProperties": false
}
    arguments 20 lines
  • add_watch_pattern changes data auth-required never probed

    Add a recall watch pattern for this API key. Same websearch syntax as search_product_recalls (AND, OR, -exclude, quoted phrases). New matches show up in Recall Kitchen. Requires an API key.

    mcp-tool

    {
  "type": "object",
  "required": [
    "pattern"
  ],
  "properties": {
    "weight": {
      "type": "integer",
      "maximum": 8,
      "minimum": 0,
      "description": "optional weight 0-8, default 4"
    },
    "pattern": {
      "type": "string",
      "description": "websearch pattern: unquoted words are AND, OR is or, -term excludes, quoted phrases match as a unit"
    }
  },
  "additionalProperties": false
}
    arguments 19 lines
  • list_api_keys reads auth-required 40d ago

    List this account's API keys (id, name, prefix, created). Secrets are not shown. Requires an API key.

    mcp-tool

    {
  "type": "object",
  "additionalProperties": false
}
    arguments 4 lines
  • give_feedback sends messages auth-required never probed

    Report a bug, missing capability, bad search result, or confusing schema to the Recall Kitchen team. Use this instead of silently working around a problem. message is required and should include the MCP tool names you called, the actions you took, the query or identifiers, and any recall_id. Do not send API keys, photos, or PII. Optional category: bad_result, tool_error, missing_capability, confusing_schema, docs, other. Optional severity: blocked, workaround, annoyance. No API key or x402 required. Does not count against search quotas.

    mcp-tool

    {
  "type": "object",
  "required": [
    "message"
  ],
  "properties": {
    "message": {
      "type": "string",
      "description": "describe the problem. Include the MCP tool names you called, the actions you took, the query or identifiers, and any recall_id. Do not send API keys, photos, or PII."
    },
    "category": {
      "enum": [
        "bad_result",
        "tool_error",
        "missing_capability",
        "confusing_schema",
        "docs",
        "other"
      ],
      "type": "string",
      "description": "optional: bad_result, tool_error, missing_capability, confusing_schema, docs, or other"
    },
    "severity": {
      "enum": [
        "blocked",
        "workaround",
        "annoyance"
      ],
      "type": "string",
      "description": "optional: blocked, workaround, or annoyance"
    }
  },
  "additionalProperties": false
}
    arguments 34 lines
  • remove_watch_pattern changes data auth-required never probed

    Remove a recall watch pattern for this API key. Requires an API key.

    mcp-tool

    {
  "type": "object",
  "required": [
    "pattern"
  ],
  "properties": {
    "pattern": {
      "type": "string",
      "description": "watch pattern to remove"
    }
  },
  "additionalProperties": false
}
    arguments 13 lines
  • list_recall_notifications reads auth-required 11h ago

    List recall notifications for this API key. unread defaults to true (unread only); pass false for all. New matches show up in Recall Kitchen. Empty for new accounts until a new matching recall is published; not a backfill of check_tracked_products. message is a short plain-text summary. Requires an API key.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer",
      "default": 3,
      "maximum": 100,
      "minimum": 1,
      "description": "number of notifications to return"
    },
    "offset": {
      "type": "integer",
      "maximum": 100,
      "minimum": 0,
      "description": "number of notifications to skip"
    },
    "unread": {
      "type": [
        "null",
        "boolean"
      ],
      "description": "if true, only unread notifications; if false, include read. Default: true (unread only)"
    }
  },
  "additionalProperties": false
}
    arguments 26 lines
  • revoke_api_key changes data auth-required never probed

    Revoke an API key by key_id from list_api_keys. Requires an API key. Revoking the current key will fail subsequent calls.

    mcp-tool

    {
  "type": "object",
  "required": [
    "key_id"
  ],
  "properties": {
    "key_id": {
      "type": "string",
      "description": "key_id from list_api_keys"
    }
  },
  "additionalProperties": false
}
    arguments 13 lines
  • list_inventory reads auth-required 18h ago

    List this API key's tracked inventory products. Requires an API key.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer",
      "default": 3,
      "maximum": 100,
      "minimum": 1,
      "description": "number of products to return"
    },
    "query": {
      "type": "string",
      "description": "optional inventory search"
    },
    "offset": {
      "type": "integer",
      "maximum": 100,
      "minimum": 0,
      "description": "number of products to skip"
    }
  },
  "additionalProperties": false
}
    arguments 23 lines
  • remove_inventory_product changes data auth-required never probed

    Remove a product from this API key's inventory by id. Requires an API key.

    mcp-tool

    {
  "type": "object",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "integer",
      "description": "inventory product id from list_inventory"
    }
  },
  "additionalProperties": false
}
    arguments 13 lines
  • add_inventory_product changes data auth-required never probed

    Add a product to this API key's inventory. Optional category is food, beverage, baby, household, electronics, vehicle, medical_device, drug, cosmetics, pet, or other. Requires a verified account (sign in at https://app.recallkitchen.com with the signup email). Unverified signup keys cannot add inventory.

    mcp-tool

    {
  "type": "object",
  "required": [
    "name"
  ],
  "properties": {
    "sku": {
      "type": "string",
      "description": "optional SKU or UPC"
    },
    "name": {
      "type": "string",
      "description": "product name"
    },
    "brand": {
      "type": "string",
      "description": "optional brand"
    },
    "category": {
      "enum": [
        "food",
        "beverage",
        "baby",
        "household",
        "electronics",
        "vehicle",
        "medical_device",
        "drug",
        "cosmetics",
        "pet",
        "other"
      ],
      "type": "string",
      "description": "optional product category: food, beverage, baby, household, electronics, vehicle, medical_device, drug, cosmetics, pet, or other"
    }
  },
  "additionalProperties": false
}
    arguments 38 lines
  • create_api_key changes data auth-required never probed

    Create an additional API key for this account. Requires an existing API key. Unverified accounts may have only one key; verified accounts may have three. Usage is counted per account, not per key.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "kind": {
      "enum": [
        "user",
        "agent"
      ],
      "type": "string",
      "description": "optional kind: user or agent, default agent"
    },
    "name": {
      "type": "string",
      "description": "optional key name"
    }
  },
  "additionalProperties": false
}
    arguments 18 lines
  • signup changes data auth-required never probed

    Create a Recall Kitchen account and API key from an email. No API key or x402 payment required. Set accept_terms true only after you ask the person and they confirm they are 13 or older and accept the Terms (https://recallkitchen.com/terms), Privacy Policy (https://recallkitchen.com/privacy) and API Terms (https://recallkitchen.com/api-terms); never set it automatically or on the person's behalf. The key is returned once. Unverified accounts have lower rate limits (60 tool calls/hour, 400/day, one key) and can add a few watch patterns. Sign in at https://app.recallkitchen.com with the same email to verify, raise limits, and add inventory. Does not re-issue a key if the email already has an account.

    mcp-tool

    {
  "type": "object",
  "required": [
    "email",
    "accept_terms"
  ],
  "properties": {
    "name": {
      "type": "string",
      "description": "optional display name"
    },
    "email": {
      "type": "string",
      "description": "email address for the new account"
    },
    "accept_terms": {
      "type": "boolean",
      "description": "Set true only after you ask the person and they confirm they are 13 or older and accept the Terms (https://recallkitchen.com/terms), Privacy Policy (https://recallkitchen.com/privacy) and API Terms (https://recallkitchen.com/api-terms). Never set this automatically or on the person's behalf."
    }
  },
  "additionalProperties": false
}
    arguments 22 lines
  • list_watch_patterns reads auth-required 11h ago

    List this API key's recall watch patterns. Requires an API key.

    mcp-tool

    {
  "type": "object",
  "additionalProperties": false
}
    arguments 4 lines
  • check_tracked_products reads auth-required 18h ago

    Check this API key's watch patterns and inventory against current indexed recalls (including historical notices). Does not create notifications. Generic patterns such as food or hazard only match in titles. Requires an API key.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer",
      "default": 3,
      "maximum": 100,
      "minimum": 1,
      "description": "maximum matches to return"
    },
    "offset": {
      "type": "integer",
      "maximum": 100,
      "minimum": 0,
      "description": "number of matches to skip"
    }
  },
  "additionalProperties": false
}
    arguments 19 lines
  • lookup_product reads unknown 9h ago

    Look up a product by UPC/EAN. Returns found=false when unknown. Does not search recalls.

    mcp-tool

    {
  "type": "object",
  "required": [
    "upc"
  ],
  "properties": {
    "upc": {
      "type": "string",
      "description": "UPC or EAN barcode digits"
    }
  },
  "additionalProperties": false
}
    arguments 13 lines
  • search_product_recalls reads unknown 11h ago

    Search product recalls by query. Query uses websearch syntax: unquoted words are AND, OR is or, -term excludes, quoted phrases match as a unit (example: Generac Generator -Portable). Optional filters: source (cpsc, fdafoodsafety, FDAMedWatch, usda, nhtsa, canada, openfda), since/until (YYYY-MM-DD), location (country, region, or place, ANDed with the query), offset, limit. Descriptions are truncated and extracted products are capped; use get_product_recall for the full text.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer",
      "default": 3,
      "maximum": 100,
      "minimum": 1,
      "description": "number of recalls to return, 1-100, default 3"
    },
    "query": {
      "type": "string",
      "description": "websearch query: unquoted words are AND, OR is or, -term excludes, quoted phrases match as a unit. Example: Generac Generator -Portable"
    },
    "since": {
      "type": "string",
      "description": "optional published-on start date YYYY-MM-DD"
    },
    "until": {
      "type": "string",
      "description": "optional published-on end date YYYY-MM-DD"
    },
    "years": {
      "type": "integer",
      "maximum": 50,
      "minimum": 1,
      "description": "optional published window in years (1-50). Ignored when since is set"
    },
    "offset": {
      "type": "integer",
      "maximum": 100,
      "minimum": 0,
      "description": "number of recalls to skip"
    },
    "source": {
      "enum": [
        "cpsc",
        "fdafoodsafety",
        "FDAMedWatch",
        "usda",
        "nhtsa",
        "canada",
        "openfda"
      ],
      "type": "string",
      "description": "optional source filter: cpsc, fdafoodsafety, FDAMedWatch, usda, nhtsa, canada, or openfda. Aliases: FDA and food map to fdafoodsafety; medwatch maps to FDAMedWatch; vehicle, vin, and car map to nhtsa; healthcanada, cfia, and hc-sc map to canada; enforcement, res, and fdaenforcement map to openfda. For more than one source, pass sources."
    },
    "sources": {
      "type": "array",
      "items": {
        "enum": [
          "cpsc",
          "fdafoodsafety",
          "FDAMedWatch",
          "usda",
          "nhtsa",
          "canada",
          "openfda"
        ],
        "type": "string"
      },
      "description": "optional sources to include (OR). Same values as source",
      "uniqueItems": true
    },
    "location": {
      "type": "string",
      "description": "optional country, region, or place; ANDed with the query. USA, Canada, Mexico, EU, and Europe match places in that region. CA is California, not Canada."
    }
  },
  "additionalProperties": false
}
    arguments 71 lines
  • search_recalls_by_identifier reads unknown 2h ago

    Search recalls by extracted UPC, lot code, model number, product name, or VIN. Multiple identifiers are AND-matched on the same product. VIN lookup lists NHTSA campaigns for the decoded year and make; confirm your vehicle on nhtsa.gov/recalls. lot_code matches extracted lot codes after normalizing spaces, case, and punctuation; if lots were not extracted, also searches notice title and description — verify against the notice. product_name falls back to the same full-text search as search_product_recalls when no exact extracted name matches, and returns a hint if still empty.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "upc": {
      "type": "string",
      "description": "product UPC or EAN as stored on the recall"
    },
    "vin": {
      "type": "string",
      "description": "17-character VIN. Lookup lists NHTSA campaigns for the decoded year and make; confirm your vehicle on nhtsa.gov/recalls."
    },
    "limit": {
      "type": "integer",
      "default": 3,
      "maximum": 100,
      "minimum": 1,
      "description": "number of recalls to return"
    },
    "offset": {
      "type": "integer",
      "maximum": 100,
      "minimum": 0,
      "description": "number of recalls to skip"
    },
    "lot_code": {
      "type": "string",
      "description": "lot or batch code. Matches extracted lot codes after normalizing spaces, case, and punctuation; if lots were not extracted, also searches the notice title and description. Verify against the notice."
    },
    "model_number": {
      "type": "string",
      "description": "model number as stored on the recall"
    },
    "product_name": {
      "type": "string",
      "description": "extracted product name (exact match; if none, falls back to the same full-text search as search_product_recalls)"
    }
  },
  "additionalProperties": false
}
    arguments 39 lines
  • search_product_recalls_by_upc reads unknown 2h ago

    Search recalls by UPC/EAN or a barcode image URL/data URI/MCP image content. Matches extracted recall UPCs first. Returns found=false when the UPC is unknown.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "upc": {
      "type": "string",
      "description": "UPC or EAN barcode digits"
    },
    "url": {
      "type": "string",
      "description": "alias for image_url"
    },
    "limit": {
      "type": "integer",
      "default": 3,
      "maximum": 100,
      "minimum": 1,
      "description": "number of recalls to return, 1-100, default 3"
    },
    "offset": {
      "type": "integer",
      "maximum": 100,
      "minimum": 0,
      "description": "number of recalls to skip"
    },
    "barcode": {
      "type": "string",
      "description": "alias for upc"
    },
    "image_url": {
      "type": "string",
      "description": "optional HTTPS URL or data:image/...;base64 URI of a barcode image"
    }
  },
  "additionalProperties": false
}
    arguments 35 lines
  • get_product_recall reads unknown 18h ago

    Get a recall by id, including extracted lots, UPCs, model numbers, locations, contact info, and product photo URLs

    mcp-tool

    {
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "alias for recall_id"
    },
    "recall_id": {
      "type": "string",
      "description": "recall id returned by search tools"
    }
  },
  "additionalProperties": false
}
    arguments 14 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 e7df1436ae752d00.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/e7df1436ae752d00/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/e7df1436ae752d00/badge.svg)](https://brick.blue/agent/e7df1436ae752d00?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
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.