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

laboratory-love

https://www.laboratory.love

Registry code: 75705fe9fa120ed5

api record

Laboratory.love publishes laboratory measurements of phthalates, bisphenols and phthalate substitutes in consumer products. Covers chemicals that come from plastics (phthalates, BPA and other bisphenols, and phthalate substitutes), the usual meaning of "plastic chemicals" in food; it does not measure microplastic particles, so say so if someone asks about microplastics. Search before saying whether a product has been tested. Always say whether a record was commissioned by Laboratory.love or derived from PlasticList, keep "not detected", "below the limit of quantitation" and measured values…

endpoint
https://www.laboratory.love/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 laboratory-love live?
Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
Is laboratory-love free to use?
Yes — the hub reached it with no key and no payment.
What tools does laboratory-love have?
9 tools: get_crowdfund_status, search_results, get_result, create_contribution_checkout, create_testing_checkout, get_checkout_status, search_crowdfund, list_analytes, ….
Is laboratory-love 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
663ms

last good check

priced tools
0

of 9 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ 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 9 tools
3 open 6 never probed 3 of 9 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_crowdfund open 1h ago

    List products the public can fund toward laboratory testing, with goal, amount funded, amount remaining, and status. Defaults to products currently accepting contributions. Read-only.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "maxLength": 100,
      "description": "Words to match in the product name or brand."
    },
    "limit": {
      "type": "integer",
      "default": 10,
      "maximum": 50,
      "minimum": 1
    },
    "cursor": {
      "type": "string",
      "maxLength": 200,
      "description": "next_cursor from a previous call with the same filters."
    },
    "status": {
      "enum": [
        "accepting_contributions",
        "funded",
        "testing_in_progress",
        "tested",
        "all"
      ],
      "type": "string",
      "description": "Defaults to accepting_contributions."
    }
  },
  "additionalProperties": false
}
    arguments 33 lines
  • list_analytes open 1h ago

    List the chemicals Laboratory.love reports (abbreviations such as DEHP, DBP, BPA, BPS), their categories, lab panels, and how each feeds the exposure ratings. Use it to explain abbreviations or to pick an analyte filter. Read-only.

    mcp-tool

    {
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
    arguments 5 lines
  • list_testing_tiers open 1h ago

    List the direct testing packages a person can buy to have Laboratory.love test products they choose: price, number of products, samples, panels, turnaround, and refund terms. Read-only.

    mcp-tool

    {
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
    arguments 5 lines
  • get_crowdfund_status unknown never probed

    Get live funding status for one crowdfunding product id: goal, funded, remaining, allowed contribution range, and the result link once tested. Read-only.

    mcp-tool

    {
  "type": "object",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "pattern": "^[1-9][0-9]{0,9}$",
      "description": "Crowdfunding product id from search_crowdfund."
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • search_results unknown never probed

    Search Laboratory.love’s published product-test records. Use this before answering whether a product, brand, or category has been tested. Records are either Laboratory.love-commissioned tests or clearly labeled PlasticList-derived historical records; report which. Results describe the samples tested, not every unit of a product. Covers chemicals that come from plastics (phthalates, BPA and other bisphenols, and phthalate substitutes), the usual meaning of "plastic chemicals" in food; it does not measure microplastic particles, so say so if someone asks about microplastics. Read-only.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "q": {
      "type": "string",
      "maxLength": 100,
      "description": "Words to match in the product name, brand, category, or tags, e.g. \"Coca-Cola Zero\" or \"tofu\"."
    },
    "tag": {
      "type": "string",
      "maxLength": 60,
      "description": "A PlasticList source tag such as \"sodas\" or \"baby_food\"."
    },
    "sort": {
      "enum": [
        "relevance",
        "tested_on_desc",
        "tested_on_asc",
        "name_asc"
      ],
      "type": "string",
      "description": "Defaults to relevance when q is given, otherwise tested_on_desc."
    },
    "brand": {
      "type": "string",
      "maxLength": 60,
      "description": "Brand words. PlasticList records have no separate brand field, so this also matches their product name."
    },
    "limit": {
      "type": "integer",
      "default": 10,
      "maximum": 50,
      "minimum": 1
    },
    "cursor": {
      "type": "string",
      "maxLength": 200,
      "description": "next_cursor from a previous call with the same filters."
    },
    "source": {
      "enum": [
        "commissioned",
        "plasticlist_derived"
      ],
      "type": "string",
      "description": "Only commissioned (Laboratory.love-commissioned) or plasticlist_derived records."
    },
    "analyte": {
      "type": "string",
      "maxLength": 60,
      "description": "Analyte abbreviation or name from list_analytes, e.g. DEHP or BPA. Keeps only results where it was measured."
    },
    "category": {
      "enum": [
        "beverages",
        "water",
        "fast-food-and-restaurants",
        "prepared-meals",
        "baby-food-and-formula",
        "produce-and-meat",
        "milk-and-dairy",
        "supplements-and-protein",
        "pantry",
        "personal-care-and-non-food"
      ],
      "type": "string",
      "description": "Category slug."
    },
    "detected": {
      "type": "boolean",
      "description": "With analyte: true keeps results where that analyte was detected in at least one sample; false keeps results where it was measured but never detected. Without analyte: any analyte."
    }
  },
  "additionalProperties": false
}
    arguments 75 lines
  • get_result unknown never probed

    Get the full public record for one result id from search_results: provenance, every sample with its lot and analyses, every analyte measurement with its status, LOQ where known, and Laboratory.love’s per-serving exposure ratings with their assumptions. When answering: name the source (commissioned vs PlasticList-derived), keep detected / below_limit_of_quantitation / not_detected / not_tested distinct, give sample counts, and do not call a product safe because values are low or not detected. Read-only.

    mcp-tool

    {
  "type": "object",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "pattern": "^(cf-[1-9][0-9]{0,9}|pl-[0-9]{1,10})$",
      "description": "Result id such as \"cf-116\" or \"pl-72\"."
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • create_contribution_checkout unknown never probed

    Write (treat as a sensitive, purchase-starting action; confirm the product and amount with the person first). Creates a secure Stripe-hosted checkout link for a contribution toward testing one crowdfunding product. Nothing is charged by this call: the person must open checkout_url and pay. Returns the amount, currency, seller, refund terms, and expiry. Use get_checkout_status to see whether they paid.

    mcp-tool

    {
  "type": "object",
  "required": [
    "id",
    "amount"
  ],
  "properties": {
    "id": {
      "type": "string",
      "pattern": "^[1-9][0-9]{0,9}$",
      "description": "Crowdfunding product id."
    },
    "amount": {
      "type": "integer",
      "maximum": 1995,
      "minimum": 1,
      "description": "Whole US dollars; must be within the product’s contribution range (minimum $5, or less if less remains)."
    },
    "idempotency_key": {
      "type": "string",
      "pattern": "^[A-Za-z0-9_.:-]{8,100}$",
      "description": "Optional key; repeating a call with the same key and arguments returns the same checkout instead of a new one."
    }
  },
  "additionalProperties": false
}
    arguments 26 lines
  • create_testing_checkout unknown never probed

    Write (treat as a sensitive, purchase-starting action; confirm the tier, price, and product links with the person first). Saves a pending testing order and creates a secure Stripe-hosted checkout link for it. Nothing is charged by this call: the person must open checkout_url and pay. Use get_checkout_status to see whether they paid.

    mcp-tool

    {
  "type": "object",
  "required": [
    "tier",
    "products"
  ],
  "properties": {
    "tier": {
      "enum": [
        "single",
        "kitchen",
        "pantry"
      ],
      "type": "string",
      "description": "Tier id from list_testing_tiers."
    },
    "products": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "url"
        ],
        "properties": {
          "url": {
            "type": "string",
            "format": "uri",
            "maxLength": 2048,
            "description": "Product page URL."
          },
          "notes": {
            "type": "string",
            "maxLength": 500,
            "description": "Optional size/variant hint."
          }
        },
        "additionalProperties": false
      },
      "maxItems": 10,
      "minItems": 1,
      "description": "Products to test (at most the tier’s product count), each a public http(s) product page."
    },
    "idempotency_key": {
      "type": "string",
      "pattern": "^[A-Za-z0-9_.:-]{8,100}$",
      "description": "Optional key; repeating a call with the same key and arguments returns the same checkout."
    }
  },
  "additionalProperties": false
}
    arguments 50 lines
  • get_checkout_status unknown never probed

    Check whether a checkout created by this connector is awaiting payment, paid, processing, or expired. Report "paid" only when this returns paid. Read-only.

    mcp-tool

    {
  "type": "object",
  "required": [
    "checkout_id"
  ],
  "properties": {
    "checkout_id": {
      "type": "string",
      "pattern": "^cs_(live|test)_[A-Za-z0-9]{10,200}$",
      "description": "checkout_id returned by a checkout tool."
    }
  },
  "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 75705fe9fa120ed5.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/75705fe9fa120ed5/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/75705fe9fa120ed5/badge.svg)](https://brick.blue/agent/75705fe9fa120ed5?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.