_ registry / mcp streamable-http · checked 14h ago

trueprice

https://checktrueprice.com

Registry code: 58976a8334014b2f

api record

Price history for products at 145,000+ stores and coupon codes that Trueprice's AI shopping agents tested in a real cart. Daily history starts 2026-11-13. Earlier prices appear only as labelled archived snapshots (Wayback Machine, since 2025-01) in `archived`, never mixed into the daily points, stats or deal score.

endpoint
https://checktrueprice.com/api/mcp/shopping
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 trueprice live?
Yes — it answered the hub's last check (checked 14h ago). It answered 100% of checks over the last 30 days.
Is trueprice free to use?
Yes — the hub reached it with no key and no payment.
What tools does trueprice have?
8 tools: store_codes, search_products, lookup_price, product_history, lookup_gtin, cheapest_path, find_store, find_products.
Is trueprice 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
274ms

last good check

priced tools
0

of 8 tools

_ answered our checks, 90 days 2 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 8 tools
1 open 7 never probed 1 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.

  • find_products open 14h ago

    Filter every product Trueprice tracks across its Shopify stores, like the Product Finder at /product-finder (same filters, same results as GET /api/v1/finder). Drops are % below the product's highest in-stock price in the last 7 or 30 days (daily history starts 2026-11-13). new_days = listed by the store within N days (first seen after Trueprice's first read of that store). One currency at a time (default USD). Sorts: drop (dropped products first, biggest drop first), new (new listings first), price (lowest first), rating (best rated first), reviews (most reviewed first), rank (each product type's cheapest in-stock products first). Each row has rating + reviews from the store's review app and type_rank (#rank cheapest of `of` in-stock products of its product_type and currency). 20 results a page; each has a url to its Trueprice price-history page.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "page": {
          "type": "integer",
          "default": 1,
          "maximum": 50,
          "minimum": 1
        },
        "sort": {
          "enum": [
            "drop",
            "new",
            "price",
            "rating",
            "reviews",
            "rank"
          ],
          "type": "string",
          "default": "drop"
        },
        "brand": {
          "type": "string",
          "description": "Brand (Shopify vendor), exact, any case"
        },
        "query": {
          "type": "string",
          "description": "Words that must all be in the title"
        },
        "store": {
          "type": "string",
          "description": "Store domain, e.g. example.com"
        },
        "drop_7d": {
          "type": "number",
          "description": "Minimum % drop over 7 days (1-100)"
        },
        "currency": {
          "type": "string",
          "description": "ISO currency, default USD"
        },
        "drop_30d": {
          "type": "number",
          "description": "Minimum % drop over 30 days (1-100)"
        },
        "has_code": {
          "type": "boolean",
          "description": "Only stores with a checked promo code"
        },
        "in_stock": {
          "type": "boolean"
        },
        "new_days": {
          "type": "integer",
          "maximum": 365,
          "minimum": 1,
          "description": "Only products newly listed in the last N days"
        },
        "max_price": {
          "type": "number"
        },
        "min_price": {
          "type": "number"
        },
        "min_rating": {
          "type": "number",
          "maximum": 5,
          "minimum": 0,
          "description": "Minimum star rating from the store's review app"
        },
        "min_reviews": {
          "type": "integer",
          "minimum": 1,
          "description": "Minimum number of reviews"
        },
        "product_type": {
          "type": "string",
          "description": "Shopify product type, exact, any case"
        }
      }
    }
    arguments 81 lines
  • store_codes unknown never probed

    Promo codes for a store that Trueprice applied in a real cart and the store accepted.

    mcp-tool

    {
      "type": "object",
      "required": [
        "domain"
      ],
      "properties": {
        "domain": {
          "type": "string",
          "description": "Store domain, e.g. example.com"
        }
      }
    }
    arguments 12 lines
  • search_products unknown never probed

    Find products by title words across every store Trueprice tracks. Returns store domain and handle for product_history.

    mcp-tool

    {
      "type": "object",
      "required": [
        "query"
      ],
      "properties": {
        "limit": {
          "type": "integer",
          "default": 10,
          "maximum": 50,
          "minimum": 1
        },
        "query": {
          "type": "string"
        }
      }
    }
    arguments 17 lines
  • lookup_price unknown 14h ago

    True price (the lowest price the product really sold at that we know of, from daily checks and archived snapshots: `true_price`), price history, deal score, checked promo code and product spec (description, tags, options, SKUs, weights, images) for a product page URL of a Shopify store Trueprice tracks (e.g. https://example.com/products/blue-mug). History (`points`) starts the day Trueprice first read the product; `archived` holds earlier prices from archived copies of the store's page (Wayback Machine, since 2025-01), labelled "archived snapshot": snapshots, not daily checks, and not used in the stats or deal score.

    mcp-tool

    {
      "type": "object",
      "required": [
        "url"
      ],
      "properties": {
        "url": {
          "type": "string",
          "description": "The product page URL; a ?variant=<id> in it returns that option's own history"
        }
      }
    }
    arguments 12 lines
  • product_history unknown 14h ago

    True price (`true_price`: lowest price it really sold at, from daily checks and archived snapshots), Stats per 30/90/180/365-day and all-time window (`stats.windows`: low/high with dates, average, price at window start, out-of-stock %, drop count, is_lowest, last_price_change), star rating and review count with history (`rating`), reviews from the store's review app (`reviews`: rating, count, star histogram, 3 recent reviews, Q&A, what reviewers mention), category rank among same-type products across stores (`category_rank`: #cheapest of N in stock, 30-day drop rank), units in stock per option (`stock`: qty, null = not limited, with its change history; `variants[].stock`), live price, every recorded price change, archived snapshots from before tracking began (`archived`, labelled "archived snapshot", not used in stats or score), 30/90-day and all-time low/average/high, deal score, checked promo code and product spec (description, tags, options, SKUs, weights, images) for one product.

    mcp-tool

    {
      "type": "object",
      "required": [
        "domain",
        "handle"
      ],
      "properties": {
        "domain": {
          "type": "string",
          "description": "Store domain, e.g. example.com"
        },
        "handle": {
          "type": "string",
          "description": "Shopify product handle"
        },
        "variant": {
          "type": "string",
          "description": "Optional option (variant) id from `variants[].id`: that size/colour's own price history"
        }
      }
    }
    arguments 21 lines
  • lookup_gtin unknown 41h ago

    Every tracked Shopify listing with this barcode (GTIN / UPC / EAN), across stores: domain, handle, title, price and stock of that option, and its Trueprice URL. Barcodes come from the stores' own product data; coverage grows as products are read.

    mcp-tool

    {
      "type": "object",
      "required": [
        "gtin"
      ],
      "properties": {
        "gtin": {
          "type": "string",
          "description": "8, 12, 13 or 14 digits (UPC-A, EAN-13, GTIN-14)"
        }
      }
    }
    arguments 12 lines
  • cheapest_path unknown never probed

    The cheapest way to buy a product Trueprice tracks (same as POST /api/v1/prices/optimize): the exact steps (sale, each code, shipping, tax, rewards) with each step's amount, source_id (the code's deals id or the product URL), confidence and checked_at, then checkout_total = items − eligible discounts + shipping + tax (tax only with user.taxRate), effective_cost after rewards (null without one), codes rejected and why (not stackable, minimum not met, new customers only, expired), assumptions, and snapshot_id: the purchase_paths row that reproduces every number. Maths is deterministic code, never a model; ranking never follows commission. Pass a product URL, or domain + handle, or your own offers/coupons/rewards. path is null when nothing is buyable.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "url": {
          "type": "string",
          "description": "Product page URL (a tracked Shopify store or any store page Trueprice tracks)"
        },
        "user": {
          "type": "object",
          "properties": {
            "region": {
              "type": "string"
            },
            "taxRate": {
              "type": "number",
              "description": "0.0625 = 6.25%"
            },
            "firstOrder": {
              "type": "boolean"
            }
          }
        },
        "domain": {
          "type": "string"
        },
        "handle": {
          "type": "string"
        },
        "offers": {
          "type": "array",
          "items": {
            "type": "object"
          },
          "description": "Your own offers: {store, url, price, checked_at, compare_at?, currency?, shipping?, available?, kind?, ref?}"
        },
        "coupons": {
          "type": "array",
          "items": {
            "type": "object"
          },
          "description": "{code, store, kind: percent|fixed|ship_percent|ship_fixed, value, min_spend?, stackable?, new_customer_only?, expires_at?}"
        },
        "rewards": {
          "type": "array",
          "items": {
            "type": "object"
          },
          "description": "{source, kind: percent|fixed, value, checked_at, store?, cap?, min_spend?}"
        }
      }
    }
    arguments 51 lines
  • find_store unknown 41h ago

    Store domains for a brand or site name (e.g. "Nike", "allbirds"): `with_codes` = domains with promo codes a real cart accepted (count in working_codes; read them with store_codes), `tracked_prices` = domains whose product prices Trueprice reads daily (product count). Empty lists mean Trueprice doesn't cover that brand yet.

    mcp-tool

    {
      "type": "object",
      "required": [
        "name"
      ],
      "properties": {
        "name": {
          "type": "string",
          "description": "Brand, store name or domain"
        }
      }
    }
    arguments 12 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 58976a8334014b2f.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/58976a8334014b2f/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/58976a8334014b2f/badge.svg)](https://brick.blue/agent/58976a8334014b2f?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.