_ registry / mcp streamable-http · checked just now

Recipes Daily

https://recipes-daily.com

Registry code: 608f2a355c363d2d

api record

Reach for `search_recipes` whenever the question is what to cook — a dish

by name, a cuisine, a time budget, a week of dinners. Reach for

endpoint
https://recipes-daily.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 Recipes Daily live?
Yes — it answered the hub's last check (checked just now). It answered 100% of checks over the last 30 days.
Is Recipes Daily free to use?
Yes — the hub reached it with no key and no payment.
What tools does Recipes Daily have?
4 tools: read_guide, show_recipes, find_recipes_by_ingredients, search_recipes.
Is Recipes Daily 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 99.8%· all time 99.8%

latency
263ms

last good check

priced tools
0

of 4 tools

_ answered our checks, 90 days 401 checks · signed record
  • degraded → live
  • degraded → live
  • live → degraded· timeout after 20000ms
  • unknown → live
_ what it is for
used for
  • search recipes by dish or cuisine
  • find recipes from ingredients on hand
  • read a cooking guide
  • show recipe cards
takes → gives
text → data, text
tools
4 reads
_ 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 4 tools
1 open 3 never probed 1 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_recipes reads open 13h ago

    Find something to cook, from the recipes published at recipes-daily.com. Call this for any question about what to make — a dish by name, a cuisine, a weeknight time budget, a week of dinners — rather than answering from memory, because each result is a real page with quantities, timings and a photograph behind it. For what to cook from ingredients someone already has, call find_recipes_by_ingredients instead: this tool requires every query word to appear in one recipe, so several ingredient names in one search return nothing rather than a coverage report. Returns a shortlist — title, absolute URL, description, total time, servings and categories — so candidates can be ruled out without opening them. The first page also lists matching cooking guides, for how and why questions about technique, storage and substitutions; read one in full with read_guide.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "page": {
          "type": "integer",
          "default": 1,
          "minimum": 1,
          "description": "1-based. The response names the next page when there is one."
        },
        "limit": {
          "type": "integer",
          "default": 25,
          "maximum": 50,
          "minimum": 1,
          "description": "Results per page."
        },
        "query": {
          "type": "string",
          "maxLength": 200,
          "description": "What to search for. Recipes are matched on titles and descriptions, so a word or short phrase matches better than a full question, and there are no boolean operators. Omit it to list every recipe, newest first."
        }
      }
    }
    arguments 23 lines
  • read_guide reads unknown 6h ago

    Read the full text of a cooking guide from recipes-daily.com, as markdown. Call this when search_recipes lists a guide that answers the question — how or why something works in the kitchen, how to store or substitute an ingredient, how to use a piece of equipment — and answer from what it says rather than from memory, citing its URL. Pass the guide URL exactly as search_recipes returned it. For recipes, use show_recipes instead: a recipe is a page the person cooks from, not text to retell.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "guide": {
          "type": "string",
          "maxLength": 300,
          "description": "The guide to read, as the absolute recipes-daily.com URL search_recipes returned — e.g. \"https://recipes-daily.com/guides/preparations/why-do-dried-beans-take-so-long-to-cook\"."
        }
      }
    }
    arguments 10 lines
  • show_recipes reads unknown 6h ago

    Draw recipes as picture cards the person can click through to. Takes any recipes-daily.com recipe URLs you are already holding. Whenever you name recipes from this server in an answer, pass those same ones here — the cards are how a person actually gets to a recipe, and they appear only if you call this. Order is kept, so put the strongest recommendation first.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "recipes": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "maxItems": 12,
          "minItems": 1,
          "description": "The recipes to draw, as absolute recipes-daily.com URLs — e.g. [\"https://recipes-daily.com/make/chicken-piccata-pan-fried-25-minute\"]. A bare slug works too. Order is kept, so put the strongest recommendation first."
        }
      }
    }
    arguments 14 lines
  • find_recipes_by_ingredients reads unknown 6h ago

    Given ingredients someone has, rank the recipes at recipes-daily.com by how many of them each one uses and name what is missing from the rest. Matches by ingredient text, not identity — a near-miss on the name still counts, but two ingredients that are genuinely different words for the same thing (courgette/zucchini) may not. This is not a substitution finder: if nothing uses every ingredient given, the closest partial matches are still worth reading — deciding whether a missing ingredient can be swapped or skipped is the caller's call, not this tool's.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "limit": {
          "type": "integer",
          "default": 10,
          "maximum": 25,
          "minimum": 1,
          "description": "Recipes to return, ranked by coverage."
        },
        "ingredients": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "maxItems": 10,
          "minItems": 1,
          "description": "What is on hand, one ingredient per entry — e.g. [\"broccoli\", \"chicken breast\", \"lemon\"]."
        }
      }
    }
    arguments 21 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 608f2a355c363d2d.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/608f2a355c363d2d/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/608f2a355c363d2d/badge.svg)](https://brick.blue/agent/608f2a355c363d2d?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.