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

siftivo

https://api.siftivo.com

Registry code: 4e480727442fb479

api record

Siftivo is a book catalog and a reader's library. It covers what a book is about, what to read after it, what a series contains, what is circulating this week, and what a reader has on their shelves.

search_books takes a title or an author name, recommend_from_description takes a theme or a mood in the reader's own words, and recommend_from_titles takes books they already liked. All three return workId values, and every other tool takes one of those.

endpoint
https://api.siftivo.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 siftivo live?
Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
Is siftivo free to use?
Partly — some of its tools are open, others need a key or payment.
What tools does siftivo have?
12 tools: search_books, get_book, add_to_library, get_my_book, remove_from_library, recommend_from_titles, recommend_from_description, get_author, ….
Is siftivo 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 99.7%· all time 99.7%

latency
493ms

last good check

priced tools
0

of 12 tools

_ answered our checks, 90 days 378 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • unknown → live
_ what it is for
topic
education & learning
used for
  • search books
  • get book recommendations by mood
  • find what to read next
  • manage reading shelves
takes → gives
text → data
tools
10 reads2 changes data
_ 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 12 tools
1 open1 auth-required 10 never probed 2 of 12 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.

  • get_reading_index reads open 4h ago

    The weekly Siftivo Reading Index: the fiction and nonfiction books moving most in cultural circulation this week, ranked.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "week": {
      "type": "string",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
      "description": "Edition week, YYYY-MM-DD. Omit for the current edition."
    }
  },
  "additionalProperties": false
}
    arguments 12 lines
  • get_my_library reads auth-required 4h ago

    The signed-in reader's own Siftivo library: what they want to read, are reading, finished, or set down, with their ratings.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "status": {
      "enum": [
        "NOT_STARTED",
        "READING",
        "FINISHED",
        "DNF"
      ],
      "type": "string",
      "description": "Filter to one shelf. Omit for the whole library."
    }
  },
  "additionalProperties": false
}
    arguments 17 lines
  • search_books reads unknown never probed

    Keyword search over the Siftivo book catalog. Matches titles, authors, and descriptions. Returns works with the ids other Siftivo tools accept.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 10,
      "maximum": 20,
      "minimum": 1
    },
    "query": {
      "type": "string",
      "maxLength": 200,
      "minLength": 1,
      "description": "Words to search for"
    },
    "isFiction": {
      "type": "boolean",
      "description": "Restrict to fiction (true) or nonfiction (false)"
    }
  },
  "additionalProperties": false
}
    arguments 26 lines
  • get_book reads unknown never probed

    Full detail for one book: synopsis, authors, series position, genres, and its page on siftivo.com. Accepts a work id, an edition id, or a slug.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "minLength": 1,
      "description": "A Siftivo work id, edition id, or URL slug"
    }
  },
  "additionalProperties": false
}
    arguments 15 lines
  • add_to_library changes data unknown never probed

    Put a book on one of the signed-in reader's shelves, move it to a different shelf, rate it, or record how far through it they are. The workId is one returned by search_books, get_book or recommend_from_titles. "Finished it, four and a half stars" is one call with readingStatus FINISHED and rating 4.5. Each field given replaces what the reader had there before, so send a rating or a note only when they asked for that one to change. Omitting readingStatus leaves the book on the shelf it is already on.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "workId"
  ],
  "properties": {
    "notes": {
      "type": "string",
      "maxLength": 2000,
      "description": "The reader's own note on the book, private to them"
    },
    "rating": {
      "type": "number",
      "maximum": 5,
      "minimum": 0.5,
      "multipleOf": 0.5,
      "description": "Stars, 0.5 to 5 in half-star steps"
    },
    "workId": {
      "type": "string",
      "minLength": 1
    },
    "progress": {
      "type": "integer",
      "maximum": 100,
      "minimum": 0,
      "description": "Percent read, 0 to 100"
    },
    "readingStatus": {
      "enum": [
        "NOT_STARTED",
        "READING",
        "FINISHED",
        "DNF"
      ],
      "type": "string",
      "description": "The shelf to put the book on. Omit to leave it where it is, or NOT_STARTED for a book the reader has not opened yet."
    }
  },
  "additionalProperties": false
}
    arguments 42 lines
  • get_my_book reads unknown never probed

    Whether the signed-in reader has this book on a shelf, and if so which shelf, their rating and how far through they are. Answers "have I read this?" without pulling the whole library.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "workId"
  ],
  "properties": {
    "workId": {
      "type": "string",
      "minLength": 1
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • remove_from_library changes data unknown never probed

    Take a book off the signed-in reader's shelves entirely, discarding its shelf, progress and notes. The reader's rating for the book stays. This is removal rather than a shelf change: add_to_library with a new readingStatus moves a book between shelves instead.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "workId"
  ],
  "properties": {
    "workId": {
      "type": "string",
      "minLength": 1
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • recommend_from_titles reads unknown 6h ago

    Give Siftivo a few books someone liked, by title, and get books like them. Titles are resolved against the catalog first; anything that does not resolve is reported back rather than guessed at.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "titles"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 5,
      "maximum": 10,
      "minimum": 1
    },
    "titles": {
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1
      },
      "maxItems": 10,
      "minItems": 1,
      "description": "Book titles, optionally \"Title by Author\""
    },
    "isFiction": {
      "type": "boolean"
    }
  },
  "additionalProperties": false
}
    arguments 29 lines
  • recommend_from_description reads unknown 23h ago

    Describe what someone is in the mood for, in their own words, and get books that match. It suits a theme, subject or feeling ("books about grief", "cozy mysteries set in Cornwall"), and matches on meaning rather than on a title or an author name.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "description"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 5,
      "maximum": 10,
      "minimum": 1
    },
    "isFiction": {
      "type": "boolean"
    },
    "description": {
      "type": "string",
      "maxLength": 300,
      "minLength": 1,
      "description": "What the reader is after, in plain language"
    }
  },
  "additionalProperties": false
}
    arguments 25 lines
  • get_author reads unknown 6h ago

    An author, their biography, and the works Siftivo holds for them. Accepts an author id or slug.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "minLength": 1
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • get_series reads unknown 4h ago

    A series and its works in reading order. Accepts a series id or slug.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "minLength": 1
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • what_to_read_next reads unknown 6h ago

    Given one book, what to read after it: the next books in its series, more by the same author, and books that read like it. This is the same set the book page on siftivo.com shows.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "workId"
  ],
  "properties": {
    "workId": {
      "type": "string",
      "minLength": 1,
      "description": "A workId from search_books, get_book, or a URL slug"
    }
  },
  "additionalProperties": false
}
    arguments 15 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 4e480727442fb479.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/4e480727442fb479/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/4e480727442fb479/badge.svg)](https://brick.blue/agent/4e480727442fb479?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.