_ registry / mcp streamable-http · checked 56m ago

crystlquant

https://crystlquant.com

Registry code: a5d0253e814d3f6e

api record

CrystlQuant (crystlquant.com) publishes a win chance for every game it covers before the game starts, next to the market's chance for the same result, and grades every call afterwards. Use these tools for upcoming NFL, NBA, college football and basketball, NHL, MLB, football (soccer) and UFC games, for where CrystlQuant and the market disagree most, for title chances (who wins it all) and for team ratings. Percentages are chances to win. The board lists each game with CrystlQuant's pick; find_game gives one game's CrystlQuant chance. A game's market chance and gap are on its page…

endpoint
https://crystlquant.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 crystlquant live?
Yes — it answered the hub's last check (checked 56m ago). It answered 100% of checks over the last 30 days.
Is crystlquant free to use?
Yes — the hub reached it with no key and no payment.
What tools does crystlquant have?
5 tools: find_game, rankings, who_wins_it_all, biggest_gaps, todays_board.
Is crystlquant 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
421ms

last good check

priced tools
0

of 5 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 5 tools
2 open 3 never probed 2 of 5 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.

  • biggest_gaps open 56m ago

    The three upcoming games where CrystlQuant and the market disagree most, biggest gap first, including games where they back different winners. Each row links to the game's page; every other disagreement is on crystlquant.com (the link comes with the answer). Quote each number as a forecast of who wins, naming the side and its chance (never 'coin flip', 'toss-up' or '50-50'). These are forecasts of who wins, not tips.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "limit": {
          "type": "integer",
          "default": 3,
          "maximum": 3,
          "minimum": 1,
          "description": "How many rows to return (1-3, default 3)."
        },
        "sport": {
          "enum": [
            "nfl",
            "nba",
            "football",
            "mma",
            "mlb",
            "nhl",
            "ncaaf",
            "ncaab"
          ],
          "type": "string",
          "description": "Optional. One sport: nfl = NFL, nba = NBA, football = Football (soccer), mma = UFC / MMA, mlb = MLB, nhl = NHL, ncaaf = College football, ncaab = College basketball."
        }
      },
      "additionalProperties": false
    }
    arguments 27 lines
  • todays_board open 56m ago

    The games on CrystlQuant's board today and tomorrow, in start order: each matchup, its start time and CrystlQuant's pick, with a link to each game's page. The board carries no chances: for one game's CrystlQuant chance, call find_game with a team name; the market's chance and the gap are on the game's page. Quote each number as a forecast of who wins, naming the side and its chance (never 'coin flip', 'toss-up' or '50-50'). These are forecasts of who wins, not tips.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "limit": {
          "type": "integer",
          "default": 15,
          "maximum": 25,
          "minimum": 1,
          "description": "How many rows to return (1-25, default 15)."
        },
        "sport": {
          "enum": [
            "nfl",
            "nba",
            "football",
            "mma",
            "mlb",
            "nhl",
            "ncaaf",
            "ncaab"
          ],
          "type": "string",
          "description": "Optional. One sport: nfl = NFL, nba = NBA, football = Football (soccer), mma = UFC / MMA, mlb = MLB, nhl = NHL, ncaaf = College football, ncaab = College basketball."
        }
      },
      "additionalProperties": false
    }
    arguments 27 lines
  • find_game unknown never probed

    CrystlQuant's pick and win chance for one upcoming game (today or tomorrow), found by a team or fighter name, for example 'Chiefs', 'Arsenal' or 'Pereira', with a link to the game's page, where the market's chance and the gap are. Quote each number as a forecast of who wins, naming the side and its chance (never 'coin flip', 'toss-up' or '50-50'). These are forecasts of who wins, not tips.

    mcp-tool

    {
      "type": "object",
      "required": [
        "team"
      ],
      "properties": {
        "team": {
          "type": "string",
          "maxLength": 60,
          "minLength": 3,
          "description": "A team or fighter name, or part of one (3 letters or more)."
        }
      },
      "additionalProperties": false
    }
    arguments 15 lines
  • rankings unknown never probed

    CrystlQuant's team ratings for the NFL, NBA, MLB or NHL, or its UFC rankings by division and pound for pound, with movement since the last update. The limit is per list (each UFC division is its own list).

    mcp-tool

    {
      "type": "object",
      "required": [
        "list"
      ],
      "properties": {
        "list": {
          "enum": [
            "nfl",
            "nba",
            "mlb",
            "nhl",
            "ufc"
          ],
          "type": "string",
          "description": "Which list: nfl, nba, mlb, nhl or ufc."
        },
        "limit": {
          "type": "integer",
          "default": 10,
          "maximum": 10,
          "minimum": 1,
          "description": "How many rows to return per list (1-10, default 10)."
        }
      },
      "additionalProperties": false
    }
    arguments 27 lines
  • who_wins_it_all unknown 56m ago

    Title chances: each league's likeliest champions from CrystlQuant's season forecasts, with the change since the last update and a link to the league's page. A row with no CrystlQuant number yet shows the Blind model's chance and says so. The limit is per league.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "limit": {
          "type": "integer",
          "default": 5,
          "maximum": 5,
          "minimum": 1,
          "description": "How many rows to return per league (1-5, default 5)."
        },
        "sport": {
          "enum": [
            "nfl",
            "ncaaf",
            "nba",
            "ncaab",
            "nhl",
            "mlb",
            "football",
            "f1",
            "motogp"
          ],
          "type": "string",
          "description": "Optional. One sport: nfl = NFL, ncaaf = College football, nba = NBA, ncaab = College basketball, nhl = NHL, mlb = MLB, football = Football (soccer), f1 = F1, motogp = MOTOGP."
        }
      },
      "additionalProperties": false
    }
    arguments 28 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 a5d0253e814d3f6e.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/a5d0253e814d3f6e/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/a5d0253e814d3f6e/badge.svg)](https://brick.blue/agent/a5d0253e814d3f6e?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
90%

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.