_ registry / mcp streamable-http · checked 4h ago

lazyedge

https://api.lazyedge.net

Registry code: cf26fd9ff55fba82

api record

LazyEdge serves its own model's numbers for NBA and NFL games beside the live market, before the start and in play. Every row carries `read`, one plain sentence saying what the row means; quote or paraphrase it when you answer. Glossary: probabilities and prices run from 0 to 1 (a price of 0.62 is 62 cents, the market's chance). `pick` is the team our number has winning and `pick_p` our chance on it. `corrected_p` is what our pregame picks at that chance have actually won this season. An edge (`edge_pp`, `play_edge_pp`, `best_edge_pp`) is our chance minus the market's, in percentage points,…

endpoint
https://api.lazyedge.net/v1/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 lazyedge live?
Yes — it answered the hub's last check (checked 4h ago). It answered 100% of checks over the last 30 days.
Is lazyedge free to use?
Yes — the hub reached it with no key and no payment.
What tools does lazyedge have?
11 tools: nba_hit_rates, nfl_props, nfl_prop_pairs, results, line_moves, nba_games, nba_props, nba_spreads, ….
Is lazyedge 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
598ms

last good check

priced tools
0

of 11 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 11 tools
6 open 5 never probed 6 of 11 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.

  • nba_games open 31h ago

    Every NBA game today, before the tip and in play: the team our number has winning (`pick`) and our chance (`pick_p`), what our pregame picks at that chance have won this season, the market price on our pick, the edge, the score and the clock. Without an API key: today's free game only; any other game says what a plan unlocks.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "live_only": {
          "type": "boolean",
          "description": "Only games in play."
        }
      },
      "additionalProperties": false
    }
    arguments 10 lines
  • nba_props open 31h ago

    NBA player props for today's games: the line, our projection, our chance of the over, the market's and the edge in percentage points, live once a game starts. Largest edges first. Without an API key: today's free game only; any other game says what a plan unlocks.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "stat": {
          "enum": [
            "pts",
            "reb",
            "ast"
          ],
          "type": "string"
        },
        "limit": {
          "type": "integer",
          "maximum": 60,
          "minimum": 1,
          "description": "Rows to return, largest edge first."
        },
        "player": {
          "type": "string",
          "description": "Part of a player's name."
        },
        "game_id": {
          "type": "string"
        }
      },
      "additionalProperties": false
    }
    arguments 27 lines
  • nba_spreads open 4h ago

    Every NBA spread line on Kalshi and Polymarket for a game or a team today: our chance the team covers, the price on each venue and the edge, largest first. The same line on both venues side by side shows where it is priced lower. Without an API key: today's free game only; any other game says what a plan unlocks.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "team": {
          "type": "string",
          "description": "Team code, such as NY, LAL or BOS."
        },
        "limit": {
          "type": "integer",
          "maximum": 60,
          "minimum": 1,
          "description": "Rows to return, largest edge first."
        },
        "game_id": {
          "type": "string"
        }
      },
      "additionalProperties": false
    }
    arguments 19 lines
  • nfl_games open 4h ago

    This week's NFL games: our pick and chance, our projected score, the market's chance, our margin and total beside the spread and total lines, and the strongest edge on each game. Without an API key: today's free game only; any other game says what a plan unlocks.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • free_game open 31h ago

    Today's free game, open to everyone without a key: the league, the matchup, the start time, our number on it now with the time it was produced and whether it is pregame or live, how far it has moved since the start, and which tools open the rest of it. Call this first without a key.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • nba_totals open 4h ago

    Each NBA game's total today: the market's line and price beside our projected total, pregame and live. Without an API key: today's free game only; any other game says what a plan unlocks.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "team": {
          "type": "string",
          "description": "Team code, such as NY, LAL or BOS."
        },
        "game_id": {
          "type": "string"
        }
      },
      "additionalProperties": false
    }
    arguments 13 lines
  • nba_hit_rates unknown never probed

    How often an NBA player has gone over a line: his recent game log for a stat, his averages, and with a line how many of his last 5, last 10 and season games went over it.

    mcp-tool

    {
      "type": "object",
      "required": [
        "player"
      ],
      "properties": {
        "line": {
          "type": "number",
          "description": "Count the games over this line."
        },
        "stat": {
          "enum": [
            "pts",
            "reb",
            "ast",
            "3pm",
            "pra",
            "stl",
            "blk"
          ],
          "type": "string"
        },
        "games": {
          "type": "integer",
          "maximum": 82,
          "minimum": 1
        },
        "player": {
          "type": "string",
          "description": "The player's name."
        }
      },
      "additionalProperties": false
    }
    arguments 34 lines
  • nfl_props unknown never probed

    NFL player props this week where a venue lists a line: our mean and median projection, our chance of the over at the line, the market's and the edge. Largest edges first, role questions left out. Without an API key: today's free game only; any other game says what a plan unlocks.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "stat": {
          "enum": [
            "pass_yds",
            "rush_yds",
            "rec_yds",
            "receptions"
          ],
          "type": "string"
        },
        "limit": {
          "type": "integer",
          "maximum": 60,
          "minimum": 1,
          "description": "Rows to return, largest edge first."
        },
        "player": {
          "type": "string"
        },
        "game_id": {
          "type": "string"
        }
      },
      "additionalProperties": false
    }
    arguments 27 lines
  • nfl_prop_pairs unknown never probed

    Same-game NFL prop pairs this week whose legs move together (a QB's passing yards with a teammate's receiving yards or catches, one receiver's catches with his yards): our chance both overs hit priced together with the correlation measured on every season since 2019, beside the two chances multiplied, and our chance and the market's on each leg. Strongest first; `favoured` marks a pair whose two overs we both favour at or above the market. Without an API key: today's free game only; any other game says what a plan unlocks.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "limit": {
          "type": "integer",
          "maximum": 60,
          "minimum": 1,
          "description": "Rows to return, largest edge first."
        },
        "game_id": {
          "type": "string"
        },
        "favoured_only": {
          "type": "boolean",
          "description": "Only pairs whose two overs we both favour."
        }
      },
      "additionalProperties": false
    }
    arguments 19 lines
  • results unknown never probed

    How our numbers have graded: an NBA night or NFL week (the newest by default), each finished game with our pregame call on the winner, the spread and the total and whether it was right, and the season totals against the market. Free without a key.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "date": {
          "type": "string",
          "description": "An NBA night, YYYY-MM-DD (newest when left out)."
        },
        "week": {
          "type": "integer",
          "maximum": 22,
          "minimum": 1,
          "description": "An NFL week this season (newest when left out)."
        },
        "sport": {
          "enum": [
            "nba",
            "nfl"
          ],
          "type": "string"
        }
      },
      "additionalProperties": false
    }
    arguments 23 lines
  • line_moves unknown never probed

    DraftKings' opening spread, total and moneyline beside its line now for each game still to start, with which way each moved relative to our number. Largest moves first. Without an API key: today's free game only; any other game says what a plan unlocks.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "sport": {
          "enum": [
            "nba",
            "nfl"
          ],
          "type": "string"
        }
      },
      "additionalProperties": false
    }
    arguments 13 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 cf26fd9ff55fba82.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/cf26fd9ff55fba82/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/cf26fd9ff55fba82/badge.svg)](https://brick.blue/agent/cf26fd9ff55fba82?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.