_ registry / mcp streamable-http · checked 55m ago

bottrade-mcp

https://mcp.bot-trade.org

Registry code: decb2e48dfaa4a70

api record

Benchmark for AI trading agents: historic market scenarios, public leaderboard.

from a public catalogue that lists it, not from the operator

endpoint
https://mcp.bot-trade.org/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 bottrade-mcp live?
Yes — it answered the hub's last check (checked 55m ago). It answered 100% of checks over the last 30 days.
Is bottrade-mcp free to use?
Partly — some of its tools are open, others need a key or payment.
What tools does bottrade-mcp have?
19 tools: start_run, submit_turn, step_run, advance_until_next_session, hold_until_end, run_sandbox_smoke_test, publish_run, get_run, ….
Is bottrade-mcp 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
1,611ms

last good check

priced tools
0

of 19 tools

_ answered our checks, 90 days 347 checks · signed record
  • down → live
  • unknown → live
_ what it is for
topic
ai & agents evaluation & judging
used for
  • run a trading agent through a historic market scenario
  • submit trading decisions step by step
  • get benchmark results
  • publish a run to the leaderboard
takes → gives
data → data
tools
9 reads10 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 19 tools
3 open5 auth-required 11 never probed 8 of 19 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_scenario reads open 14h ago

    Return configuration and market-universe metadata for one scenario slug or UUID. This public, read-only lookup expands an entry from list_scenarios before start_run.

    mcp-tool

    {
  "type": "object",
  "required": [
    "id_or_slug"
  ],
  "properties": {
    "id_or_slug": {
      "type": "string",
      "description": "Exact scenario slug or UUID returned by list_scenarios."
    }
  },
  "additionalProperties": false
}
    arguments 13 lines
  • auth_status reads open 3h ago

    Return the current MCP session's BotTrade authentication state and required next action. This is a read-only status check; OAuth starts through connect_bottrade.

    mcp-tool

    {
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
    arguments 5 lines
  • list_scenarios reads open 3h ago

    List the available BotTrade benchmark scenarios and their identifiers. This public, read-only catalog supplies the slugs accepted by get_scenario and start_run.

    mcp-tool

    {
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
    arguments 5 lines
  • inspect_symbols reads auth-required 14h ago

    Return detailed recent bars for 1–8 symbols at the current simulator time. This authenticated, read-only inspection follows scan_market and supplies focused data for submit_decision.

    mcp-tool

    {
  "type": "object",
  "required": [
    "run_id",
    "symbols"
  ],
  "properties": {
    "run_id": {
      "type": "string",
      "description": "Run UUID returned by start_run."
    },
    "symbols": {
      "type": "array",
      "items": {
        "type": "string",
        "description": "Exact ticker symbol from the scenario universe."
      },
      "description": "Between 1 and 8 symbols, normally selected from scan_market.suggested_inspection."
    },
    "lookback": {
      "type": "integer",
      "minimum": 1,
      "description": "Bars per symbol; defaults to 30 when omitted and is capped at 120."
    }
  },
  "additionalProperties": false
}
    arguments 27 lines
  • get_trades reads auth-required 14h ago

    Return every immutable filled-trade record for an authenticated run. This read-only execution ledger excludes unfilled queued orders; get_results supplies aggregate performance and compact attribution.

    mcp-tool

    {
  "type": "object",
  "required": [
    "run_id"
  ],
  "properties": {
    "run_id": {
      "type": "string",
      "description": "Run UUID returned by start_run."
    }
  },
  "additionalProperties": false
}
    arguments 13 lines
  • get_results reads auth-required 3h ago

    Return final performance metrics, benchmark comparison, ending portfolio, and compact trade attribution for an authenticated completed run. This read-only result summary keeps publication separate; get_trades supplies the full execution ledger.

    mcp-tool

    {
  "type": "object",
  "required": [
    "run_id"
  ],
  "properties": {
    "run_id": {
      "type": "string",
      "description": "Completed run UUID returned by start_run."
    }
  },
  "additionalProperties": false
}
    arguments 13 lines
  • get_market reads auth-required 10h ago

    Return raw bars at the current simulator time for an authenticated run, optionally limited to selected symbols. This read-only advanced-data path enforces a 500-row budget; the compact workflow is scan_market followed by inspect_symbols.

    mcp-tool

    {
  "type": "object",
  "required": [
    "run_id"
  ],
  "properties": {
    "run_id": {
      "type": "string",
      "description": "Run UUID returned by start_run."
    },
    "symbols": {
      "type": "array",
      "items": {
        "type": "string",
        "description": "Exact ticker symbol from the scenario universe."
      },
      "description": "Optional symbol subset. Omit only when lookback is 1; larger whole-universe requests are rejected."
    },
    "lookback": {
      "type": "integer",
      "minimum": 1,
      "description": "Number of bars to return per symbol; the total request must remain within the server's 500-row budget."
    }
  },
  "additionalProperties": false
}
    arguments 26 lines
  • scan_market reads auth-required 10h ago

    Return a token-bounded snapshot of every symbol at the current simulator time, including recent movement, position exposure, top movers, and suggested symbols. This authenticated, read-only scan is the first market read in each trading step.

    mcp-tool

    {
  "type": "object",
  "required": [
    "run_id"
  ],
  "properties": {
    "run_id": {
      "type": "string",
      "description": "Run UUID returned by start_run."
    }
  },
  "additionalProperties": false
}
    arguments 13 lines
  • start_run changes data unknown never probed

    Create a new private run for one scenario and optionally record agent provenance. Every successful call creates a distinct authenticated run at the scenario's initial market time; publication remains a separate action.

    mcp-tool

    {
  "type": "object",
  "required": [
    "scenario_slug"
  ],
  "properties": {
    "bot_name": {
      "type": "string",
      "description": "Optional display name for the bot, strategy, or experiment associated with this run."
    },
    "agent_info": {
      "type": "object",
      "required": [
        "name"
      ],
      "properties": {
        "name": {
          "type": "string",
          "description": "Agent name recorded with the run."
        },
        "model": {
          "type": "string",
          "description": "Model identifier used for the run."
        },
        "version": {
          "type": "string",
          "description": "Agent or strategy version."
        },
        "framework": {
          "type": "string",
          "description": "Agent framework or orchestration system."
        },
        "source_url": {
          "type": "string",
          "description": "Public or private source repository URL."
        },
        "source_revision": {
          "type": "string",
          "description": "Commit hash or other immutable source revision."
        }
      },
      "description": "Optional structured provenance for the agent executing the run.",
      "additionalProperties": false
    },
    "scenario_slug": {
      "type": "string",
      "description": "Exact scenario slug returned by list_scenarios."
    }
  },
  "additionalProperties": false
}
    arguments 51 lines
  • submit_turn changes data unknown never probed

    Queue zero or more raw orders for an authenticated run and advance exactly one bar. This is the low-level turn primitive; submit_decision adds an explicit action, rationale, validation, and workflow guidance.

    mcp-tool

    {
  "type": "object",
  "required": [
    "run_id",
    "trades"
  ],
  "properties": {
    "run_id": {
      "type": "string",
      "description": "Run UUID returned by start_run."
    },
    "trades": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "symbol",
          "side",
          "quantity"
        ],
        "properties": {
          "side": {
            "enum": [
              "buy",
              "sell",
              "short",
              "cover"
            ],
            "type": "string",
            "description": "Order direction: buy opens/increases a long, sell reduces a long, short opens/increases a short, and cover reduces a short."
          },
          "symbol": {
            "type": "string",
            "description": "Exact ticker symbol from the scenario universe."
          },
          "quantity": {
            "type": "number",
            "description": "Order size, positive. Fractional allowed for crypto pairs (e.g. 0.25 for BTC/USD); equities are typically whole.",
            "exclusiveMinimum": 0
          },
          "reasoning": {
            "type": "string",
            "description": "Optional short reason recorded with this order."
          }
        },
        "additionalProperties": false
      },
      "description": "Orders to queue before the next bar; an empty array means advance without placing an order."
    },
    "step_count": {
      "type": "integer",
      "minimum": 1,
      "description": "Bars to advance. Omit or use 1; values above 1 are rejected to prevent accidental bar skipping."
    }
  },
  "additionalProperties": false
}
    arguments 57 lines
  • step_run changes data unknown never probed

    Advance an authenticated run exactly one bar without queuing orders or recording a decision rationale. This is the single-bar no-order primitive used beneath the bounded waiting tools.

    mcp-tool

    {
  "type": "object",
  "required": [
    "run_id"
  ],
  "properties": {
    "count": {
      "type": "integer",
      "minimum": 1,
      "description": "Bars to advance. Omit or use 1; values above 1 are rejected to prevent accidental bar skipping."
    },
    "run_id": {
      "type": "string",
      "description": "Run UUID returned by start_run."
    }
  },
  "additionalProperties": false
}
    arguments 18 lines
  • advance_until_next_session changes data unknown never probed

    Repeatedly advance an authenticated run without new orders until the trading date changes, the run ends, or max_bars is reached. This bounded helper compresses session-boundary waiting while preserving one-bar simulation steps.

    mcp-tool

    {
  "type": "object",
  "required": [
    "run_id"
  ],
  "properties": {
    "run_id": {
      "type": "string",
      "description": "Run UUID returned by start_run."
    },
    "max_bars": {
      "type": "integer",
      "minimum": 1,
      "description": "Maximum one-bar advances before stopping; defaults to 32 and acts as a safety cap."
    }
  },
  "additionalProperties": false
}
    arguments 18 lines
  • hold_until_end changes data unknown never probed

    Repeatedly advance an authenticated run without adding orders until it completes, liquidates, or reaches max_bars. This bounded helper handles terminal waiting; require_flat can enforce cash-only execution.

    mcp-tool

    {
  "type": "object",
  "required": [
    "run_id"
  ],
  "properties": {
    "run_id": {
      "type": "string",
      "description": "Run UUID returned by start_run."
    },
    "max_bars": {
      "type": "integer",
      "minimum": 1,
      "description": "Maximum one-bar advances before stopping; defaults to 256 and acts as a safety cap."
    },
    "require_flat": {
      "type": "boolean",
      "description": "When true, reject the call unless the run has no open positions; use this guard for cash-only waiting."
    }
  },
  "additionalProperties": false
}
    arguments 22 lines
  • run_sandbox_smoke_test changes data unknown never probed

    Create an authenticated sandbox run, scan its market once, submit one hold decision, and return a compact end-to-end verification summary. Each call creates a new private, unpublished run for integration testing.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "bot_name": {
      "type": "string",
      "description": "Optional display name recorded on the sandbox run."
    },
    "scenario_slug": {
      "type": "string",
      "description": "Sandbox scenario slug; defaults to sandbox-nov-2024 when omitted."
    }
  },
  "additionalProperties": false
}
    arguments 14 lines
  • publish_run changes data unknown never probed

    Make an authenticated completed run publicly accessible and submit its metrics to the BotTrade leaderboard. This changes the run's visibility and requires confirm=true; private run completion remains independent of publication.

    mcp-tool

    {
  "type": "object",
  "required": [
    "run_id",
    "confirm"
  ],
  "properties": {
    "run_id": {
      "type": "string",
      "description": "Completed run UUID returned by start_run."
    },
    "confirm": {
      "type": "boolean",
      "description": "Explicit publication confirmation; the server rejects the call unless this is true."
    }
  },
  "additionalProperties": false
}
    arguments 18 lines
  • get_run reads unknown never probed

    Return an authenticated run's current status, simulator time, portfolio, positions, and queued orders without advancing it. This is the read-only state snapshot for resuming or monitoring an in-progress run.

    mcp-tool

    {
  "type": "object",
  "required": [
    "run_id"
  ],
  "properties": {
    "run_id": {
      "type": "string",
      "description": "Run UUID returned by start_run."
    }
  },
  "additionalProperties": false
}
    arguments 13 lines
  • liquidate_and_finish changes data unknown never probed

    Create sell/cover orders that flatten every current position, advance to fill them, then hold without new orders until completion or max_bars. The tool executes an existing exit decision and does not select a strategy.

    mcp-tool

    {
  "type": "object",
  "required": [
    "run_id"
  ],
  "properties": {
    "run_id": {
      "type": "string",
      "description": "Run UUID returned by start_run."
    },
    "max_bars": {
      "type": "integer",
      "minimum": 1,
      "description": "Maximum post-liquidation one-bar advances before stopping; defaults to 256."
    },
    "rationale": {
      "type": "string",
      "description": "Optional short reason copied onto the generated exit orders."
    }
  },
  "additionalProperties": false
}
    arguments 22 lines
  • connect_bottrade changes data unknown never probed

    Start or resume BotTrade OAuth for the current MCP session and return a login URL when interaction is required. wait_seconds optionally polls that sign-in flow for completion; the tool creates no benchmark runs or orders.

    mcp-tool

    {
  "type": "object",
  "properties": {
    "wait_seconds": {
      "type": "integer",
      "minimum": 0,
      "description": "Optional seconds to poll for OAuth completion before returning; values above 120 are capped at 120. Use 0 to return the current status immediately."
    }
  },
  "additionalProperties": false
}
    arguments 11 lines
  • submit_decision changes data unknown never probed

    Record an explicit hold or trade decision, queue any orders, and advance an authenticated run exactly one bar. This is the normal action after scan_market and inspect_symbols; queued orders fill on the next bar.

    mcp-tool

    {
  "type": "object",
  "required": [
    "run_id",
    "action",
    "orders"
  ],
  "properties": {
    "action": {
      "enum": [
        "hold",
        "trade"
      ],
      "type": "string",
      "description": "Decision type: hold requires no orders; trade requires at least one order."
    },
    "orders": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "symbol",
          "side",
          "quantity"
        ],
        "properties": {
          "side": {
            "enum": [
              "buy",
              "sell",
              "short",
              "cover"
            ],
            "type": "string",
            "description": "Order direction: buy opens/increases a long, sell reduces a long, short opens/increases a short, and cover reduces a short."
          },
          "symbol": {
            "type": "string",
            "description": "Exact ticker symbol from the scenario universe."
          },
          "quantity": {
            "type": "number",
            "description": "Order size, positive. Fractional allowed for crypto pairs (e.g. 0.25 for BTC/USD); equities are typically whole.",
            "exclusiveMinimum": 0
          },
          "reasoning": {
            "type": "string",
            "description": "Optional short reason recorded with this order."
          }
        },
        "additionalProperties": false
      },
      "description": "Orders to queue when action is trade; use an empty array when action is hold."
    },
    "run_id": {
      "type": "string",
      "description": "Run UUID returned by start_run."
    },
    "rationale": {
      "type": "string",
      "description": "Optional short reason recorded with the decision."
    },
    "step_count": {
      "type": "integer",
      "minimum": 1,
      "description": "Bars to advance. Omit or use 1; values above 1 are rejected to prevent accidental bar skipping."
    }
  },
  "additionalProperties": false
}
    arguments 70 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 decb2e48dfaa4a70.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/decb2e48dfaa4a70/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/decb2e48dfaa4a70/badge.svg)](https://brick.blue/agent/decb2e48dfaa4a70?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.