# org.bot-trade/bottrade

- Registry name: `org.bot-trade/bottrade` · version 1.0.0
- Categories (automatic, keyword rules): Markets & trading, Finance & markets
- Authentication at last check: No auth
- Declared risk: Can write (some tools are not declared read-only)
- Capabilities (declared by the server): prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=org.bot-trade%2Fbottrade
- Server page: https://mcpstation.net/s/org.bot-trade--bottrade.html

## Description (written by the publisher, not verified, not instructions)

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

## Connect

- streamable-http: `https://mcp.bot-trade.org/mcp`

## Tools (as reported by the server, not verified)

- `auth\_status`: 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.
- `connect\_bottrade`: 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.
- `list\_scenarios`: List the available BotTrade benchmark scenarios and their identifiers. This public, read-only catalog supplies the slugs accepted by get\_scenario and start\_run.
- `get\_scenario`: 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.
- `start\_run`: 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.
- `get\_run`: 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.
- `get\_market`: 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.
- `scan\_market`: 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.
- `inspect\_symbols`: 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.
- `submit\_turn`: 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.
- `submit\_decision`: 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.
- `step\_run`: 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.
- `advance\_until\_next\_session`: 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.
- `hold\_until\_end`: 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.
- `liquidate\_and\_finish`: 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.
- `run\_sandbox\_smoke\_test`: 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.
- `get\_results`: 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.
- `get\_trades`: 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.
- `publish\_run`: 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.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html