Skip to main content
Glama

L2WS

Server Details

Binance order book (L2), trades, SQL, backtests and AI price levels for BTC, ETH and SOL.

If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

B3.2/5.0

Scored across 13 tools

Disambiguation5/5

Each tool targets a distinct resource or action: data catalog/schema/quality, SQL querying, strategy save/list, backtest run/status/report/list, and AI feeds. The backtest tools are related but clearly separable by lifecycle stage (queue, monitor, inspect final report, list recent runs), so misselection is unlikely.

Naming Consistency4/5

Names are uniformly snake_case and most follow verb_noun patterns (get_*, list_*, run_*, save_*). Minor deviations exist in resource-first names like backtest_report, backtest_status, and sql_query, but they remain readable and predictable.

Tool Count5/5

With 13 tools, the surface is well-scoped for a data/backtesting platform. Each tool covers a distinct part of the workflow without excessive fragmentation.

Completeness4/5

Core workflows are covered: discover/query data, save and list strategies, run and inspect backtests, and access AI outputs. Minor gaps remain, such as no explicit strategy update/delete, no backtest cancel, and no single-strategy detail tool, but agents can mostly work around them.

Available Tools

13 tools
backtest_reportBInspect

Full report of a finished run: FARM, PnL, WR, DD, regimes, trades.

Inputs: run_id (required).

backtest_statusCInspect

Run status: queued | running (+progress) | done | failed.

Inputs: run_id (required).

catalog_streamsAInspect

List of data streams: name, tier, kind, day range, description. all=True also lists streams outside your plan, marked available_on.

Inputs: all. Returns: result

get_ai_levelsCInspect

Recorded AI levels, prediction history and observed outcomes. Free access is delayed.

Inputs: model, symbol.

get_ai_traderBInspect

Our AI trader: training status, latest exam on held-out weeks after fees, released decisions (free: 24 h delay).

Inputs: no named parameters.

get_contract_docsBInspect

Strategy contract and sandbox rules (the same text as on /docs-contract).

Inputs: no named parameters. Returns: result

get_qualityCInspect

Q index and data-quality metrics of a day (day as YYYY-MM-DD).

Inputs: day (required).

get_schemaCInspect

Columns and types of a stream.

Inputs: stream (required).

list_runsDInspect

Latest runs: id, status, FARM, parameters, queue time.

Inputs: limit. Returns: result

list_strategiesCInspect

My strategies: id, name, version, latest FARM.

Inputs: no named parameters. Returns: result

run_backtestBInspect

Queue a backtest. Needs strategy_id OR code (a one-off strategy). Minutes are charged at queue time.

Inputs: date_to (required), symbols (required), date_from (required), code, +3 more.

save_strategyBInspect

Save a strategy (the contract is in get_contract_docs). Returns strategy_id, version and the lint result.

Inputs: code (required), name (required).

sql_queryBInspect

SELECT/WITH over the streams (the day is a virtual column day). The result holds at most min(limit, 50000) rows.

Inputs: query (required), limit.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      C
      maintenance
      Real-time institutional crypto & equity orderflow intelligence. Detects BUY/SELL pressure from live Binance L2 orderbook and aggressive trade feeds for any USDT pair or US equity.
      10
      36 PyPI
      5
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      MidasFlow Flow API - Cross-exchange order flow, whale detection, liquidations, funding rates, squeeze alerts for AI agents. Native MCP server.
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Read-only crypto perps microstructure for AI agents: normalized cross-exchange market state (funding + multi-year percentile, OI, volume, CVD, order-book imbalance, liquidations, basis), OHLCV, 15-min state history, and measured conditional outcomes (historical base rates, not predictions) — 6 assets across Binance, Bybit, OKX and Hyperliquid, every metric with self-declared coverage and freshness
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources