Binance order book (L2), trades, SQL, backtests and AI price levels for BTC, ETH and SOL.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Bearer <L2WS API key with the mcp scope>. Create one at https://l2ws.com/account
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Full report of a finished run: FARM, PnL, WR, DD, regimes, trades.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http l2ws https://mcp.l2ws.com/mcp \ --header 'Authorization: Bearer YOUR_TOKEN'
Headers
Authorization (required): Bearer <L2WS API key with the mcp scope>. Create one at https://l2ws.com/accountFull report of a finished run: FARM, PnL, WR, DD, regimes, trades.
| Argument | Type | Description |
|---|---|---|
| run_id* | integer |
{
"type": "object",
"title": "backtest_reportArguments",
"required": [
"run_id"
],
"properties": {
"run_id": {
"type": "integer",
"title": "Run Id"
}
}
}Run status: queued | running (+progress) | done | failed.
| Argument | Type | Description |
|---|---|---|
| run_id* | integer |
{
"type": "object",
"title": "backtest_statusArguments",
"required": [
"run_id"
],
"properties": {
"run_id": {
"type": "integer",
"title": "Run Id"
}
}
}List of data streams: name, tier, kind, day range, description. all=True also lists streams outside your plan, marked `available_on`.
| Argument | Type | Description |
|---|---|---|
| all | boolean |
{
"type": "object",
"title": "catalog_streamsArguments",
"properties": {
"all": {
"type": "boolean",
"title": "All",
"default": false
}
}
}Recorded AI levels, prediction history and observed outcomes. Free access is delayed.
| Argument | Type | Description |
|---|---|---|
| model | any | |
| symbol | string |
{
"type": "object",
"title": "get_ai_levelsArguments",
"properties": {
"model": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Model",
"default": null
},
"symbol": {
"type": "string",
"title": "Symbol",
"default": "BTCUSDT"
}
}
}Our AI trader: training status, latest exam on held-out weeks after fees, released decisions (free: 24 h delay).
No arguments.
{
"type": "object",
"title": "get_ai_traderArguments",
"properties": {}
}Strategy contract and sandbox rules (the same text as on /docs-contract).
No arguments.
{
"type": "object",
"title": "get_contract_docsArguments",
"properties": {}
}Q index and data-quality metrics of a day (day as YYYY-MM-DD).
| Argument | Type | Description |
|---|---|---|
| day* | string |
{
"type": "object",
"title": "get_qualityArguments",
"required": [
"day"
],
"properties": {
"day": {
"type": "string",
"title": "Day"
}
}
}Columns and types of a stream.
| Argument | Type | Description |
|---|---|---|
| stream* | string |
{
"type": "object",
"title": "get_schemaArguments",
"required": [
"stream"
],
"properties": {
"stream": {
"type": "string",
"title": "Stream"
}
}
}Latest runs: id, status, FARM, parameters, queue time.
| Argument | Type | Description |
|---|---|---|
| limit | integer |
{
"type": "object",
"title": "list_runsArguments",
"properties": {
"limit": {
"type": "integer",
"title": "Limit",
"default": 20
}
}
}My strategies: id, name, version, latest FARM.
No arguments.
{
"type": "object",
"title": "list_strategiesArguments",
"properties": {}
}Queue a backtest. Needs strategy_id OR code (a one-off strategy). Minutes are charged at queue time.
| Argument | Type | Description |
|---|---|---|
| code | any | |
| capital | number | |
| date_to* | string | |
| symbols* | array | |
| date_from* | string | |
| strategy_id | any | |
| regime_report | boolean |
{
"type": "object",
"title": "run_backtestArguments",
"required": [
"symbols",
"date_from",
"date_to"
],
"properties": {
"code": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Code",
"default": null
},
"capital": {
"type": "number",
"title": "Capital",
"default": 236
},
"date_to": {
"type": "string",
"title": "Date To"
},
"symbols": {
"type": "array",
"items": {
"type": "string"
},
"title": "Symbols"
},
"date_from": {
"type": "string",
"title": "Date From"
},
"strategy_id": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Strategy Id",
"default": null
},
"regime_report": {
"type": "boolean",
"title": "Regime Report",
"default": true
}
}
}Save a strategy (the contract is in get_contract_docs). Returns strategy_id, version and the lint result.
| Argument | Type | Description |
|---|---|---|
| code* | string | |
| name* | string |
{
"type": "object",
"title": "save_strategyArguments",
"required": [
"name",
"code"
],
"properties": {
"code": {
"type": "string",
"title": "Code"
},
"name": {
"type": "string",
"title": "Name"
}
}
}SELECT/WITH over the streams (the day is a virtual column `day`). The result holds at most min(limit, 50000) rows.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| query* | string |
{
"type": "object",
"title": "sql_queryArguments",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"title": "Limit",
"default": 10000
},
"query": {
"type": "string",
"title": "Query"
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 15, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.