Tool reference¶
Server: atelier-mcp · Tools: 18 · Result form: JSON text content
Every tool follows one record: intent, a parameter table, and one example call with an example result. Parameters marked required must be supplied; the rest fall through to a server default. Results are illustrative — field values vary with live data.
Errors are data
A backend failure returns {"ok": false, "error": "..."} as a normal result, not
a protocol error. A client reads it and adapts in the same loop.
Platform¶
platform_health¶
Liveness of the backing services — overseer, overdex-server, overwatch, and the pulsar ClickHouse. Call first, before you do real work.
| Param | Type | Required | Default | Notes |
|---|---|---|---|---|
| none |
Collectors¶
list_collectors¶
List the caller's deployed market-data collectors with their services and status.
| Param | Type | Required | Default | Notes |
|---|---|---|---|---|
| none |
{
"services": [
{ "service_id": "63060972", "status": "active", "exchange": "binance", "symbol": "BTCUSDT" }
]
}
deploy_collector¶
Register a remote (bring-your-own) market-data collector on an exchange. Returns
service_id, binding_id, and the agent JWT for running your own agent container
against the gateway with that token.
This tool is remote bring-your-own only. It registers the collector and hands
back a JWT; the caller runs their own agent container against the gateway with that
JWT. The overseer never spawns a platform-managed container from this tool. Consult
list_cex_options for a venue's native symbol format, market
types, and valid order-book depths before calling.
| Param | Type | Required | Default | Notes |
|---|---|---|---|---|
exchange |
string | yes | Lowercase venue id, e.g. binance, coinbase, kraken |
|
symbols |
string[] | yes | Venue-native symbol form, one worker each — binance BTCUSDT, coinbase BTC-USD, kraken BTC/USD |
|
market_type |
string | no | spot |
e.g. spot, perpetual |
region |
string | no | Advisory: the colocation region this choice is based on | |
orderbook |
bool | no | true |
Collect an order book |
orderbook_depth |
int | no | 50 |
Order book depth |
trades |
bool | no | true |
Collect trades |
kind |
string | no | data |
data (synchronized + parquet) or market (raw) |
Datatype defaults land order book (depth 50) and trades ON; liquidations, funding rates, and open interest OFF.
{
"tool": "deploy_collector",
"arguments": {
"exchange": "binance",
"symbols": ["BTCUSDT"],
"market_type": "spot"
}
}
collector_status¶
Get a collector's status — service, binding, and recent commands — by service_id.
| Param | Type | Required | Default | Notes |
|---|---|---|---|---|
service_id |
string | yes | The id returned by deploy_collector |
{
"service": { "service_id": "63060972", "status": "active" },
"binding": { "binding_id": "cfb7688a", "status": "active" },
"commands": []
}
collector_command¶
Send a live command to a collector.
| Param | Type | Required | Default | Notes |
|---|---|---|---|---|
service_id |
string | yes | Target collector | |
kind |
string | yes | task_pause, task_resume, binding_release, or agent_restart |
collector_health¶
Health of a deployed collector: a top-line verdict (healthy · starting ·
degraded · silent) plus liveness and data-landing detail. Answers "is the
collector I deployed actually producing data?" — a fresh deploy reads as starting
until data lands.
| Param | Type | Required | Default | Notes |
|---|---|---|---|---|
service_id |
string | yes | Target collector |
{
"service_id": "63060972",
"binding_id": "cfb7688a",
"verdict": "starting",
"service_status": "active",
"binding_status": "active",
"liveness": { "connected": true, "heartbeat_age_s": 4, "ws_latency_ms": 22.1 },
"landing": { "rows_last_5m": 0, "total_rows": 0, "last_row_age_s": null,
"expected_first_data_by": "2026-07-03T18:05:00Z" }
}
stop_collector¶
Operator-stop a collector by service_id. Use it to clean up a collector you
deployed.
| Param | Type | Required | Default | Notes |
|---|---|---|---|---|
service_id |
string | yes | Target collector |
Deploy-prep¶
list_cex_options¶
List every deployable CEX option: the 12 supported venues with their native symbol
format (with example), market types, valid order-book depths, and datatype
availability. Consult this before deploy_collector to pick a
correct exchange, symbols, market_type, and orderbook_depth.
| Param | Type | Required | Default | Notes |
|---|---|---|---|---|
| none |
{
"venues": [
{
"exchange": "binance",
"label": "Binance",
"symbol_format": "concatenated uppercase",
"symbol_example": "BTCUSDT",
"market_types": ["spot"],
"orderbook_depths": [5, 10, 20, 50, 100, 500, 1000],
"default_orderbook_depth": 50,
"datatypes": [
{ "name": "orderbook", "available": true },
{ "name": "trades", "available": true },
{ "name": "funding", "available": false, "pending_on": "perpetual endpoint routing" }
]
},
{
"exchange": "coinbase",
"label": "Coinbase",
"symbol_format": "dash-separated",
"symbol_example": "BTC-USD",
"market_types": ["spot"],
"orderbook_depths": [50],
"default_orderbook_depth": 50,
"datatypes": [
{ "name": "orderbook", "available": true },
{ "name": "trades", "available": true }
]
}
]
}
Colocation¶
query_colocation¶
Query the colocation oracle for the best AWS region per exchange, ranked by latency
score. Omit exchange for all venues.
| Param | Type | Required | Default | Notes |
|---|---|---|---|---|
exchange |
string | no | Filter to one venue; omit for all, ranked by score |
{
"count": 1,
"exchanges": [
{ "exchange": "binance", "region": "ap-northeast-1", "score": 0.96 }
]
}
Governance¶
governance_catalog¶
The governance catalog: every declared stream reconciled with observed reality,
labeled present, absent, or stale. All filters are optional.
| Param | Type | Required | Default | Notes |
|---|---|---|---|---|
exchange |
string | no | Filter by venue | |
market_type |
string | no | Filter by market type | |
symbol |
string | no | Filter by symbol | |
datatype |
string | no | Filter by datatype | |
presence |
string | no | present, absent, or stale |
{
"streams": [
{ "exchange": "coinbase", "market_type": "spot", "symbol": "BTC/USDT",
"datatype": "orderbook", "presence": "present" }
]
}
stream_scorecard¶
Completeness and quality scorecard for one stream. window_secs recomputes
completeness live over a trailing window. Symbols may contain a slash (BTC/USDT).
| Param | Type | Required | Default | Notes |
|---|---|---|---|---|
exchange |
string | yes | Venue id | |
market_type |
string | yes | e.g. spot |
|
symbol |
string | yes | As the platform records it, may contain a slash | |
datatype |
string | yes | orderbook, trades, funding, open_interest, or liquidations |
|
window_secs |
int | no | Recompute completeness over this trailing window (seconds) |
{
"tool": "stream_scorecard",
"arguments": {
"exchange": "coinbase", "market_type": "spot",
"symbol": "BTC/USDT", "datatype": "orderbook"
}
}
{
"exchange": "coinbase", "symbol": "BTC/USDT", "datatype": "orderbook",
"completeness": { "grade": "critical", "ratio": 0.049 },
"quality": { "max_severity": "none", "checks": [] }
}
governance_datasets¶
The governance file-level dataset catalog over the parquet lake, across all datatypes.
| Param | Type | Required | Default | Notes |
|---|---|---|---|---|
| none |
{
"datasets": [
{ "exchange": "kraken", "symbol": "ETH-USD", "datatype": "trades", "files": 12 }
]
}
Fit & serve¶
list_datasets¶
List fittable datasets (venue, symbol, datatype), each with an opaque dataset_id.
| Param | Type | Required | Default | Notes |
|---|---|---|---|---|
| none |
{
"datasets": [
{ "dataset_id": "ds_9f3a…", "exchange": "kraken", "symbol": "ETH-USD",
"datatype": "trades" }
]
}
fit_pricing¶
The fit price in compute tokens. A fit charges compute tokens against the caller's identity; this returns the current price so a client can report it before running a fit.
| Param | Type | Required | Default | Notes |
|---|---|---|---|---|
| none |
fit_hawkes¶
Fit a univariate Hawkes process (MLE) to a dataset and persist it. Returns fitted
params and diagnostics; the chart series are omitted — fetch them with get_fit. A
non-converged fit returns an error you can adapt to by loosening tolerance. Prefer
a trades dataset.
| Param | Type | Required | Default | Notes |
|---|---|---|---|---|
dataset_id |
string | yes | From list_datasets |
|
tolerance |
float | no | 1e3 |
Gradient infinity-norm; tight for real data — loosen (e.g. 1e4, 5e4) if not converged |
max_iter |
int | no | 50000 |
Optimizer iteration cap |
train_ratio |
float | no | 0.8 |
Train split fraction |
learning_rate |
float | no | 1e-2 |
Gradient-ascent step |
seed |
int | no | Reproducibility seed |
{
"fit_id": "fit_7c21…",
"converged": true,
"branching_ratio": 0.182,
"n_train": 561,
"tolerance_used": 10000
}
list_fits¶
List the caller's fit runs, newest first.
| Param | Type | Required | Default | Notes |
|---|---|---|---|---|
| none |
{
"fits": [
{ "fit_id": "fit_7c21…", "dataset_id": "ds_9f3a…", "converged": true,
"created_at": "2026-07-03T17:50:00Z" }
]
}
get_fit¶
Fetch a persisted fit artifact by fit_id, including the full chart series.
| Param | Type | Required | Default | Notes |
|---|---|---|---|---|
fit_id |
string | yes | From fit_hawkes or list_fits |
{
"fit_id": "fit_7c21…",
"converged": true,
"branching_ratio": 0.182,
"series": { "intensity": [ ], "residuals": [ ] }
}
forecast_fit¶
Forecast event arrivals from a stored fit — median plus a p25/p75 band. Reproducible for a given seed.
| Param | Type | Required | Default | Notes |
|---|---|---|---|---|
fit_id |
string | yes | The fit to forecast from | |
n_forecast |
int | no | 50 |
Steps to forecast |
mc_paths |
int | no | 500 |
Monte-Carlo paths; >1 gives a p25/p75 band |
seed |
int | no | Reproducibility seed |