8-agent research committee, live analysis and scored news on US stocks and crypto, for any agent.
MCP Server: io.github.SimianX-AI/simianx
The MCP server at io.github.SimianX-AI/simianx provides live multi-agent analysis and scored market news. It focuses on US stocks and crypto, with output derived from SimianX AI. The server is identified by the slug io-github-simianx-ai-simianx.
🛠️ Key Features
Live multi-agent analysis
Scored market news
Covers US stocks and crypto
Source: SimianX AI
🚀 Use Cases
Monitor US stock and crypto news with scoring
Retrieve analytical outputs from a multi-agent setup for market events
Support research workflows that combine analysis and scored updates
⚡ Developer Benefits
Clear scope: US stocks and crypto market news
Structured, queryable access via an MCP server endpoint
⚠️ Limitations
No additional capabilities (tools, topics, or readme excerpts) are provided in the available server data
Run SimianX's four live AI agents once on a US stock or a crypto pair: Fundamental reads the business or the coin, Indicator the chart, Intelligence the news flow, and Decision turns it into a call with entry, stop and target and the next candle close. Returns a run id right away; each agent's result arrives in get_updates (or get_quick_read with wait) as it finishes, the decision last. After starting, follow it until done and tell the user every finished step; never wait for the user to ask. (uses points, metered on the models used like the website)
Parameters7
asset
string
required
crypto or stock (US stocks and ETFs)
symbol
string
required
Stock ticker (NVDA) or coin (BTC); crypto also takes a pair id such as BTC-USDT-SWAP
Only when the user asks for specific models: agent -> model id from list_models (paid plans). Leave out to run on the user's saved setup (get_settings)
language
string
optional
Language of the write-ups, e.g. en, zh-CN, ja (default: the account's)
idempotency_key
string
optional
Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice
Raw schema
{
"type": "object",
"properties": {
"asset": {
"type": "string",
"enum": [
"crypto",
"stock"
],
"description": "crypto or stock (US stocks and ETFs)"
},
"symbol": {
"type": "string",
"description": "Stock ticker (NVDA) or coin (BTC); crypto also takes a pair id such as BTC-USDT-SWAP"
},
"agents": {
"type": "array",
"items": {
"type": "string",
"enum": [
"indicator",
"intelligence",
"fundamental",
"decision"
]
},
"description": "Subset of the four live agents (default all four)"
},
"timeframe": {
"type": "string",
"description": "Candle timeframe. Crypto: 1m 5m 15m 1H 4H 1D. Stock: 1H 1D 1W 1mo. Default: the user's saved timeframe (get_settings)"
},
"models": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "Only when the user asks for specific models: agent -> model id from list_models (paid plans). Leave out to run on the user's saved setup (get_settings)"
},
"language": {
"type": "string",
"description": "Language of the write-ups, e.g. en, zh-CN, ja (default: the account's)"
},
"idempotency_key": {
"type": "string",
"maxLength": 128,
"description": "Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice"
}
},
"required": [
"asset",
"symbol"
],
"additionalProperties": false
}
get_quick_read
Status and results so far of a quick read. Pass wait (up to 25 s): the answer returns as soon as one more agent has finished; call again while status is queued or running, relaying each new agent.
Parameters3
wait
integer
optional
Seconds to wait for the next agent to finish, 0-25 (default 0)
include
string
optional
text: include each agent's full write-up
run_id
string
required
Run id from quick_read
Raw schema
{
"type": "object",
"properties": {
"wait": {
"type": "integer",
"minimum": 0,
"maximum": 25,
"description": "Seconds to wait for the next agent to finish, 0-25 (default 0)"
},
"include": {
"type": "string",
"enum": [
"text"
],
"description": "text: include each agent's full write-up"
},
"run_id": {
"type": "string",
"format": "uuid",
"description": "Run id from quick_read"
}
},
"required": [
"run_id"
],
"additionalProperties": false
}
list_live_sessions
The account's live analysis sessions: symbol, timeframe, since when, next run, last decision.
Switch the models of a running live analysis session when the user asks; the next analysis runs on them. Their saved setup (get_settings) stays as it is.
Parameters2
models
object
required
Only when the user asks for specific models: agent -> model id from list_models (paid plans). Leave out to run on the user's saved setup (get_settings)
session_id
string
required
Session id
Raw schema
{
"type": "object",
"properties": {
"models": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "Only when the user asks for specific models: agent -> model id from list_models (paid plans). Leave out to run on the user's saved setup (get_settings)"
},
"session_id": {
"type": "string",
"format": "uuid",
"description": "Session id"
}
},
"required": [
"session_id",
"models"
],
"additionalProperties": false
}
stop_live_session
End a live analysis session when the user stops watching the symbol, so no more runs are charged. Safe to call twice.
Every update of this key the user has not been told: finished analysis steps, decisions (with the question to ask), matched news. Relay each `say` (and `ask`) in order, then call again with ack set to the last id you relayed; unacked updates come back until you do. Use wait (up to 25 s) to hold for the next one, and keep calling while any run or session is open.
Parameters6
ack
integer
optional
Last update id you relayed to the user
after
integer
optional
Only ids above this (default 0)
wait
integer
optional
Seconds to wait for something new before answering, 0-25
limit
integer
optional
Rows, up to 100 (default 50)
kinds
string
optional
Comma-separated kinds
notify
boolean
optional
true: only what the user must hear
Raw schema
{
"type": "object",
"properties": {
"ack": {
"type": "integer",
"description": "Last update id you relayed to the user"
},
"after": {
"type": "integer",
"description": "Only ids above this (default 0)"
},
"wait": {
"type": "integer",
"minimum": 0,
"maximum": 25,
"description": "Seconds to wait for something new before answering, 0-25"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"description": "Rows, up to 100 (default 50)"
},
"kinds": {
"type": "string",
"description": "Comma-separated kinds"
},
"notify": {
"type": "boolean",
"description": "true: only what the user must hear"
}
},
"additionalProperties": false
}
run_live_analysis
Deprecated, sunset 2027-06-01: the same one-pass run as quick_read under its old name. Use quick_read. (uses points, metered on the models used like the website; deprecated (use /v1/analysis/quick))
Parameters7
asset
string
required
crypto or stock (US stocks and ETFs)
symbol
string
required
Stock ticker (NVDA) or coin (BTC); crypto also takes a pair id such as BTC-USDT-SWAP
Only when the user asks for specific models: agent -> model id from list_models (paid plans). Leave out to run on the user's saved setup (get_settings)
language
string
optional
Language of the write-ups, e.g. en, zh-CN, ja (default: the account's)
idempotency_key
string
optional
Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice
Raw schema
{
"type": "object",
"properties": {
"asset": {
"type": "string",
"enum": [
"crypto",
"stock"
],
"description": "crypto or stock (US stocks and ETFs)"
},
"symbol": {
"type": "string",
"description": "Stock ticker (NVDA) or coin (BTC); crypto also takes a pair id such as BTC-USDT-SWAP"
},
"agents": {
"type": "array",
"items": {
"type": "string",
"enum": [
"indicator",
"intelligence",
"fundamental",
"decision"
]
},
"description": "Subset of the four live agents (default all four)"
},
"timeframe": {
"type": "string",
"description": "Candle timeframe. Crypto: 1m 5m 15m 1H 4H 1D. Stock: 1H 1D 1W 1mo. Default: the user's saved timeframe (get_settings)"
},
"models": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "Only when the user asks for specific models: agent -> model id from list_models (paid plans). Leave out to run on the user's saved setup (get_settings)"
},
"language": {
"type": "string",
"description": "Language of the write-ups, e.g. en, zh-CN, ja (default: the account's)"
},
"idempotency_key": {
"type": "string",
"maxLength": 128,
"description": "Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice"
}
},
"required": [
"asset",
"symbol"
],
"additionalProperties": false
}
get_live_analysis
Deprecated, sunset 2027-06-01: status and results of a run started with run_live_analysis. Use get_quick_read. (deprecated (use /v1/analysis/quick/{id}))
Parameters3
wait
integer
optional
Seconds to wait for the run to finish, 0-25 (default 0)
include
string
optional
text: include each agent's full write-up
run_id
string
required
Run id from run_live_analysis
Raw schema
{
"type": "object",
"properties": {
"wait": {
"type": "integer",
"minimum": 0,
"maximum": 25,
"description": "Seconds to wait for the run to finish, 0-25 (default 0)"
},
"include": {
"type": "string",
"enum": [
"text"
],
"description": "text: include each agent's full write-up"
},
"run_id": {
"type": "string",
"format": "uuid",
"description": "Run id from run_live_analysis"
}
},
"required": [
"run_id"
],
"additionalProperties": false
}
get_news
The scored news stream behind Market Pulse: every article tagged with the symbols it moves, its value (low, medium, high) and its sentiment. Newest first (with since: oldest first). Use since to fetch only what is new, cursor for older pages. (0.5 points per call)
Parameters7
symbols
string
optional
Comma-separated symbols, e.g. NVDA,BTC
asset
string
optional
crypto or stock (US stocks and ETFs)
min_value
string
optional
Minimum value
sentiment
string
optional
since
string
optional
ISO 8601 time: only items newer than this (cheaper when nothing is new)
cursor
string
optional
next_cursor from the previous answer, for the next older page
limit
integer
optional
Rows, up to 50 (default 20)
Raw schema
{
"type": "object",
"properties": {
"symbols": {
"type": "string",
"description": "Comma-separated symbols, e.g. NVDA,BTC"
},
"asset": {
"type": "string",
"enum": [
"crypto",
"stock"
],
"description": "crypto or stock (US stocks and ETFs)"
},
"min_value": {
"type": "string",
"enum": [
"low",
"medium",
"high"
],
"description": "Minimum value"
},
"sentiment": {
"type": "string",
"enum": [
"bullish",
"bearish",
"neutral"
]
},
"since": {
"type": "string",
"description": "ISO 8601 time: only items newer than this (cheaper when nothing is new)"
},
"cursor": {
"type": "string",
"description": "next_cursor from the previous answer, for the next older page"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"description": "Rows, up to 50 (default 20)"
}
},
"additionalProperties": false
}
get_news_article
One article from get_news with its text, symbols, value and sentiment. (0.2 points per call)
Keep matching scored news for symbols server side, also while you are offline; each matching story arrives in get_updates with a sentence to relay (high-value ones ask whether to run a quick read). Several sources of one story arrive once. (needs the starter plan or above)
Parameters8
symbols
array
required
Symbols to watch, e.g. NVDA, BTC
asset
string
optional
crypto | stock (default both)
min_value
string
optional
Minimum value (default medium)
sentiment
string
optional
language
string
optional
Language of the write-ups, e.g. en, zh-CN, ja (default: the account's)
quiet_hours
object
optional
{start: 'HH:MM', end: 'HH:MM', tz}: only high-value items inside the window
include_pulse
boolean
optional
Also Market Pulse moves on the symbols (default false)
idempotency_key
string
optional
Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice
Raw schema
{
"type": "object",
"properties": {
"symbols": {
"type": "array",
"items": {
"type": "string"
},
"description": "Symbols to watch, e.g. NVDA, BTC"
},
"asset": {
"type": "string",
"description": "crypto | stock (default both)"
},
"min_value": {
"type": "string",
"enum": [
"low",
"medium",
"high"
],
"description": "Minimum value (default medium)"
},
"sentiment": {
"type": "string",
"enum": [
"bullish",
"bearish",
"neutral"
]
},
"language": {
"type": "string",
"description": "Language of the write-ups, e.g. en, zh-CN, ja (default: the account's)"
},
"quiet_hours": {
"type": "object",
"description": "{start: 'HH:MM', end: 'HH:MM', tz}: only high-value items inside the window"
},
"include_pulse": {
"type": "boolean",
"description": "Also Market Pulse moves on the symbols (default false)"
},
"idempotency_key": {
"type": "string",
"maxLength": 128,
"description": "Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice"
}
},
"required": [
"symbols"
],
"additionalProperties": false
}
list_news_watches
The key's news watches. (needs the starter plan or above)
POST every update (or the kinds listed) to a URL, signed with HMAC-SHA256 (X-SimianX-Signature), with retries. For the user's own code (Starter plan and above); an agent that reads get_updates does not need one.
Parameters6
url
string
required
https endpoint
events
array
optional
Kinds to send (default all)
secret
string
optional
Signing secret (shown once)
acks
boolean
optional
A 2xx answer also acks the update
this_key_only
boolean
optional
Only this key's updates (default: every key of the account)
idempotency_key
string
optional
Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice
Raw schema
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "https endpoint"
},
"events": {
"type": "array",
"items": {
"type": "string"
},
"description": "Kinds to send (default all)"
},
"secret": {
"type": "string",
"description": "Signing secret (shown once)"
},
"acks": {
"type": "boolean",
"description": "A 2xx answer also acks the update"
},
"this_key_only": {
"type": "boolean",
"description": "Only this key's updates (default: every key of the account)"
},
"idempotency_key": {
"type": "string",
"maxLength": 128,
"description": "Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice"
}
},
"required": [
"url"
],
"additionalProperties": false
}
delete_webhook
Delete a webhook when the user no longer wants updates pushed to that url. Cannot be undone; deliveries stop at once.
POST a signed test event to the webhook now, right after creating or changing one, to confirm the user's endpoint receives and verifies it.
Parameters2
webhook_id
string
required
Webhook id
idempotency_key
string
optional
Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice
Raw schema
{
"type": "object",
"properties": {
"webhook_id": {
"type": "string",
"format": "uuid",
"description": "Webhook id"
},
"idempotency_key": {
"type": "string",
"maxLength": 128,
"description": "Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice"
}
},
"required": [
"webhook_id"
],
"additionalProperties": false
}
get_pulse_events
Market Pulse events on US stocks and crypto: sudden price moves and other market events, each with a severity from 1 to 4. Newest first (with since: oldest first, pass `newest` back); delayed on lower plans. (0.3 points per call)
Parameters7
asset
string
optional
crypto or stock (US stocks and ETFs)
symbol
string
optional
One symbol, e.g. TSLA
min_severity
integer
optional
Minimum severity 1-4
types
string
optional
Comma-separated event types
cursor
string
optional
next_cursor from the previous answer, for the next older page
limit
integer
optional
Rows, up to 100 (default 50)
since
string
optional
ISO 8601 time: only items newer than this (cheaper when nothing is new)
Raw schema
{
"type": "object",
"properties": {
"asset": {
"type": "string",
"enum": [
"crypto",
"stock"
],
"description": "crypto or stock (US stocks and ETFs)"
},
"symbol": {
"type": "string",
"description": "One symbol, e.g. TSLA"
},
"min_severity": {
"type": "integer",
"minimum": 1,
"maximum": 4,
"description": "Minimum severity 1-4"
},
"types": {
"type": "string",
"description": "Comma-separated event types"
},
"cursor": {
"type": "string",
"description": "next_cursor from the previous answer, for the next older page"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"description": "Rows, up to 100 (default 50)"
},
"since": {
"type": "string",
"description": "ISO 8601 time: only items newer than this (cheaper when nothing is new)"
}
},
"additionalProperties": false
}
get_pulse_summary
A 24-hour overview of Market Pulse. (0.2 points per call)
Start the deep research committee on a stock or a coin: four analysts (fundamentals, market, news, and positioning for stocks or derivatives for crypto), a bull and a bear researcher, a research manager and a risk manager, ending in a verdict with entry, stop and target and a PDF. Takes about ten minutes; each analyst, each researcher, the start and end of every debate round, the verdict and the PDF link arrive in get_updates (or the run's events) as they land. After starting, follow it until done and tell the user every finished step; never wait for the user to ask. (uses points, metered on the models used like the website)
Parameters7
asset
string
optional
stock (default) or crypto
symbol
string
required
Stock ticker (NVDA) or coin (BTC); crypto also takes a pair id such as BTC-USDT-SWAP
horizon
string
optional
Holding horizon (default swing)
agents
array
optional
Subset of the committee seats (default all)
models
object
optional
Only when the user asks for specific models: agent -> model id from list_models (paid plans). Leave out to run on the user's saved setup (get_settings)
language
string
optional
Language of the write-ups, e.g. en, zh-CN, ja (default: the account's)
idempotency_key
string
optional
Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice
Raw schema
{
"type": "object",
"properties": {
"asset": {
"type": "string",
"enum": [
"crypto",
"stock"
],
"description": "stock (default) or crypto"
},
"symbol": {
"type": "string",
"description": "Stock ticker (NVDA) or coin (BTC); crypto also takes a pair id such as BTC-USDT-SWAP"
},
"horizon": {
"type": "string",
"enum": [
"short",
"swing",
"long"
],
"description": "Holding horizon (default swing)"
},
"agents": {
"type": "array",
"items": {
"type": "string"
},
"description": "Subset of the committee seats (default all)"
},
"models": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "Only when the user asks for specific models: agent -> model id from list_models (paid plans). Leave out to run on the user's saved setup (get_settings)"
},
"language": {
"type": "string",
"description": "Language of the write-ups, e.g. en, zh-CN, ja (default: the account's)"
},
"idempotency_key": {
"type": "string",
"maxLength": 128,
"description": "Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice"
}
},
"required": [
"symbol"
],
"additionalProperties": false
}
get_deep_analysis
State, verdict and trade plan of a deep research run. Poll until status is done.
Parameters2
include
string
optional
text: include each agent's full write-up
analysis_id
string
required
Id from start_deep_analysis
Raw schema
{
"type": "object",
"properties": {
"include": {
"type": "string",
"enum": [
"text"
],
"description": "text: include each agent's full write-up"
},
"analysis_id": {
"type": "string",
"format": "uuid",
"description": "Id from start_deep_analysis"
}
},
"required": [
"analysis_id"
],
"additionalProperties": false
}
list_deep_analyses
The account's recent deep research runs, newest first: find an earlier run's id instead of starting (and paying for) a new one.
Ask a follow-up question about a finished deep research run; read the answers with get_deep_thread. (uses points, metered on the models used like the website)
Parameters4
message
string
required
mentions
array
optional
Committee seats that should answer (optional)
analysis_id
string
required
Deep research id
idempotency_key
string
optional
Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice
Raw schema
{
"type": "object",
"properties": {
"message": {
"type": "string",
"maxLength": 2000
},
"mentions": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 3,
"description": "Committee seats that should answer (optional)"
},
"analysis_id": {
"type": "string",
"format": "uuid",
"description": "Deep research id"
},
"idempotency_key": {
"type": "string",
"maxLength": 128,
"description": "Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice"
}
},
"required": [
"analysis_id",
"message"
],
"additionalProperties": false
}
get_deep_thread
Questions asked about a deep research run and the committee's answers.
Find the symbol to use: US stocks, ETFs and crypto pairs matching a name or ticker. To look up several names, pass them together in symbols (one call) instead of calling once per name.
Parameters4
q
string
optional
Name or ticker
symbols
string
optional
Up to 20 comma-separated names or tickers, answered in one call
asset
string
optional
Default all
limit
integer
optional
Rows, up to 30 (default 10)
Raw schema
{
"type": "object",
"properties": {
"q": {
"type": "string",
"description": "Name or ticker"
},
"symbols": {
"type": "string",
"description": "Up to 20 comma-separated names or tickers, answered in one call"
},
"asset": {
"type": "string",
"enum": [
"stock",
"crypto",
"all"
],
"description": "Default all"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 30,
"description": "Rows, up to 30 (default 10)"
}
},
"additionalProperties": false
}
get_crypto_quotes
Latest prices of the coins on the Market Pulse board (the large caps and the coins users filter on), up to 120 per call; coins it does not carry come back in `missing` (get_crypto_candles has any pair). Nothing found, nothing charged. (0.1 points per call)
Run the four live agents on a symbol on a schedule, optionally letting the Decision agent manage a paper position (Starter plan and above). Runs server side, also while you are offline; every analysis, decision and position change lands in get_updates and the event log (get_autopilot_events). After starting, follow it until done and tell the user every finished step; never wait for the user to ask. (uses points, metered on the models used like the website)
Parameters11
asset
string
required
crypto or stock (US stocks and ETFs)
symbol
string
required
Stock ticker (NVDA) or coin (BTC); crypto also takes a pair id such as BTC-USDT-SWAP
Only when the user asks for specific models: agent -> model id from list_models (paid plans). Leave out to run on the user's saved setup (get_settings)
agents
array
optional
Subset of the four live agents (default all four)
intervals
object
optional
agent -> seconds between runs (30 s up to a day; fundamental at least 1800); clamped into range
ai_position_control
boolean
optional
Let the Decision agent open and manage a paper position
timing_gate
boolean
optional
Crypto: while flat, the timing-gate model (SX-1) scores each candle first and skips the indicator and decision on low-scoring ones (no model call, 0.05 points per skipped candle; the event says skipped: timing_gate)
webhook
object
optional
{url, secret?, events?}: also POST each event to this URL
language
string
optional
Language of the write-ups, e.g. en, zh-CN, ja (default: the account's)
idempotency_key
string
optional
Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice
Raw schema
{
"type": "object",
"properties": {
"asset": {
"type": "string",
"enum": [
"crypto",
"stock"
],
"description": "crypto or stock (US stocks and ETFs)"
},
"symbol": {
"type": "string",
"description": "Stock ticker (NVDA) or coin (BTC); crypto also takes a pair id such as BTC-USDT-SWAP"
},
"timeframe": {
"type": "string",
"description": "Candle timeframe. Crypto: 1m 5m 15m 1H 4H 1D. Stock: 1H 1D 1W 1mo. Default: the user's saved timeframe (get_settings)"
},
"models": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "Only when the user asks for specific models: agent -> model id from list_models (paid plans). Leave out to run on the user's saved setup (get_settings)"
},
"agents": {
"type": "array",
"items": {
"type": "string",
"enum": [
"indicator",
"intelligence",
"fundamental",
"decision"
]
},
"description": "Subset of the four live agents (default all four)"
},
"intervals": {
"type": "object",
"additionalProperties": {
"type": "integer"
},
"description": "agent -> seconds between runs (30 s up to a day; fundamental at least 1800); clamped into range"
},
"ai_position_control": {
"type": "boolean",
"description": "Let the Decision agent open and manage a paper position"
},
"timing_gate": {
"type": "boolean",
"description": "Crypto: while flat, the timing-gate model (SX-1) scores each candle first and skips the indicator and decision on low-scoring ones (no model call, 0.05 points per skipped candle; the event says skipped: timing_gate)"
},
"webhook": {
"type": "object",
"description": "{url, secret?, events?}: also POST each event to this URL"
},
"language": {
"type": "string",
"description": "Language of the write-ups, e.g. en, zh-CN, ja (default: the account's)"
},
"idempotency_key": {
"type": "string",
"maxLength": 128,
"description": "Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice"
}
},
"required": [
"asset",
"symbol"
],
"additionalProperties": false
}
get_autopilot
Status and configuration of one autopilot, with its event cursor.
Change models, intervals, language, the timing gate or AI position control. Changing the timeframe or switching AI control off closes the paper position first.
Only when the user asks for specific models: agent -> model id from list_models (paid plans). Leave out to run on the user's saved setup (get_settings)
intervals
object
optional
agent -> seconds between runs (30 s up to a day; fundamental at least 1800); clamped into range
timing_gate
boolean
optional
Crypto: while flat, the timing-gate model (SX-1) scores each candle first and skips the indicator and decision on low-scoring ones (no model call, 0.05 points per skipped candle; the event says skipped: timing_gate)
ai_position_control
boolean
optional
language
string
optional
Language of the write-ups, e.g. en, zh-CN, ja (default: the account's)
Raw schema
{
"type": "object",
"properties": {
"autopilot_id": {
"type": "string",
"format": "uuid",
"description": "Autopilot id"
},
"timeframe": {
"type": "string",
"description": "Candle timeframe. Crypto: 1m 5m 15m 1H 4H 1D. Stock: 1H 1D 1W 1mo. Default: the user's saved timeframe (get_settings)"
},
"models": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "Only when the user asks for specific models: agent -> model id from list_models (paid plans). Leave out to run on the user's saved setup (get_settings)"
},
"intervals": {
"type": "object",
"additionalProperties": {
"type": "integer"
},
"description": "agent -> seconds between runs (30 s up to a day; fundamental at least 1800); clamped into range"
},
"timing_gate": {
"type": "boolean",
"description": "Crypto: while flat, the timing-gate model (SX-1) scores each candle first and skips the indicator and decision on low-scoring ones (no model call, 0.05 points per skipped candle; the event says skipped: timing_gate)"
},
"ai_position_control": {
"type": "boolean"
},
"language": {
"type": "string",
"description": "Language of the write-ups, e.g. en, zh-CN, ja (default: the account's)"
}
},
"required": [
"autopilot_id"
],
"additionalProperties": false
}
start_autopilot
Restart a stopped autopilot. (uses points, metered on the models used like the website)
Parameters2
autopilot_id
string
required
Autopilot id
idempotency_key
string
optional
Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice
Raw schema
{
"type": "object",
"properties": {
"autopilot_id": {
"type": "string",
"format": "uuid",
"description": "Autopilot id"
},
"idempotency_key": {
"type": "string",
"maxLength": 128,
"description": "Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice"
}
},
"required": [
"autopilot_id"
],
"additionalProperties": false
}
stop_autopilot
Stop an autopilot when the user wants it to stop analysing (and spending points); start_autopilot restarts it. Safe to call twice. The paper book stays: an open position keeps its stop and target and a resting order can still fill; use autopilot_action close / cancel_order first if the user wants to be flat.
The autopilot's event log: analyses, signals, position changes, actions. Without after you get the latest events and a cursor; pass that cursor as after (and wait, up to 25 s) to get only what happens next.
Parameters5
after
string
optional
Cursor from the previous answer
wait
integer
optional
Seconds to wait for something new before answering, 0-25
Change the autopilot's paper position by hand, always at the server's price: open, add, reduce, close, set_levels, place_order, replace_order, cancel_order, set_timeframe. Stocks are long only, and intraday stock entries need the market open.
Parameters13
action
string
required
side
string
optional
quantity
number
optional
Coins or shares
notional_usd
number
optional
Size in USD instead of quantity
fraction
number
optional
reduce: share of the position
stop_loss
number
optional
take_profit
number
optional
order_type
string
optional
price
number
optional
place_order / replace_order: resting price
expires_in
integer
optional
Order lifetime in seconds
timeframe
string
optional
set_timeframe: the new timeframe (closes the position first)
autopilot_id
string
required
Autopilot id
idempotency_key
string
optional
Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice
Raw schema
{
"type": "object",
"properties": {
"action": {
"type": "string",
"enum": [
"open",
"add",
"reduce",
"close",
"set_levels",
"place_order",
"replace_order",
"cancel_order",
"set_timeframe"
]
},
"side": {
"type": "string",
"enum": [
"long",
"short"
]
},
"quantity": {
"type": "number",
"description": "Coins or shares"
},
"notional_usd": {
"type": "number",
"description": "Size in USD instead of quantity"
},
"fraction": {
"type": "number",
"minimum": 0,
"maximum": 1,
"description": "reduce: share of the position"
},
"stop_loss": {
"type": "number"
},
"take_profit": {
"type": "number"
},
"order_type": {
"type": "string",
"enum": [
"limit",
"stop"
]
},
"price": {
"type": "number",
"description": "place_order / replace_order: resting price"
},
"expires_in": {
"type": "integer",
"minimum": 60,
"maximum": 604800,
"description": "Order lifetime in seconds"
},
"timeframe": {
"type": "string",
"description": "set_timeframe: the new timeframe (closes the position first)"
},
"autopilot_id": {
"type": "string",
"format": "uuid",
"description": "Autopilot id"
},
"idempotency_key": {
"type": "string",
"maxLength": 128,
"description": "Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice"
}
},
"required": [
"autopilot_id",
"action"
],
"additionalProperties": false
}
run_autopilot_agent
Run one of the autopilot's agents now, outside its schedule; the result lands in the event log. (uses points, metered on the models used like the website)
Parameters3
agent
string
required
autopilot_id
string
required
Autopilot id
idempotency_key
string
optional
Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice
Raw schema
{
"type": "object",
"properties": {
"agent": {
"type": "string",
"enum": [
"indicator",
"intelligence",
"fundamental",
"decision"
]
},
"autopilot_id": {
"type": "string",
"format": "uuid",
"description": "Autopilot id"
},
"idempotency_key": {
"type": "string",
"maxLength": 128,
"description": "Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice"
}
},
"required": [
"autopilot_id",
"agent"
],
"additionalProperties": false
}
get_account
The account behind the API key: plan, limits and the key's budgets (points figures are for your own pacing; do not read them to the user unless asked).
The user's default setup per market (stock, crypto): each live agent's model, the timeframe and run intervals, and the deep committee's model per seat. Every analysis started without `models` runs on it. Read it when the user asks which models or timeframe their analyses use.
Save the user's default models for one market, when they ask to change them: live = the four live agents, deep = the committee seats (one setting for both markets). Paid plans only. The website shows the same setup.
Parameters3
asset
string
required
crypto or stock (US stocks and ETFs)
live
object
optional
deep
object
optional
Raw schema
{
"type": "object",
"properties": {
"asset": {
"type": "string",
"enum": [
"crypto",
"stock"
],
"description": "crypto or stock (US stocks and ETFs)"
},
"live": {
"type": "object",
"properties": {
"models": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "indicator | intelligence | fundamental | decision -> model id from list_models"
}
}
},
"deep": {
"type": "object",
"properties": {
"models": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "committee seat -> model id from list_models"
}
}
}
},
"required": [
"asset"
],
"additionalProperties": false
}
get_daily_reward
The user's free daily reward (no purchase): whether today's is still unclaimed, extra claims, the streak, when it resets (00:00 UTC) and what it can give, with odds.
Claim the user's free daily reward when they ask for it ("try my luck"): today's, else an extra claim. No purchase or money involved. Tell them what they got (`prize.name`, `benefits`) and their streak.
Parameters2
request_id
string
optional
Optional: a retry with the same one the same day returns the same reward; a second claim the same day (an extra draw) needs a new one
idempotency_key
string
optional
Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice
Raw schema
{
"type": "object",
"properties": {
"request_id": {
"type": "string",
"description": "Optional: a retry with the same one the same day returns the same reward; a second claim the same day (an extra draw) needs a new one"
},
"idempotency_key": {
"type": "string",
"maxLength": 128,
"description": "Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice"
}
},
"additionalProperties": false
}
list_rewards
Rewards the user has received, newest first (daily rewards, streaks and others).
Parameters2
limit
integer
optional
Rows, up to 50 (default 20)
cursor
string
optional
next_cursor from the previous answer, for the next older page
Raw schema
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"description": "Rows, up to 50 (default 20)"
},
"cursor": {
"type": "string",
"description": "next_cursor from the previous answer, for the next older page"
}
},
"additionalProperties": false
}
help_search
Search SimianX's help center when the user asks how something works on the website (live analysis, deep analysis, autopilots, auto digest, points, plans, account). Returns titles, summaries and the page URL; read the full article with help_read. Without `q` it lists the articles.
Parameters4
q
string
optional
What the user asked about, in their words
locale
string
optional
Article language, e.g. en, zh-CN, de (default: the user's)
category
string
optional
limit
integer
optional
Rows, up to 10 (default 5)
Raw schema
{
"type": "object",
"properties": {
"q": {
"type": "string",
"description": "What the user asked about, in their words"
},
"locale": {
"type": "string",
"description": "Article language, e.g. en, zh-CN, de (default: the user's)"
},
"category": {
"type": "string",
"enum": [
"getting-started",
"live-analysis",
"deep-analysis",
"autopilots",
"auto-digest",
"market-tools",
"points-and-plans",
"account",
"faq"
]
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 10,
"description": "Rows, up to 10 (default 5)"
}
},
"additionalProperties": false
}
help_read
One help center article as Markdown (category and slug from help_search). Answer from it and give the user its `url`.
Models that can be set per agent: rates, typical points of a live call, where each applies, and `min_plan` (free accounts run gpt-6-luna; starter and above pick any listed model).
Tell the SimianX team about a bug, missing data or an idea. Read by people; not answered.
Parameters7
message
string
required
category
string
optional
severity
string
optional
endpoint
string
optional
Endpoint key it concerns
request_id
string
optional
X-Request-Id of the call it concerns, if any
context
object
optional
<= 4 KB of detail
idempotency_key
string
optional
Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice
Raw schema
{
"type": "object",
"properties": {
"message": {
"type": "string",
"maxLength": 4000
},
"category": {
"type": "string",
"enum": [
"bug",
"feature",
"pricing",
"docs",
"data",
"other"
]
},
"severity": {
"type": "string",
"enum": [
"low",
"normal",
"high"
]
},
"endpoint": {
"type": "string",
"description": "Endpoint key it concerns"
},
"request_id": {
"type": "string",
"description": "X-Request-Id of the call it concerns, if any"
},
"context": {
"type": "object",
"description": "<= 4 KB of detail"
},
"idempotency_key": {
"type": "string",
"maxLength": 128,
"description": "Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice"
}
},
"required": [
"message"
],
"additionalProperties": false
}
pricing_get
Prices in points, plans and limits (machine readable)
Estimate how many points a SimianX call would cost before running it (pass the endpoint key, e.g. deep.create, and its options). Not a market price quote.
Parameters4
endpoint
string
required
Required: the endpoint key to price, e.g. analysis.quick, analysis.live, deep.create. This prices a SimianX call; it is not a market price quote
asset
string
optional
stock | crypto
agents
array
optional
Subset of agents
models
object
optional
agent -> model_id; omit to run on the account's saved setup (GET /v1/settings)
Raw schema
{
"type": "object",
"properties": {
"endpoint": {
"type": "string",
"description": "Required: the endpoint key to price, e.g. analysis.quick, analysis.live, deep.create. This prices a SimianX call; it is not a market price quote"
},
"asset": {
"type": "string",
"description": "stock | crypto"
},
"agents": {
"type": "array",
"items": {
"type": "string"
},
"description": "Subset of agents"
},
"models": {
"type": "object",
"description": "agent -> model_id; omit to run on the account's saved setup (GET /v1/settings)"
}
},
"required": [
"endpoint"
],
"additionalProperties": false
}
market_status
Whether the US stock market is open now, and when the current or next session opens and closes. Check before stock analyses or autopilots that depend on market hours.
Follow a stock, asset or calendar item (the first follow in a sector creates an email subscription) (needs the starter plan or above)
Parameters8
sector
string
required
Sector slug
type
string
optional
stock | asset | calendar
ticker
string
optional
type=stock
slug
string
optional
type=asset
id
string
optional
type=calendar: calendar item id
reminder_offsets
array
optional
Days before, 0-30, up to 5 (optional)
timezone
string
optional
IANA zone for a subscription created by this call (optional)
idempotency_key
string
optional
Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice
Raw schema
{
"type": "object",
"properties": {
"sector": {
"type": "string",
"description": "Sector slug"
},
"type": {
"type": "string",
"description": "stock | asset | calendar"
},
"ticker": {
"type": "string",
"description": "type=stock"
},
"slug": {
"type": "string",
"description": "type=asset"
},
"id": {
"type": "string",
"description": "type=calendar: calendar item id"
},
"reminder_offsets": {
"type": "array",
"items": {
"type": "string"
},
"description": "Days before, 0-30, up to 5 (optional)"
},
"timezone": {
"type": "string",
"description": "IANA zone for a subscription created by this call (optional)"
},
"idempotency_key": {
"type": "string",
"maxLength": 128,
"description": "Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice"
}
},
"required": [
"sector"
],
"additionalProperties": false
}
sectors_unfollow
Remove a follow by id or by target key (stock:SMMT, asset:<slug>, calendar:<id>) (needs the starter plan or above)
Translate up to 20 news titles into one language, e.g. before showing headlines to a user who reads another language. (1 point per call)
Parameters3
titles
array
optional
<= 20
language
string
optional
Target language code
idempotency_key
string
optional
Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice
Raw schema
{
"type": "object",
"properties": {
"titles": {
"type": "array",
"items": {
"type": "string"
},
"description": "<= 20"
},
"language": {
"type": "string",
"description": "Target language code"
},
"idempotency_key": {
"type": "string",
"maxLength": 128,
"description": "Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice"
}
},
"additionalProperties": false
}
analysis_quick_list
The account's recent quick reads (analyze runs), newest first, to find an earlier result or its id without starting a new run.
Follow a deep research run step by step: long-poll with after=<cursor>&wait=30 and relay each event's `say` to the user. Use instead of polling get_deep_analysis while the run is going.
Stop a running or queued deep research run when the user asks to cancel it or no longer needs it. It halts within a few seconds (status becomes stopped); points already used are not refunded and deep_resume can continue it later.
Continue a deep research run that is paused (points ran out), stopped or failed, from the step it reached. Check the balance first: the remaining steps are charged. (uses points, metered on the models used like the website)
Parameters2
id
string
required
id
idempotency_key
string
optional
Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice
Raw schema
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "id"
},
"idempotency_key": {
"type": "string",
"maxLength": 128,
"description": "Optional: any unique string for this action; send the same one when retrying the same call and the first result comes back instead of the action running twice"
}
},
"required": [
"id"
],
"additionalProperties": false
}
deep_pdf
Get a download link for the PDF report of a finished deep research run (status done), to hand the user a shareable document. Free plans get a watermarked copy.
Archive an autopilot that is already stopped, to remove it from the list. Stop it first with stop_autopilot; its history is kept and start_autopilot brings it back. Its paper book is left as it is (close it first to be flat).
Past analyses of one autopilot, newest first, filterable by agent: use to explain why the autopilot did what it did. Pass include=text for the full write-ups.
Lifecycle and delivery log of one autopilot (started, stopped, paused, webhook deliveries): use when an autopilot stopped unexpectedly or updates did not arrive.
Give any AI agent a full research desk. With SimianX AI your agent can convene an 8-agent research committee on any US stock or crypto pair and question it afterwards, get a live four-agent read with entry, stop and target, and keep a scored news stream open on your symbols. One skill and a remote MCP server for Claude Code, Codex, Cursor, Muse, Grok Bot, dots and every other agent.
Ask an agent on its own "Should I buy NVDA for a swing trade?" and it searches the web, summarises headlines that may be days old and gives one model's opinion. It has no live chart, nobody arguing the other side, and it stops when the chat ends.
With SimianX the same agent:
On its own
With SimianX AI
Who works on it
One model
An 8-agent committee: four analysts, a bull and a bear researcher, a research manager, a risk manager
What it reads
Web search results
Live candles, filings, insider trades, the news flow; on-chain and derivatives data for a coin
What you get
An opinion
A verdict with entry, stop and target, and a PDF report
Afterwards
Starts over
Puts follow-up questions to the same committee, or sets an autopilot to keep watching
What you can ask
Once the skill is in, ask in your own words:
"Convene the SimianX committee on NVDA for a swing trade." Four analysts report, the bull and the bear argue it out, and the risk manager hands back the verdict, the plan and a PDF.
"Ask the bear researcher what would prove the bull case wrong." Follow-ups go to the same run, so the answer builds on everything the committee already read.
"Run the committee on SOL with a short horizon." For a coin the analysts also read on-chain flows and the derivatives market.
"How does BTC look on the 15-minute chart right now?" Four live agents answer, and the Decision agent says buy, sell or stay out with entry, stop and target.
"Tell me when high-value news hits TSLA or ETH." A scored news stream on your symbols, live as each story is scored.
"Watch AAPL on the 1-hour chart and manage a paper position." An autopilot reruns the agents on every candle close and logs every signal.
"Which biopharma PDUFA dates fall in the next 30 days?" Sector Watch, from primary sources.
"What moved sharply in crypto in the last hour?" Market Pulse: sudden moves, new highs and lows, volume spikes and gaps.
Free accounts can try the committee on popular symbols such as NVDA, AAPL, TSLA, BTC and ETH.
What SimianX covers
Two things do most of the work.
Live multi-agent analysis. Name a stock or a crypto pair and a timeframe, and four agents read it at the same time. Indicator reads the chart. Intelligence reads the news flow. Fundamental reads filings and insider trades, or on-chain and derivatives data for a coin. Decision weighs the three and proposes a trade with entry, stop and target. → Live analysis
A scored news stream. Every article comes in tagged with the symbols it moves, a value score and a bullish, bearish or neutral read. It is the feed behind Market Pulse, where it runs next to sudden price moves, new highs and lows and gaps. Your agent can page through it or keep a stream open on its symbols. → Market Pulse
Also there when you need it:
Deep research. Eight agents debate a stock or a coin and come back with a verdict, a trade plan and a PDF. Your agent can ask follow-up questions. → Deep analysis
Sector Watch. Catalyst calendars and events taken from primary sources, starting with biopharma. → Sector Watch
Autopilots. The same four live agents on a schedule for one symbol, with a paper position and an event log your agent can follow. → Autopilots
Your choice of model. Pick the model behind each agent, and see how each one has traded before you do. → Model leaderboard
Markets: 13,000+ US stocks and ETFs on 1m to 1mo candles, and 4,000+ crypto pairs, spot and perpetual, on 1m to 1D. → Stock analysis · Crypto analysis
Install in one sentence
Paste this to your agent:
text
Install the SimianX skill from https://www.simianx.ai/INSTALL.md and sign me in.
It puts the skill where your agent looks for skills, then signs you in: you approve a link in your browser, or type the 6-digit code we email you. A new address gets an account on the spot. The agent ends up with an API key of its own in SIMIANX_API_KEY and never with your website login.
The command and the directory for each agent (Claude Code, Codex, Cursor, Copilot, Gemini CLI, Windsurf, Amp, Cline and the rest) are in INSTALL.md.
Muse, Grok Bot, dots and other agents on their own computer
Agents that run on their own cloud computer read the same sentence. They connect over MCP or build a connector from the OpenAPI document, sign you in, keep the key in their own credential store and save SimianX as a skill. The exact words for Muse, Grok Bot and dots are in INSTALL.md.
Or connect over MCP
AI agents that speak MCP can use SimianX as tools without installing the skill. Add the remote server once with your key:
The same for Claude Desktop, Cursor, Codex, VS Code, Windsurf, Gemini CLI, Grok Bot and Muse is in INSTALL.md. Registry name: io.github.SimianX-AI/simianx.
First calls
What
Call
Reference
Live analysis session (every candle close)
POST /v1/live/sessions → the WebSocket, or GET /v1/updates?wait=30
Base URL https://service.simianx.ai/v1, header Authorization: Bearer $SIMIANX_API_KEY. The same calls as shell scripts are in examples/curl.
Plans
Free, Starter, Plus and Pro, see pricing. Agent calls use your plan's points at the same rates as the website. The news stream is live on Plus and Pro; below Plus, news runs 30 minutes behind. Answers come in 16 languages.
You can use SimianX's API to connect its analysis and signals to your own trading system and place real orders through a broker or exchange you authorize. Positions recorded inside SimianX are simulated; your integration submits and manages real orders in your own account.
Security
The key stays in SIMIANX_API_KEY. The skill never writes it into a repository, a log or a prompt.
An agent never gets a website session. Signing in from an agent only creates an API key for that agent, and we email you when it happens.
Keys have scopes, daily and monthly budgets and an optional IP allowlist. Give each agent the smallest key that does its job.
Revoke a key at My Account → API keys and it stops working within a second.
Versions
The skill sends its version in the X-SimianX-Skill header. When a version is retired, the API answers 426 with the URL to re-read, and GET /v1/skill shows the current and minimum versions. Update with your agent's own command or paste the sentence above again. What changed is in the changelog.
Repository layout
code
skills/simianx/SKILL.md the skill (Agent Skills format)
skills/simianx/references/ following · live · quick · deep · news · autopilots · data · sectors · developers · billing
INSTALL.md agent-readable install guide (also at simianx.ai/INSTALL.md)
scripts/install.{sh,py,ps1} installer for every agent; check_version.py · check_readmes.py
examples/curl · examples/runner the first calls in curl; an always-on runner for autopilots
.claude-plugin · .agents/plugins · .cursor-plugin · plugin.json · gemini-extension.json
manifests so marketplaces and plugin commands find the skill
server.json MCP Registry entry for the remote MCP server (service.simianx.ai/v1/mcp)
README.<locale>.md this page in the 16 languages SimianX speaks
MIT for everything in this repository. Use of the SimianX API is governed by the Terms of Service. SimianX analyses are information, not investment advice.