SimianX AI

Start an autopilot

create_autopilot

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)

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "asset": "<asset>",
      "symbol": "<symbol>"
    },
    "name": "create_autopilot"
  }
}

Input Schema

Name	Required	Description
`asset`	Yes	crypto or stock (US stocks and ETFs)
`agents`	No	Subset of the four live agents (default all four)
`models`	No	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)
`symbol`	Yes	Stock ticker (NVDA) or coin (BTC); crypto also takes a pair id such as BTC-USDT-SWAP
`webhook`	No	{url, secret?, events?}: also POST each event to this URL
`language`	No	Language of the write-ups, e.g. en, zh-CN, ja (default: the account's)
`intervals`	No	agent -> seconds between runs (30 s up to a day; fundamental at least 1800); clamped into range
`timeframe`	No	Candle timeframe. Crypto: 1m 5m 15m 1H 4H 1D. Stock: 1H 1D 1W 1mo. Default: the user's saved timeframe (get_settings)
`timing_gate`	No	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)
`idempotency_key`	No	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
`ai_position_control`	No	Let the Decision agent open and manage a paper position

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedNov 13, 2026

addedInput schema / properties / idempotency_key

Added value: +{
+  "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",
+  "maxLength": 128,
+  "type": "string"
+}

changedInput schema / properties / models / description

Previous value: -"Per-agent model override, agent -> model id from list_models (paid plans)"New value: +"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)"

removedInput schema / properties / tier

Removed value: -{
-  "description": "Model tier (default fast)",
-  "enum": [
-    "fast",
-    "standard",
-    "frontier"
-  ],
-  "type": "string"
-}

changedInput schema / properties / timeframe / description

Previous value: -"Candle timeframe. Crypto: 1m 5m 15m 1H 4H 1D. Stock: 1m 15m 1H 1D 1W 1mo. Default 15m"New value: +"Candle timeframe. Crypto: 1m 5m 15m 1H 4H 1D. Stock: 1H 1D 1W 1mo. Default: the user's saved timeframe (get_settings)"

Changed2 schema fields changedOct 31, 2026

changedInput schema / properties / intervals / description

Previous value: -"agent -> seconds between runs"New value: +"agent -> seconds between runs (30 s up to a day; fundamental at least 1800); clamped into range"

addedInput schema / properties / timing_gate / description

Added value: +"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)"

First observedOct 16, 2026

TDQS

A4.1/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations: it discloses that execution is server side and continues while the user is offline, that all analyses/decisions/position changes surface in get_updates and get_autopilot_events, and that the call consumes metered points. That is exactly the operational context annotations like destructiveHint=false cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose, then billing/plan constraints, then the follow-up instruction; each sentence carries distinct information. The trailing parenthetical about points duplicates the metering theme slightly but does not bloat the definition meaningfully.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 11-parameter, nested-object, mutation-style tool with no output schema, the description does the important compensations: it names where results land (get_updates, get_autopilot_events) and how to track progress. It stops short of saying what the immediate call returns (e.g., an autopilot identifier) needed to chain follow-up calls.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema itself carries rich per-parameter text (timing_gate costs, interval clamping, idempotency behavior), so the baseline is 3. The description adds only a light gloss on ai_position_control and models that the schema already documents, adding no new parameter syntax or constraints.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Run the four live agents on a symbol on a schedule', plus the optional Decision-agent position management. It clearly distinguishes itself from the read-side siblings get_updates and get_autopilot_events, but it does not address the near-identical sibling start_autopilot, leaving an agent unsure which starter to pick.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete usage conditions: Decision position management requires 'Starter plan and above', models should be passed 'only when the user asks', and it closes with a clear post-call operating instruction ('follow it until done... never wait for the user to ask'). It lacks an explicit when-to-use-this-vs-start_autopilot exclusion, but the context it does give is actionable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All SimianX AI tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.