Manage IB native TRAIL orders for stocks and naked LEAPS positions. Default mode is dry-run — no orders are placed unless execute=True. PMCC positions are excluded; use ib_stop_loss for those. Requires TWS or IB Gateway running locally. Args: port: IB port (7496 for live, 7497 for paper) account:...
AI agents invoke ib_trailing_stop to trigger actions in Trading Skills. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes trades/orders on Interactive Brokers accounts, modifying portfolio state through real-money trading infrastructure. While it defaults to dry-run mode, the execute=True parameter allows irreversible order placement.
From the tool's definition Manage IB native TRAIL orders for stocks and naked LEAPS positions. Requires TWS or IB Gateway running locally. Arguments include execute=True parameter and account/symbol filtering that trigger external broker operations.
Documented attack patterns abuse exactly the kind of access ib_trailing_stop gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Trading Skills, and nothing reaches the server without passing your rules. This is the rule we recommend for ib_trailing_stop:
{
"version": "1",
"default": "deny",
"tools": {
"ib_trailing_stop": {
"limits": [
{
"counter": "ib_trailing_stop_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}ib_trailing_stop stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Manage IB native TRAIL orders for stocks and naked LEAPS positions. Default mode is dry-run — no orders are placed unless execute=True. PMCC positions are excluded; use ib_stop_loss for those. Requires TWS or IB Gateway running locally. Args: port: IB port (7496 for live, 7497 for paper) account: Specific account ID (optional) symbols: Comma-separated symbols to filter (optional, e.g. 'JOBY,TSLA') trail_pct: Trail amount as % of reference price (default 20, mutually exclusive with trail_amt) trail_amt: Trail amount in dollars (mutually exclusive with trail_pct) price_mode: Option pricing — 'mid' (bid+ask)/2 or 'last' (LEAPS only) execute: Cancel orphan TS_ orders and place new TRAIL orders (default False = dry-run) forced: Cancel and replace existing TS_ orders with current parameters (requires execute=True). It is categorised as a Execute tool in the Trading Skills MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Trading Skills MCP server in PolicyLayer and add a rule for ib_trailing_stop: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Trading Skills. Nothing to install.
ib_trailing_stop is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the ib_trailing_stop rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for ib_trailing_stop. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
ib_trailing_stop is provided by the Trading Skills MCP server (staskh/trading_skills). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 35 Trading Skills tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
35 Trading Skills tools catalogued and risk-classified — across an index of 42,500+ MCP servers.