options_chain
Options contracts for a symbol — BYOK Alpaca only (requires an options-enabled key). Returns {ok, symbol, count, contracts:[{symbol,type,strike,expiration,open_interest}]}.
This record as markdown: /tools/com-wingmanprotocol-agent-gateway/options-chain.md
What options_chain does on Gateway
AI agents call options_chain to retrieve information from Gateway without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
type | string | — | call|put (optional) |
limit | integer | — | max contracts (default 100) |
handle | string | — | |
secret | string | — | |
symbol | string | Yes | underlying ticker |
key_ref | string | — | |
expiration | string | — | YYYY-MM-DD filter (optional) |
alpaca_key_id | string | — | |
alpaca_secret | string | — |
Parameters from the server's own tool schema.
Why options_chain is rated Low
This tool retrieves and queries financial market data (options chain information) without modifying state, executing trades, or moving money. It is a pure data retrieval operation analogous to a market data API call. The presence of financial domain (options contracts, Alpaca broker) does not elevate it to Financial category—that category applies to tools that execute transactions or commit obligations.
From the tool's definition Tool returns options contract data: 'Returns {ok, symbol, count, contracts:[...]}'. The description uses only query/read verbs ('Options contracts for a symbol') with no mutation, deletion, or execution language.
Risk signalsHandles credentials or secrets (secret)
Attacks that exploit this kind of access
The rule that runs options_chain safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Gateway, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For options_chain, this is the rule to start with:
options_chain is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Gateway, apply this rule, and every options_chain call is checked against it from then on.
Questions about options_chain
Options contracts for a symbol — BYOK Alpaca only (requires an options-enabled key). Returns {ok, symbol, count, contracts:[{symbol,type,strike,expiration,open_interest}]}. It is categorised as a Read tool in the Gateway MCP Server, which means it retrieves data without modifying state.
options_chain accepts 9 parameters: type, limit, handle, secret, symbol, key_ref, expiration, alpaca_key_id, alpaca_secret. Required: symbol. The full parameter table on this page comes from the server's own tool schema.
Register the Gateway MCP server in PolicyLayer and add a rule for options_chain: 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 Gateway. Nothing to install.
options_chain is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the options_chain 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 options_chain. 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.
options_chain is provided by the Gateway MCP server (https://wingmanprotocol.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Gateway, and thousands of servers like it.
This server
Across the catalogue