Skip to main content
Glama
alpacahq

alpaca-mcp-server

Official
by alpacahq
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

get_option_bars

Retrieve historical OHLCV bar data for one or more option contracts by symbol and timeframe, with sorting, limits, and pagination.

Instructions

Retrieves historical bar (OHLCV) data for one or more option contracts.

Input Schema

NameRequiredDescriptionDefault
endNoThe inclusive end of the interval. Format: RFC-3339 or YYYY-MM-DD. Default: the current time if the user has a real-time access for the feed, otherwise 15 minutes before the current time.
sortNoSort data in ascending or descending order.
limitNoThe maximum number of data points to return in the response page. The API may return less, even if there are more available data points in the requested interval. Always check the `next_page_token` for more pages. The limit applies to the total number of data points, not per symbol!
startNoThe inclusive start of the interval. Format: RFC-3339 or YYYY-MM-DD. Default: the beginning of the current day, but at least 15 minutes ago if the user doesn't have real-time access for the feed.
symbolsYesA comma-separated list of contract symbols with a limit of 100.
timeframeYesThe timeframe represented by each bar in aggregation. You can use any of the following values: - `[1-59]Min` or `[1-59]T`, e.g. `5Min` or `5T` creates 5-minute aggregations - `[1-23]Hour` or `[1-23]H`, e.g. `12Hour` or `12H` creates 12-hour aggregations - `1Day` or `1D` creates 1-day aggregations - `1Week` or `1W` creates 1-week aggregations - `[1,2,3,4,6,12]Month` or `[1,2,3,4,6,12]M`, e.g. `3Month` or `3M` creates 3-month aggregations
page_tokenNoThe pagination token from which to continue. The value to pass here is returned in specific requests when more data is available, usually because of a response result limit.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv2.4.0
    • changedInput schema / properties / sort / allOf
      Previous value: -[
-  {
-    "default": "asc",
-    "description": "Sort data in ascending or descending order.",
-    "enum": [
-      "asc",
-      "desc"
-    ],
-    "type": "string"
-  }
-]New value: +[
+  {
+    "type": "string"
+  },
+  {
+    "default": "asc",
+    "description": "Sort data in ascending or descending order.",
+    "enum": [
+      "asc",
+      "desc"
+    ],
+    "type": "string"
+  }
+]
    • removedInput schema / properties / sort / type
      Removed value: -"string"
  2. Changed4 schema fields changedv2.3.2
    • addedInput schema / properties / sort / allOf
      Added value: +[
+  {
+    "default": "asc",
+    "description": "Sort data in ascending or descending order.",
+    "enum": [
+      "asc",
+      "desc"
+    ],
+    "type": "string"
+  }
+]
    • removedInput schema / properties / sort / default
      Removed value: -"asc"
    • removedInput schema / properties / sort / enum
      Removed value: -[
-  "asc",
-  "desc"
-]
    • removedInput schema / properties / sort / x-go-name
      Removed value: -"TypeSort"
  3. Addedv2.0.0

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are provided, so the description carries full behavioral burden. It implies read-only retrieval of historical (non-real-time) data, but omits auth requirements, rate limits, pagination behavior, and the real-time-access caveats already implicit in the schema defaults.

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?

The description is a single front-loaded sentence with no redundant words. It is concise and well-structured, though arguably too terse for a tool with seven parameters and pagination semantics.

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

Completeness3/5

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

An output schema exists and the input schema is fully described, so return values and parameter mechanics need not be repeated. However, with no annotations and no usage guidance, the description leaves important selection and safety context uncovered for an agent choosing among many market-data siblings.

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 description coverage is 100%, so the schema already documents all seven parameters, including formats, defaults, enums, and pagination. The description adds only a vague mapping ('one or more option contracts' to symbols, 'historical bar' to timeframe) with no extra 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?

The description states a specific verb ('Retrieves'), resource ('historical bar (OHLCV) data'), and asset scope ('option contracts'). This distinguishes it from get_stock_bars and get_crypto_bars by asset type, and from get_option_trades by data type, though no sibling is named explicitly.

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

Usage Guidelines2/5

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

The description provides no when-to-use guidance, no alternatives, and no prerequisites. It only implies that the tool is for historical option bar data, leaving the agent to infer when it is preferable to get_option_trades or get_option_latest_quote.

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

Deploy Server

Other Tools