mcp-server-polymarket

Overview Schema Source Related Servers Discussions Admin

Get price history

get_price_history

Read-onlyIdempotent

Retrieve outcome token price (probability) history over a selected window, returning first, last, high, and low values to analyze prediction-market movements.

Instructions

An outcome token's price (probability) over time, with the window's first, last, high and low. For multi-day windows prefer bucket_seconds of 300, 1800, 10800 or 43200.

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": {
      "token_id": "<token_id>"
    },
    "name": "get_price_history"
  }
}

Input Schema

Name	Required	Description	Default
`end`	No	ISO 8601 time, e.g. 2026-11-01 or 2026-11-01T12:00:00Z, or epoch seconds.
`as_of`	No	Price at one moment instead of a series.
`limit`	No	Most points to return.
`start`	No	ISO 8601 time, e.g. 2026-11-01 or 2026-11-01T12:00:00Z, or epoch seconds.
`cursor`	No	next_cursor from the previous page. Empty starts at the top.
`interval`	No	Window ending now. Leave empty when giving start.	1w
`token_id`	Yes	Outcome token id (the CLOB asset id), a long decimal string.
`bucket_seconds`	No	Point spacing. Empty lets the server pick.

Output Schema

Name	Required	Description	Default
`low`	No
`high`	No
`last`	No
`first`	No
`change`	No
`points`	Yes
`token_id`	Yes
`next_cursor`	No
`resolution_seconds`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 11, 2026

TDQS

A3.6/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is fully covered. The description adds that the series carries window-level first/last/high/low, which is real behavioral context, but says nothing about pagination behavior, rate limits, or how sparse/empty windows behave.

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?

Two tight sentences with no filler, and the return shape is front-loaded before the parameter advice. The opening is a verbless fragment ('An outcome token's price...'), which costs a point on clarity but wastes no words.

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?

With an output schema present and 100% schema description coverage, the description need not explain return fields or parameter formats, and it correctly focuses on the one thing the schema cannot infer: sensible bucket sizing. The gap is the tool's multi-modal time handling (interval vs start vs as_of) and pagination via cursor/limit, which the description never ties together.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, and the description earns above that by prescribing concrete bucket_seconds values (300/1800/10800/43200) for multi-day windows — guidance the schema's generic 'Empty lets the server pick' does not provide. It leaves interval/start/as_of interactions to the schema, which is acceptable given full coverage.

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 resource — an outcome token's price/probability series — plus the aggregate shape returned (first, last, high, low). That is enough to separate it from get_perps_candles or get_market, but it never names a sibling or explicitly contrasts scope, so it stops short of 5.

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

Usage Guidelines3/5

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

The only guidance is tuning advice: 'For multi-day windows prefer bucket_seconds of 300, 1800, 10800 or 43200.' That is useful but tells the agent how to parameterize, not when to pick this tool over get_perps_candles or get_market. No when-not or alternative routing is given.

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

Deploy Server