DepthFeed

polymarket_get_snapshots

Read-only

Historical order-book snapshots (time series) for one Polymarket market. Use interval to downsample and include_orderbook for the full ladder. History depth is gated by plan.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`coin`	No	Crypto asset. Every account plan reaches all seven; only the keyless demo surface is BTC-only.	btc
`fill`	No	ffill returns ONE ROW PER BUCKET for the whole window, carrying the last captured book into buckets that held no capture. Each row then carries `filled` (0 = a capture, 1 = carried forward) and `as_of_ts`, the moment that book was recorded. Requires `interval`. Without it, `interval` returns only the buckets that held a capture — a short series means the market is quoted infrequently, not that data is missing.
`limit`	No	Page size (1–1000).
`cursor`	No	Opaque pagination cursor from a previous response's pagination.next_cursor.
`end_time`	No	End of time as ms-epoch or ISO-8601. History is clamped to your plan's window.
`interval`	No	Downsample bucket — 30s, 1m, 5m, 1h, up to 1d. Returns the newest book in each bucket. Omit for every recorded book change.
`market_id`	Yes	Market id from polymarket_search_markets.
`start_time`	No	Start of time as ms-epoch or ISO-8601. History is clamped to your plan's window.
`include_orderbook`	No	Include the full bid/ask ladder per snapshot (default top-of-book).

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed1 schema field changedSep 2, 2026

changedInput schema / properties / coin / description

Previous value: -"Crypto asset. Keyless/demo and Free plans are BTC-only; all 7 require a paid plan."New value: +"Crypto asset. Every account plan reaches all seven; only the keyless demo surface is BTC-only."

Changed2 schema fields changedSep 2, 2026

addedInput schema / properties / fill

Added value: +{
+  "description": "ffill returns ONE ROW PER BUCKET for the whole window, carrying the last captured book into buckets that held no capture. Each row then carries `filled` (0 = a capture, 1 = carried forward) and `as_of_ts`, the moment that book was recorded. Requires `interval`. Without it, `interval` returns only the buckets that held a capture — a short series means the market is quoted infrequently, not that data is missing.",
+  "enum": [
+    "ffill",
+    "none"
+  ],
+  "type": "string"
+}

changedInput schema / properties / interval / description

Previous value: -"Downsample bucket, e.g. 1m, 5m, 1h — one snapshot per bucket."New value: +"Downsample bucket — 30s, 1m, 5m, 1h, up to 1d. Returns the newest book in each bucket. Omit for every recorded book change."

First observedJun 29, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds useful behavioral context beyond annotations, such as plan-gated history depth and the fact that this is a time series of snapshots rather than a single order-book view. No contradiction exists.

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

Conciseness5/5

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

Two tight sentences: the first defines the tool's core purpose, the second gives the two most important usage levers and a plan limitation. There is no filler or repetition of schema information.

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

Completeness5/5

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

For a tool with 9 parameters, the schema carries detailed parameter semantics, while the description supplies the strategic context: what the tool returns, for one market, and how history depth is constrained. Nothing essential is missing for an agent to decide whether and how to call it.

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 every parameter in detail. The description only briefly highlights interval and include_orderbook, which adds little beyond the schema, so the baseline score of 3 is appropriate.

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

Purpose5/5

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

The description states a specific verb and resource: historical order-book snapshots (time series) for one Polymarket market. This clearly distinguishes the tool from search/get market tools and from snapshot tools on other exchanges.

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?

The description gives practical usage guidance: use interval to downsample, include_orderbook for the full ladder, and be aware that history depth is plan-gated. It does not explicitly name when not to use the tool or point to an alternative, but the context is clear enough for an agent to select it appropriately.

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

All DepthFeed tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0

Disambiguation5/5

Each tool targets a distinct venue and data type: Polymarket/Kalshi/Limitless-specific search, orderbook, and snapshot tools are clearly separated by prefix, while bars, backtest_paths, screener, and whoami serve unique purposes. No two tools could plausibly be confused in agent selection.

Naming Consistency4/5

Most tools follow a clear `<venue>_<action>_<object>` pattern (e.g., kalshi_get_orderbook, limitless_get_snapshots, polymarket_search_markets). A few like backtest_paths, bars, screener, and whoami break the pattern, but they are descriptive and consistent with their domain. Overall predictable and legible.

Tool Count5/5

15 tools is well-scoped for a multi-venue market data API. Each tool adds meaningful functionality—search, snapshots, candles, orderbooks, screener, session info—without redundancy. The count aligns well with the apparent coverage of prediction markets, crypto, and equities.

Completeness5/5

The surface covers read operations for all major venues: search, market detail, orderbook, historical snapshots, and OHLCV bars. It also includes backtesting, cross-venue screener, and session introspection. No obvious dead ends or missing critical operations for a data-centric server.

Resources

Need Help?