Skip to main content
Glama
Futuur MCP

Futuur MCP

Official
by futuur

Search events and markets

get_markets
Read-only

Browse and search Futuur events with their markets and current prices, then filter by text, category, tag, status or close date and sort by volume or activity.

Instructions

Lists or searches Futuur events, each with its markets and current prices, in one page. An event is the question (id, title, status, close date, category, volume); a market is one tradeable outcome of it, and a market's price is the probability of the long position (0 to 1) in each available currency (OOM is play money, USDC is real money). Use it to find events by text, category, tag, status or close date, or to rank them by volume or recent activity. Returns total, returned and next_offset (null on the last page); pass next_offset as offset for the next page. Use get_market_details for one event's full description.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_markets"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagsNoUp to 10 tag slugs or names (case-insensitive). An event matching any listed tag is returned.
limitNoEvents per page, 1 to 50. Default 20.
offsetNoNumber of events to skip, for paging (use next_offset from the previous page). Default 0, maximum 10000.
searchNoCase-insensitive text search across event titles, market names, categories and tags. Max 100 characters.
statusNoWhich events to list. "open" (default): open for trading, plus recently closed ones awaiting resolution. "live": live now or starting within 12 hours. "pending_resolution": closed but not resolved yet. "resolved": resolved events, newest first.open
orderingNoSort order; a leading "-" means descending. Allowed: relevance, created_on, bet_end_date, wagers_count, volume, open_date, resolve_date (each with or without "-"). Defaults to "-relevance" for a normal listing (resolved events are always newest first).
categoriesNoCategory ids (see get_categories). A top-level category includes all its subcategories. An event matching any listed category is returned.
hide_my_betsNoIf true, omit events the user already bet on. Needs API keys configured.
currency_modeNo"play_money" (default): events tradeable with OOM play money. "real_money": events tradeable with real money (USDC/USDT). Also decides which volume the "volume" ordering uses.play_money
category_slugsNoCategory slugs such as "crypto-prices", as an alternative to ids. If both are given, an event must match both.
bet_end_date_afterNoOnly events whose trading closes at or after this time. ISO 8601 with a timezone, e.g. 2026-11-01T00:00:00Z.
bet_end_date_beforeNoOnly events whose trading closes at or before this time. ISO 8601 with a timezone, e.g. 2026-12-01T00:00:00Z.
only_markets_i_followNoIf true, only events the user follows. Needs API keys configured.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.1

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare readOnlyHint and openWorldHint, but the description adds substantial behavior beyond them: page-level pagination contract ('total', 'returned', 'next_offset' with null on the last page), the instruction to feed next_offset back as offset, the meaning of price as long-position probability, and the play-money vs real-money (OOM/USDC) distinction. It also flags that some filters ('hide_my_bets', 'only_markets_i_follow') require API keys configured, which is an auth prerequisite the annotations do not convey.

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?

Four sentences, front-loaded with purpose, then concepts, then use cases, then pagination, then the sibling handoff — a logical progression with no filler. The entity definitions are slightly verbose but they pay for themselves given 13 parameters and no output schema.

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?

For a 13-parameter read-only search tool with no output schema, the description covers the return envelope, pagination, currency semantics and the sibling handoff well. The remaining gaps are minor: it does not describe result ordering defaults for resolved events beyond the schema, nor the overall auth expectation for real_money mode, only the per-filter 'needs API keys' notes.

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%, with all 13 parameters documented including enums, defaults and bounds, so the schema already carries the parameter burden and the baseline is 3. The description's added meaning is mostly conceptual (event vs market, what price means) rather than parameter-specific; it does not, for example, clarify how tags, categories and category_slugs combine beyond what the schema already says.

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 opens with a specific verb and resource ('Lists or searches Futuur events, each with its markets and current prices, in one page') and then defines the two core entities (event = question with id/title/status/close date/category/volume; market = one tradeable outcome with price as a 0-1 probability). It explicitly sets itself apart from get_market_details, so an agent can distinguish the two without opening either schema.

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

Usage Guidelines5/5

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

It states the usable dimensions directly ('find events by text, category, tag, status or close date, or to rank them by volume or recent activity') and names the alternative with its selecting condition: 'Use get_market_details for one event's full description.' That is the explicit routing pattern expected of a high-scoring definition.

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