Valorant MCP Server

get_benchmarks

Compare your stats against other players in the same matches to judge whether your numbers are good or bad, controlling for rank.

Instructions

Judge whether the player's numbers are good or bad by comparing them with the other 9 players in the same matches (so rank is controlled for):

vs_lobby: per-round metrics for you vs players in the same role that match vs the whole lobby (ACS, ADR, KAST, opening duels, deaths traded, trade-chance conversion, isolated deaths, teammate distance at death, survival, utility casts per round)
avg_place_in_lobby_of_10: your average placement among all 10 players (1 = best)
by_agent: for each agent played 2+ times, you vs everyone else on that agent in your lobbies, incl. casts per round of each ability and Henrik's performance breakdown/ratings when available

Input Schema

Name	Required	Description	Default
`map`	No	Only matches on this map, e.g. 'Ascent'
`mode`	No	Queue to analyze	competitive
`agent`	No	Only matches on this agent, e.g. 'Sova'. Fetches extra history to fill `count`.
`count`	No	Number of recent matches to analyze (max 50)
`region`	No	na, eu, ap, kr, latam or br. Defaults to the server setting.
`season`	No	Analyze a whole act instead of the last `count` games: 'current' (the act of the most recent game) or an act like 'e11a6'. When set, `count` is ignored and up to 100 matches from that act are used.
`username`	Yes	Riot ID as name#TAG, e.g. 'player#NA1'

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.4.2Nov 2, 2026

TDQS

A4/5.0

Behavior4/5

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

With no annotations, the description carries the burden and does meaningful work: it discloses the comparison baseline (other players in the same role/whole lobby), that rank is controlled for, and the 2+ games threshold for per-agent breakdowns. It omits cost/scope implications of scanning up to 50 (or 100 for a season) matches, which is the main remaining behavioral gap.

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?

Purpose is front-loaded in the first clause, followed by a tight three-bullet breakdown of the comparison outputs. No filler and no restatement of the tool name.

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?

An output schema exists, so the return values need not be explained, yet the description still sketches the three result sections, which is enough for an agent to call it and interpret the answer. The only gap is the absence of any note on runtime/cost for large count or season-wide analyses.

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 map, mode, agent, count, region, season, and username are all documented in the schema itself. The description adds conceptual context (what 'vs_lobby' and 'by_agent' aggregates mean) but nothing about how parameters shape the comparison beyond what the schema states, so baseline 3 applies.

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 analytical verb and resource: judging a player's numbers as good/bad by benchmarking against the other 9 players in the same matches, with rank controlled for. That is clearly distinct in spirit from profile/history siblings, but no sibling is named and the boundary with get_performance_report or compare_periods is left implicit.

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?

'Judge whether the player's numbers are good or bad' gives a clear triggering question for when to reach for this tool rather than raw stat tools. It offers no when-not guidance and does not route the agent to or away from any of the eight siblings.

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

Deploy Server