Cito API

cs2_positions

Read-only

CS2 positional data from parsed demos. With mapId: view=grenades (every grenade with landing spot, thrower, round, duration), view=positions (grenades, bomb plants/defuses and kills with attacker/victim spots in one timeline) or view=heatmap (counts per radar cell; kind=utility|smoke|flash|he|molotov|decoy|bomb_plant|bomb_defuse|kill|death). With playerId instead: that player's grenades across recent maps (pass map for a heatmap). Every point has game coordinates and a 0..1 radar point. Read the response notes and null fields for what is not recorded.

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": "cs2_positions"
  }
}

Input Schema

Name	Required	Description
`map`	No	With playerId: map name (Mirage, Inferno...) to get a heatmap.
`days`	No	With playerId: look-back window in days (default 180).
`grid`	No	Heatmap cells per side (default 32).
`kind`	No	view=heatmap: utility, smoke, flash, he, molotov, decoy, bomb_plant, bomb_defuse, kill or death. view=positions: grenade,bomb,kill.
`side`	No	T or CT.
`team`	No	With mapId + view=grenades: only this team (id or name).
`type`	No	Grenade type: smoke, flash, he, molotov or decoy.
`view`	No	For mapId: grenades (default), positions or heatmap.
`limit`	No	Max items to return (default 200, max 5000). Example: 200.
`mapId`	No	Map/game id from match maps, e.g. "cs2-match-2399437-map-1".
`round`	No	Only this round.
`player`	No	With mapId: only this player (id or nickname).
`playerId`	No	Player id or slug (e.g. "ropz"). Use instead of mapId for one player across maps.

Output Schema

Name	Required	Description
`ok`	Yes	true if the tool succeeded
`data`	No	Result payload when ok is true; null on error
`meta`	Yes
`error`	No
`partial`	No
`pagination`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 31, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnly/openWorld/non-destructive. The description adds real behavioral context beyond that: a data-quality caveat ('Read the response notes and null fields for what is not recorded') and the coordinate contract ('every point has game coordinates and a 0..1 radar point'). It doesn't discuss volume/pagination behavior, keeping it below 5.

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?

Front-loads the resource and mode selection in the first two sentences with no filler. The parenthetical lists of enum values are dense run-ons that partially duplicate the schema enums, costing some efficiency.

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 return values needn't be explained. The description covers all three modes, the mapId/playerId split, and data-quality caveats; the only soft spot is that with zero required parameters it doesn't explicitly state that mapId or playerId must be supplied to get results.

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, but the description adds cross-parameter semantics the schema only documents per-field: the mapId-vs-playerId mode split, the view-dependent meaning of kind, and that grid applies to heatmap cells. That interaction guidance is genuine added value.

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?

States a specific verb+resource ('CS2 positional data from parsed demos') and enumerates exactly what each of the three views returns (grenades, positions timeline, heatmap counts). An agent can distinguish it from siblings like cs2_utility_leaderboard or cs2_clutches purely from the description.

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?

Gives explicit branching guidance: with mapId choose grenades/positions/heatmap, with playerId get that player's grenades across maps, and pass map for a heatmap. It does not name sibling tools or say when-not to use it, so it falls short of a 5.

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

All Cito API tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?