Skip to main content
Glama
Sign In
Lichess Coach MCP

Lichess Coach MCP

by frogr
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Engine-flagged mistakes in a game

find_mistakes
Read-onlyIdempotent

List a player's inaccuracies, mistakes, and blunders in a Lichess game using Lichess server analysis, with engine best lines, eval changes, and win chances lost; reports if analysis is missing.

Instructions

List one player's inaccuracies, mistakes and blunders in a Lichess game, straight from Lichess's server analysis: the move played, the engine's best move and line, evals before/after and winning chances lost. If the game was never analysed, it says so instead of guessing.

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": {
      "game_id": "<game_id>",
      "for_player": "<for_player>"
    },
    "name": "find_mistakes"
  }
}

Input Schema

NameRequiredDescriptionDefault
game_idYesLichess game id (8 characters, e.g. "bKi4MXMJ") or a lichess.org game URL.
for_playerYesWhose mistakes to list: a username in the game, or "white" / "black".
min_severityNoSmallest judgment to include (default inaccuracy = everything Lichess flagged).inaccuracy

Output Schema

NameRequiredDescriptionDefault
urlYes
playerYes
game_idYes
messageYes
summaryNo
mistakesYes
analysis_availableYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations cover the read-only/idempotent/safe profile, and the description adds genuinely new behaviour: results come from Lichess's server analysis rather than a locally computed evaluation, and an unanalysed game yields an explicit statement rather than guesses. Rate limits, auth, or pagination are not mentioned.

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 sentences, zero filler: the first front-loads what is returned and from where, the second covers the degraded case. Every clause earns its place.

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?

An output schema exists, so return-value explanation is not required; the description nonetheless sketches the payload and the unanalysed-game case. With annotations covering safety and the schema covering all three parameters, nothing an agent needs to invoke this correctly is missing.

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%, including the game_id format and the white/black-or-username option for for_player, so the schema carries the burden. The description lists the three severity labels, loosely mapping to min_severity's enum, but adds no format or edge-case detail beyond the schema.

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 (list) and resource (one player's inaccuracies/mistakes/blunders in a Lichess game) and pins the source as Lichess server analysis, which cleanly separates it from siblings like evaluate_position or get_game.

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?

Implies the prerequisite context (a Lichess game that has been analysed, one player at a time) and the fallback when that precondition fails. It doesn't explicitly route the agent away from evaluate_position when the agent just wants a single-position judgement, so it stops 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.

Deploy Server

Other Tools