chess ceo

Name: chess ceo
Author: chessceo

by chessceo

Overview Schema Related Servers Score Discussions

TypeScript

@chessceo/mcp

Model Context Protocol server for chess.ceo — 11.7M+ games, ~1.5M FIDE player profiles, opening preparation, live broadcasts. Lets Claude, Cursor, and any other MCP host answer chess questions directly against real data instead of hallucinating.

No API key. No auth. No state. Free to use.

What it can do

The server exposes 8 tools that mirror the public GET API surface at chess.ceo:

Tool	What it answers
`search_player`	"Find FIDE ID for Magnus Carlsen"
`get_player_profile`	"How strong is X, what do they play, who have they beaten"
`get_player_preparation`	"What does X play against 1.e4? What's their win rate with the Najdorf?"
`get_position_stats`	"From this position, which move scores best in the 11.7M-game database?"
`get_head_to_head`	"What's the record between X and Y?"
`list_live_tournaments`	"What's being broadcast live right now?"
`list_tournament_players`	"Who's playing in tournament T?"
`list_player_live_tournaments`	"Is X playing anywhere right now?"

Related MCP server: Chess MCP

Install (Claude Desktop)

Add to your claude_desktop_config.json (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows):

{
  "mcpServers": {
    "chessceo": {
      "command": "npx",
      "args": ["-y", "@chessceo/mcp"]
    }
  }
}

Restart Claude Desktop. You should see the chess.ceo tools appear in the tool list at the bottom of the chat.

Install (Cursor)

Similar ~/.cursor/mcp.json:

{
  "mcpServers": {
    "chessceo": {
      "command": "npx",
      "args": ["-y", "@chessceo/mcp"]
    }
  }
}

Install (Claude Code)

This repo is also a Claude Code plugin marketplace, so you can add it directly:

/plugin marketplace add chessceo/chessceo-mcp
/plugin install chessceo@chessceo

Claude Code will pull the plugin from GitHub and wire the MCP server automatically. Enable "Sync automatically" in the marketplace UI if you want future updates fetched on push.

Try it

Ask your model:

"Who has the better record against Magnus Carlsen: Ding Liren or Fabiano Caruana?"
"What does Alireza Firouzja play with White against the Najdorf?"
"Are there any live tournaments right now with Hikaru Nakamura?"
"From the position after 1.e4 c5 2.Nf3 d6 3.d4 cxd4 4.Nxd4 Nf6 5.Nc3 a6, what's the top continuation across the whole database?"

Prep workflow (built-in prompts)

For MCP hosts that show prompts in a slash-menu (Claude Desktop, Cursor, Claude Code), three pre-baked prompts are included so users get a proper preparation workflow without prompt-engineering their own:

Prompt	Purpose
`prepare_for_game(me, opponent, my_color?, time_control?)`	Full pre-match workflow: resolves both players, weights games by recency + format (classical OTB > rapid/blitz > online), walks the opponent's repertoire looking for lines where they score under 40%, checks head-to-head, and delivers a concrete plan with the moves to steer toward the opponent's weak points.
`scout_player(player)`	Deep scouting report on one player — style, top openings, recent form, biggest wins and losses, recurring weaknesses.
`head_to_head_briefing(player_a, player_b)`	One-paragraph read on the history between two players — who has the edge, dominant openings, style clash, current form.

Pick one from the host's slash-menu, fill in the arguments, and the model does the rest.

Remote MCP (chess.ceo-hosted)

You can also connect to chess.ceo's hosted instance and skip installing anything:

https://mcp.chess.ceo/mcp

In Claude Code:

/plugin add-mcp url https://mcp.chess.ceo/mcp

In Claude Desktop, edit claude_desktop_config.json:

{
  "mcpServers": {
    "chessceo": {
      "url": "https://mcp.chess.ceo/mcp"
    }
  }
}

Same 8 tools, same data, zero-install. Useful when the host can't spawn subprocesses (e.g. Claude.ai web, Claude mobile, ChatGPT connectors).

Self-host the HTTP transport

The same package can run as a persistent HTTP server, not just a stdio subprocess:

chessceo-mcp --transport=http --http-port=8080 --http-host=127.0.0.1

Flags (or the corresponding env vars):

Flag	Env var	Default	Purpose
`--transport`	`MCP_TRANSPORT`	`stdio`	`stdio` or `http`
`--http-port`	`MCP_HTTP_PORT`	`8080`	Port to bind
`--http-host`	`MCP_HTTP_HOST`	`127.0.0.1`	Bind address
`--http-path`	`MCP_HTTP_PATH`	`/mcp`	Streamable-HTTP endpoint

GET /healthz returns 200 ok\n — wire it into your uptime monitor.

systemd unit (example)

# /etc/systemd/system/chessceo-mcp.service
[Unit]
Description=chess.ceo MCP server (Streamable HTTP)
After=network.target

[Service]
Type=simple
User=www-data
Environment=NODE_ENV=production
Environment=MCP_TRANSPORT=http
Environment=MCP_HTTP_PORT=8127
Environment=MCP_HTTP_HOST=127.0.0.1
ExecStart=/usr/bin/npx -y @chessceo/mcp
Restart=on-failure
RestartSec=5

[Install]
WantedBy=multi-user.target

nginx snippet (example)

server {
    listen 443 ssl http2;
    server_name mcp.chess.ceo;

    ssl_certificate     /etc/letsencrypt/live/mcp.chess.ceo/fullchain.pem;
    ssl_certificate_key /etc/letsencrypt/live/mcp.chess.ceo/privkey.pem;

    # Streamable HTTP is short JSON POSTs — no long-poll SSE required.
    location /mcp {
        proxy_pass         http://127.0.0.1:8127/mcp;
        proxy_http_version 1.1;
        proxy_set_header   Host $host;
        proxy_set_header   X-Real-IP $remote_addr;
        proxy_buffering    off;   # streaming responses shouldn't be buffered
        proxy_read_timeout 300s;
    }

    location = /healthz { proxy_pass http://127.0.0.1:8127/healthz; }
}

Development

git clone <this repo>
cd chessceo-mcp
npm install
npm run build   # tsc → dist/
npm start       # runs the server on stdio (for MCP hosts)

# or run the HTTP transport locally:
node dist/index.js --transport=http --http-port=8127
curl http://127.0.0.1:8127/healthz     # should print "ok"

Environment variable overrides:

CHESSCEO_BASE_URL — override the API base (default https://chess.ceo). Useful for testing against staging.
MCP transport env vars — see the self-host table above.

What's under the hood

The chess.ceo public API is a GET-only surface documented at chess.ceo/llms.txt. This MCP server is a thin wrapper — one tool per endpoint, with input schemas so LLMs can call them safely. When you ask the model a chess question, it picks the right tool, calls it, and reasons over the JSON. Nothing is invented; the data is straight from the database.

License

MIT

Available Tools

8 tools

analyseA

Short Stockfish evaluation at a position. Returns the top-N candidate moves with score (centipawns from side-to-move POV, positive = advantage; or mate distance) and the principal variation for each. Defaults: 2s think time, top-3 lines. PV moves come back in UCI notation (e2e4, not e4). Use this to sanity-check candidate lines from get_position_stats or get_player_preparation — human game frequency tells you what people play, engine evaluation tells you what's actually good.

ParametersJSON Schema

Name	Required	Description
`fen`	Yes	FEN of the position to analyse.
`multipv`	No	Number of candidate lines to return (default 3).
`movetime_ms`	No	Think time in milliseconds (default 2000).

TDQS

A4.6/5.0

Behavior4/5

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

With no annotations, the description discloses key behaviors: uses Stockfish, defaults (2s think time, top-3 lines), score interpretation (centipawns from side-to-move POV, positive=advantage or mate distance), and PV notation (UCI). It is largely transparent, though does not explicitly state it is read-only—this is clear from context.

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 concise sentences: first explains purpose and output, second adds defaults and usage guidance. Every sentence is informative and well-front-loaded, with no wasted words.

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?

Given no output schema, the description adequately explains output format and defaults. It covers the essential context for effective use, though it omits error conditions or rate limits—acceptable for a simple tool with 3 parameters and no nested objects.

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%, baseline 3. The description adds value by explaining score interpretation, default values for multipv and movetime, and that PV moves are in UCI notation. This enriches the semantics 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?

The description clearly states the tool performs a Short Stockfish evaluation and returns top-N candidate moves with scores and principal variations. It distinguishes itself from siblings like get_position_stats and get_player_preparation by noting the difference between engine evaluation and human game frequency.

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?

The description explicitly instructs when to use this tool (sanity-check candidate lines from other tools) and contrasts it with alternatives, stating 'human game frequency tells you what people play, engine evaluation tells you what's actually good.'

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

get_player_preparationA

For a given player, colour and starting position, return both the moves the player actually chose (frequency + win rate) and the underlying games. Position is specified either as a move sequence in SAN (line) or a raw FEN. Use line iteratively to walk the opening tree: call once with empty line, pick a move, call again with line extended by that move, etc. When preparing for a real game, weight recent games (last 12-24 months) more heavily than old ones, classical over-the-board > rapid/blitz > online, and look for variations the player scores poorly in (below ~40%) or plays with less variety (shallower prep).

ParametersJSON Schema

Name	Required	Description
`fen`	No	Alternative to `line` — raw FEN of the target position.
`line`	No	Move sequence in SAN, space-separated, no move numbers required. Example: 'e4 e5 Nf3'. Leave empty for the starting position.
`color`	Yes	Which colour the player is analysed with.
`limit`	No	Number of games to return (max 10 per request; page with offset).
`offset`	No
`fide_id`	Yes	FIDE ID from search_player.

TDQS

A4.4/5.0

Behavior4/5

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

Describes input specification and iterative behavior well, but does not mention data freshness, rate limits, or edge cases like no games found. Since annotations are absent, more disclosure would help.

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?

Single paragraph of moderate length, front-loaded with main purpose. Could benefit from bullet points for readability but remains concise.

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

Completeness3/5

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

Covers usage well but does not describe return value structure (format of frequency/win rate, game objects). Without output schema, this is a notable gap for an agent.

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 covers 83% of parameters; description adds value by explaining how to use `line` iteratively and weighting strategy. Does not repeat schema but provides usage context beyond parameter names.

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 clearly states the tool returns moves (frequency + win rate) and underlying games for a given player, color, and starting position. It distinguishes from siblings by specifying iterative tree navigation with `line`.

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?

Explicitly explains iterative usage of `line` to walk the opening tree, and provides weighting strategy for preparation (recent games, classical over rapid, etc.). No explicit when-not-to-use, but context is clear.

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

get_player_profileA

Full stats for one player: identity, monthly rating history, peak / trend stats, career W/D/L by color and time control, top-10 openings as White and Black, opponent analysis by rating bracket, notable wins and worst losses, top events with performance ratings. Often enough on its own for 'how strong is X, what do they play, who have they beaten'.

ParametersJSON Schema

Name	Required	Description	Default
`fide_id`	Yes	FIDE ID from search_player.

TDQS

A3.9/5.0

Behavior3/5

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

No annotations are provided, so the description carries the full burden. It lists the data returned but does not explicitly state that the tool is read-only or has no side effects. However, the nature of the data (stats) implies retrieval, and no contradictions are present.

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?

The description is comprehensive yet concise, listing many features in a single paragraph. It is front-loaded with the main purpose. Every sentence adds value, though it could be slightly more structured for easier scanning.

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?

Given no annotations and no output schema, the description is quite complete in telling an agent what data the tool returns. It covers all major aspects (identity, rating history, career stats, openings, opponents). However, it does not mention error handling or limitations.

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 coverage is 100% (one parameter with description 'FIDE ID from search_player'). The description does not add extra meaning beyond what the schema provides; it mentions 'FIDE ID' but that is already in the schema. Baseline 3 applies.

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 clearly states it provides 'Full stats for one player' and lists specific data categories (identity, rating history, career stats, openings, opponent analysis). It distinguishes itself from sibling tools by saying it is 'often enough on its own' for common player queries, implying it is a comprehensive profile tool.

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 ends with guidance on when to use it: 'Often enough on its own for 'how strong is X, what do they play, who have they beaten''. This implies it is suitable for high-level player overviews, but it does not explicitly state when not to use it or name alternative tools.

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

get_position_statsA

Move statistics from all 11.7M+ indexed games at a given position — game counts, win percentages, top continuations. Answers 'from position P, how often does White play 4. O-O vs 4. d3, and which scores better'.

ParametersJSON Schema

Name	Required	Description	Default
`fen`	Yes	FEN of the position to look up.
`limit`	No	Number of top continuations to return.

TDQS

A4.1/5.0

Behavior4/5

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

No annotations are provided, so the description carries the full burden. It discloses that the tool queries 11.7M+ indexed games and returns statistics, implying a read-only behavior. However, it does not specify data freshness, rate limits, or any other constraints, though the behavioral traits are reasonably clear for a simple data retrieval tool.

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?

The description is extremely concise: two short sentences that are front-loaded with the core value proposition. The example is efficient and adds concreteness without waste. Every word 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?

Given the tool is a simple query with no output schema, the description adequately explains return types (game counts, win percentages, top continuations) and the data source (11.7M+ games). It covers all needed context for an agent to understand what the tool returns.

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% (fen and limit are described). The description adds minimal extra meaning: the example clarifies that 'limit' controls number of top continuations, and 'fen' is position identifier. This meets the baseline but does not significantly enhance understanding 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?

Description clearly states the tool provides move statistics (game counts, win percentages, top continuations) from a large database of games for a given position. The example question concretely illustrates the purpose and differentiates from siblings like 'analyse' which is presumably for engine analysis.

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

Usage Guidelines3/5

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

Description implies the tool is for statistical queries from a large game database, but does not explicitly state when to use it versus alternatives like 'analyse' or provide exclusion criteria. The context signals suggest a read-only query, but no direct usage guidance is given.

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

list_live_tournamentsA

Tournaments currently being broadcast live on chess.ceo. Use this when the user asks 'what's on right now' / 'live tournaments today'.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

A4.5/5.0

Behavior3/5

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

No annotations provided, so description carries full burden. It mentions it returns live broadcast data, but does not disclose whether it requires authentication, rate limits, or data freshness. However, for a simple read-only tool with no parameters, the behavior is straightforward.

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, front-loaded with core action, no wasted words. Perfectly concise.

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?

Given low complexity (no params, no output schema), the description fully covers what the tool does and when to use it. No missing information.

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?

No parameters in input schema (100% schema coverage). Baseline for 0 params is 4; description does not need to add param info.

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 it lists tournaments currently being broadcast live, which is a specific verb-resource combination. It clearly distinguishes from sibling tools like 'analyse' or 'get_player_profile' which are unrelated to live tournaments.

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?

Provides explicit usage cues with example queries: 'what's on right now' and 'live tournaments today'. This clearly tells the agent when to use this tool.

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

list_tournament_playersC

Players participating in one live-broadcast tournament.

ParametersJSON Schema

Name	Required	Description	Default
`tour_id`	Yes	Tournament ID from list_live_tournaments.

TDQS

C2.8/5.0

Behavior2/5

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

No annotations are provided, so the description bears full responsibility for behavioral disclosure. It only states the basic purpose, omitting details like pagination, ordering, or whether results are live-updated. This is insufficient for a mutation-free tool.

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

Conciseness3/5

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

The description is a single sentence, which is concise but under-informative. It could be expanded with key details without losing conciseness.

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

Completeness2/5

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

The tool has one parameter and no output schema. The description lacks information about the output format, any default behavior, or context about what 'participating' means. It is incomplete for an agent to reliably use the tool.

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 explains the tour_id parameter. The description adds no extra meaning beyond what is in the schema, resulting in a neutral score.

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 clearly states the tool lists players participating in a live-broadcast tournament. The action (list) and resource (players) are specific, and it differentiates from sibling tools like list_live_tournaments and search_player.

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

Usage Guidelines2/5

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

No explicit guidance on when to use this tool vs alternatives. The input schema hints that tour_id comes from list_live_tournaments, implying a prerequisite, but there is no discussion of when-not-to-use or alternative tools.

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

prep_snapshotA

One call, three parallel fetches at the same position: opponent's stats on their side, your stats on your side, and the 11.7M-game general database at that position. Use this while walking the opening tree — one round trip instead of three separate calls, and you can compare the three views directly (e.g. opponent has 2 games here but the general DB has 8k → prep candidate).

ParametersJSON Schema

Name	Required	Description
`fen`	No	Alternative to line — raw FEN of the target position.
`line`	No	Move sequence in SAN, space-separated. Empty = starting position. Example: 'e4 c5 Nf3'. Either line or fen (or neither for the starting position).
`my_color`	Yes	The colour YOU will play.
`fide_id_me`	Yes	Your FIDE ID.
`fide_id_opponent`	Yes	Opponent's FIDE ID.

TDQS

A4.2/5.0

Behavior4/5

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

With no annotations, the description carries full burden and discloses that it performs three parallel fetches and returns data for comparison. It provides an example of expected behavior (opponent 2 games vs general 8k) but does not detail side effects or permissions, which is acceptable for a read-only operation.

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, front-loaded with the key action and usage recommendation. Every sentence adds value, no waste.

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?

No output schema, but the description hints at return structure by naming the three data sources and gives a concrete example of comparison. It is fairly complete for the tool's complexity, though explicitly listing output fields would improve completeness.

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 description adds minimal extra meaning beyond the schema. It mentions the three fetches but doesn't elaborate on how parameters affect each. Baseline is 3, and no significant additional semantic value is provided.

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 clearly states that the tool performs three parallel fetches at the same position, combining opponent stats, your stats, and general database. It distinguishes from siblings like get_position_stats by emphasizing the combined view and is specific about the resource and action.

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 explicitly advises using this while walking the opening tree for a single round trip instead of three separate calls, and gives an example of how to compare views. It implies the context of use but does not explicitly state when not to use or name specific alternative tools.

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

search_playerA

Fuzzy name lookup for FIDE-rated chess players. Returns candidate matches with their FIDE ID, current rating, title (GM/IM/etc.), and country. Use this to resolve a plain-English name (e.g. 'Carlsen', 'Ding Liren') to the FIDE ID that every other tool needs.

ParametersJSON Schema

Name	Required	Description	Default
`name`	Yes	Player name or partial name. Case-insensitive, fuzzy.

TDQS

A4.5/5.0

Behavior4/5

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

No annotations exist, but the description discloses key behavioral traits: fuzzy matching, case-insensitivity, and the nature of search (returns candidates). It does not mention any destructive side effects, which is appropriate for a lookup tool. However, it could mention potential empty results or performance limitations.

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 with no wasted words. The first sentence defines the operation and output, the second provides usage guidance. Information is front-loaded.

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?

Despite no output schema, the description fully explains return values (FIDE ID, rating, title, country). It also explains the tool's role in a larger workflow (resolving names for other tools). Given the tool's simplicity, the description is complete.

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 coverage is 100% with the 'name' parameter described as 'Player name or partial name. Case-insensitive, fuzzy.' The description adds context about using it to resolve to a FIDE ID, but the schema already conveys the fuzzy and partial nature. Baseline 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 clearly states the tool performs 'Fuzzy name lookup for FIDE-rated chess players' and lists the returned fields (FIDE ID, rating, title, country). This distinguishes it from siblings like analyse, get_player_preparation, etc., which involve analysis or tournament data.

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?

Explicitly tells when to use: 'Use this to resolve a plain-English name ... to the FIDE ID that every other tool needs.' This provides clear context for when this tool is appropriate versus others.

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

Install Server

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

TDQS

A3.8/5.0

Disambiguation4/5

Tools are mostly distinct, though overlap exists between get_player_preparation and prep_snapshot (both preparation-focused) and between analyse and get_position_stats (both evaluate positions). Descriptions clarify usage, reducing confusion.

Naming Consistency4/5

Most names follow verb_noun pattern (e.g., get_player_profile, list_live_tournaments). Exceptions: analyse (single verb, British spelling) and prep_snapshot (no verb). Overall consistent with minor deviations.

Tool Count5/5

8 tools is well-suited for a chess server covering player search, profiles, preparation, position analysis, engine evaluation, and live tournaments. Neither too few nor too many.

Completeness4/5

Core chess analysis needs are covered: player info, statistics, engine evaluation, and live events. Minor gaps like missing full game retrieval or historical tournament lists, but the surface is reasonably complete for its purpose.

Maintenance

ActivityMaintained

ResponsivenessSyncing

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

chess B
io.github.pipeworx-io
Chess.com MCP — wraps the Chess.com public API (free, no auth)
Sports Games & Gamification
352
Lichess B
io.github.pipeworx-io
Lichess public API: players, ratings, eval, tablebase, opening explorer
Games & Gamification Sports
412
rankparse-mcp A
io.github.abhibavishi
SEO MCP server — backlinks, domain authority, tech stack, and 18+ tools via Common Crawl.
Marketing Search
642
mcp A
ai.llmse
Public MCP server for the LLM Search Engine
Search RAG Systems Developer Tools
102

Related MCP Servers

chesscom-mxcp
Sports Databases
datYori
F
license
Not graded
quality
D
maintenance
An enterprise-grade Chess.com MCP server built with MXCP, featuring caching, analytics, audit trails, and advanced data analysis capabilities. https://mxcp.dev/
Updated a year ago (2025-06-27 07:40 UTC)
Chess MCP
Games & Gamification AI & Machine Learning
arvid-berndtsson
A
license
Not graded
quality
C
maintenance
A powerful chess engine and game server built with the Model Context Protocol (MCP). Play chess against AI, analyze positions, and integrate chess functionality into your AI applications.
Updated a month ago (2026-07-22 09:13 UTC)
20
1
ISC
chess-mcp
adityareus
F
license
Not graded
quality
C
maintenance
An MCP server that fetches and filters chess.com game data, returning compact summaries instead of massive JSON, enabling LLMs to answer questions about player performance and head-to-head records.
Updated a month ago (2026-07-26 22:54 UTC)
lichess-mcp
Sports Games & Gamification Open Data
Anay704
A
license
A
quality
C
maintenance
MCP server that exposes the Lichess public API through tools for querying player profiles, games, analysis, openings, puzzles, and tournaments, allowing natural-language chess questions without an API key.
Updated a month ago (2026-08-02 00:21 UTC)
8
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/chessceo/chessceo-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server