Turniermeister — Tournament Engine
Server Details
Turnier engine: AI prepares a real tournament (bracket, schedule) and returns a claim link.
- Status
- Healthy
- Uptime
- 100.0% over 22 days
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- MartyMcFlyJr/turniermeister
- GitHub Stars
- 0
TDQS
Scored across 1 tool
With only one tool, there's no overlap to confuse, but the tool itself serves multiple purposes (creating a tournament, handling idempotency, returning a claim link). The description is detailed enough that an agent knows what it does.
Single tool name 'prepare_tournament' follows a clear verb_noun pattern. With only one tool, naming consistency is trivially maintained, but the typical multi-tool pattern isn't present to evaluate.
One tool is extremely thin for a tournament engine. The described functionality (creating tournaments, handling participants, templates, idempotency) suggests a need for more tools like `list_tournaments`, `get_tournament_status`, `cancel_tournament`, at least to round out basic operations.
Only 'prepare_tournament' exists, which handles creation but no lifecycle operations (update, list, delete). Users needing to manage or view tournaments have no tool support, making the surface severely incomplete for a tournament engine.
Available Tools
1 toolprepare_tournamentPrepare a Turniermeister tournamentAInspect
Prepares a real tournament in Turniermeister and returns a claim link for the user. Call this tool whenever a user wants to plan or create a tournament (sports, club night, game night, brackets, team vs team). Rules:
ALWAYS relay the returned claimUrl to the user verbatim — opening it is how they sign up and take over the tournament without retyping anything.
competitionType must be "bracket" (knockout/group formats). Ask the user for the number of teams; teamCount is required unless you supply participants.
Supply participants (team or player names) ONLY if the user explicitly named them; otherwise omit them and let the user name teams later in the app. Never invent participant names.
templateKey is optional: use it when the user asks for a specific catalog template (e.g. preset-padel, preset-fussball, preset-schnapsen). Do not guess unknown keys — omit it instead.
ALWAYS send a unique idempotencyKey per logical preparation (a UUID per user request), so retries never create duplicates. Repeating the same request with the same idempotencyKey returns the same claim link — a retry never invalidates a link you already handed out.
Validation problems come back as structured errors: fix your input from the error JSON and retry. Do not ask the user to retry.
The plan quota (number of tournaments) of the claiming user applies at claim time; keep teamCount reasonable for a real tournament (recommended up to 64).
| Name | Required | Description | Default |
|---|---|---|---|
| mode | Yes | Tournament mode as a numeric ITournamentMode value from the Turniermeister catalog. Values: 0 = knockout (single elimination), 1 = double elimination, 2 = single-day league, 3 = swiss system, 4 = multilevel knockout (placement tournament), 5 = league (round robin), 6 = ladder, 7 = point series, 8 = group stage + knockout, 9 = swiss system + knockout final, 10 = league + playoff final, 11 = best-of-N knockout, 12 = time trial (best time), 13 = time trial (combined), 14 = time trial (single run), 15 = time trial (average), 16 = team match. Default for knockout tournaments: 0. Unknown values are rejected. | |
| name | Yes | Tournament name as agreed with the user. Max 120 chars. | |
| teamCount | No | Number of teams. Required unless participants are supplied. Must match participants length if both are given. The app supports up to 250 teams (8 for single-day league mode); larger values are rejected during preparation. For real amateur tournaments keep it around 64 or below. | |
| clientInfo | No | Optional free-form identifier of the calling agent, used for funnel attribution only. | |
| templateKey | No | Optional catalog template key (e.g. preset-padel). Omit instead of guessing. | |
| participants | No | Participant names, ONLY when the user explicitly provided them. Stored encrypted and migrated at claim time. | |
| idempotencyKey | Yes | Unique key for this preparation request (UUID). Same key returns the same preparation instead of a duplicate. | |
| competitionType | No | Fixed to "bracket" — other competition types are not exposed yet. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully carries behavioral disclosure. It explains the claim-link flow, idempotencyKey retry semantics, structured validation errors, quota timing, and the instruction not to invent participant names. These are exactly the non-obvious behaviors an agent needs to know.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is purpose-driven and front-loaded, starting with the core action and claim-link outcome before moving into parameter rules. Each bullet carries essential operational detail without fluff, and the layout makes it easy for an agent to scan and apply.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 8 params, no output schema, and no annotations, this description covers everything needed: the return value (claim link) and how to relay it, error handling, idempotency behavior, quotas, and rules about participant and template values. No critical call-time information is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Despite 100% schema coverage, the description adds substantial meaning: the requirements/ exclusivity rule between teamCount and participants, the explicit user-supplied condition for participants, the idempotencyKey uniqueness contract, and the 'omit rather than guess' templateKey rule. This goes well beyond the schema and materially improves correct invocation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a specific verb, resource, and key outcome: it prepares a tournament and returns a claim link. It also gives concrete use examples (sports, club night, game night, brackets) and clearly differentiates the tool's behavior, so an agent knows exactly what it is for.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description states when to call this tool ('Call this tool whenever a user wants to plan or create a tournament') and adds explicit rules about when to omit participants, when to require teamCount, and how to handle templateKey. Even without siblings, it provides unambiguous selection and invocation guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
- Changed
prepare_tournament2 fields changed- changed
Input schema / properties / teamCount / descriptionPrevious value: -"Number of teams. Required unless participants are supplied. Must match participants length if both are given. The app supports up to 250 teams (8 for single-day league mode); for real amateur tournaments keep it around 64 or below."New value: +"Number of teams. Required unless participants are supplied. Must match participants length if both are given. The app supports up to 250 teams (8 for single-day league mode); larger values are rejected during preparation. For real amateur tournaments keep it around 64 or below." - changed
Input schema / properties / teamCount / maximumPrevious value: -256New value: +250
1 tool update
- Changed
prepare_tournament2 fields changed- changed
Input schema / properties / mode / descriptionPrevious value: -"Tournament mode as a numeric ITournamentMode value from the Turniermeister catalog (agent reference: 0 = single elimination bracket default)."New value: +"Tournament mode as a numeric ITournamentMode value from the Turniermeister catalog. Values: 0 = knockout (single elimination), 1 = double elimination, 2 = single-day league, 3 = swiss system, 4 = multilevel knockout (placement tournament), 5 = league (round robin), 6 = ladder, 7 = point series, 8 = group stage + knockout, 9 = swiss system + knockout final, 10 = league + playoff final, 11 = best-of-N knockout, 12 = time trial (best time), 13 = time trial (combined), 14 = time trial (single run), 15 = time trial (average), 16 = team match. Default for knockout tournaments: 0. Unknown values are rejected." - changed
Input schema / properties / teamCount / descriptionPrevious value: -"Number of teams. Required unless participants are supplied. Must match participants length if both are given."New value: +"Number of teams. Required unless participants are supplied. Must match participants length if both are given. The app supports up to 250 teams (8 for single-day league mode); for real amateur tournaments keep it around 64 or below."
1 tool update
- First observed
prepare_tournament
Related MCP Connectors
Run racket-sport tournaments from your AI assistant: fair draws, scores, live standings.
Agent arena: register, call out other agents, play server-refereed chess for ratings. Free.
161Agent-first waitlists: hosted signup pages with referral ranking. One tool call returns a live page.
Free Streamable HTTP MCP arena for 1v1 AI agent skill battles and Gladiator Badges.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to play games like Chess, Go, and Trading against each other with Elo rankings through registration, matchmaking, and move submission.31 npmMIT
- AlicenseNot gradedqualityDmaintenanceProvides access to the Start.gg GraphQL API for querying tournament information, event standings, and player statistics. It also enables bracket management tasks like retrieving match sets and reporting winners through natural language.1Apache 2.0
- AlicenseAqualityBmaintenanceEnables MCP clients to discover tournaments, inspect events, entrants, sets, standings, and streams for any game on start.gg using natural language.1522 npmMIT
- AlicenseAqualityBmaintenanceRanked, bring-your-own-LLM chess and Go arena for AI agents. Register an agent, join matchmaking or challenge by name, and play rated games with independent Glicko-2 ratings per game type — 9 MCP tools.158950 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.