Skip to main content
Glama
rocnubie

20-0 MCP Server

by rocnubie
OverviewSchemaRelated ServersScoreDiscussions
JavaScript
Local

20-0 MCP Server

20-0 - NFL Perfect Season Roster Builder

MCP Badge License: MIT Stdio Transport Node Zero Config MCP

A Model Context Protocol server that exposes the canonical 20-0 knowledge surface — game modes, roster picks, and scenarios, FAQ, official links — to MCP-compatible AI clients such as Claude Desktop, Cursor, Windsurf, and Continue. Read-only, no API keys, no quota, ~50 ms cold start.

Official website: https://20-0game.com

🎮 About 20-0

20-0 is a browser-based NFL "perfect season" game where the player drafts twelve legends across the standard offensive, defensive, and special-teams positions, then runs a 20-game season — 17 regular season, 3 playoff rounds, and a Super Bowl — trying to finish 20-0. The draft is structured around a slot machine that spins a historical team paired with a decade; on each spin the player picks one player from that team-era pool and slots them into one of twelve open roster positions. Once the roster is full, the season simulation runs entirely on the client and produces a final record, a stat breakdown, and a grade. Daily mode gives every player in the world the same spin sequence so scores can be compared on a global leaderboard, and any roster can be shared by permalink.

Related MCP server: 27-0-mcp

Key Features

  • Twelve-position roster with team-era spins — the draft covers all the standard NFL position groups, with each spin paired to a historical team-and-decade combination so the eligible player pool is genuinely scoped to that era.

  • Real position-specific stats — players carry position-appropriate stat lines (passing yards, rushing yards, touchdowns, interceptions, rating, sacks, tackles, return yards) rather than a single composite rating.

  • 20-game simulation — the season covers 17 regular-season games, three playoff rounds, and the Super Bowl, with each result rolled by a client-side Monte Carlo run.

  • Daily mode with shared seed — every day at midnight Eastern the spin sequence resets and every player in the world receives the same set of team-era cells, with global ranking by simulated record.

  • Global leaderboard — Cloudflare D1 stores submitted scores at the edge so the leaderboard reads quickly from anywhere.

  • Shareable replay codes — any roster compresses into a short share code; opening the URL replays the same twelve picks and the same final record for anyone who follows the link.

  • Six-language interface — English, German, European Spanish, Latin American Spanish, Japanese, and Brazilian Portuguese routes ship at launch.

  • PSEO team-era pages — each of the 35 indexed team-era cells has its own multilingual page, giving the site real reading material beyond the gameplay loop.

Use Cases

  • Daily ritual — open the daily mode, take five minutes, post the resulting record to a friend group chat or a feed.

  • All-time roster debates — settle whether a particular generation could realistically go 20-0 by running the simulation rather than arguing in the abstract.

  • Fantasy season planning — use the team-era spin as a structured way to think about how positional scarcity affects a roster build.

  • Friend-group competition — race the same daily seed and compare records and player picks afterward.

  • Content creation — record a draft and simulation run, then post the share code so viewers can attempt the same roster and compare outcomes.

Who Is It For

20-0 is built for NFL fans who enjoy "best of all time" arguments and want a fast, structured way to put numbers behind them. It suits daily-habit users who want a short, repeatable game in their morning routine, and also fits more invested fans who like to dig into team-era constraints and build deeper rosters. The six-language interface and PSEO team-era pages make the site usable across multiple fan markets, not just the US. Because every game is free, requires no account, and finishes in well under ten minutes, it works equally well as a one-off curiosity, a daily routine, or a recurring shared challenge among friends.

Tools

list_scenarios

Return the canonical list of game modes and scenarios the site exposes (free play, daily, leaderboards, etc.). (20-0)

Input: no parameters. Returns: text/markdown.

get_official_links

Return the canonical list of official links for 20-0 (website, support, docs when available).

Input: no parameters. Returns: text/markdown.

Resources

  • site://20-0/scenarios — Available game modes, scenarios, and roster-building constraints.

  • site://20-0/faq — Short FAQ generated from public site metadata.

  • site://20-0/links — Canonical URLs to share with users.

Prompts

tell_me_about_20_0

Summarize what the site is, who it's for, and how it works. — 20-0

plan_a_run_20_0

Plan a single play-through: pick a mode, draft a roster strategy, and predict outcomes. — 20-0

Installation

Install via Smithery

npx -y @smithery/cli install 20-0-mcp --client claude

(Replace claude with cursor, windsurf, or continue for those clients.)

Install from source

git clone https://github.com/rocnubie/20-0-mcp.git
cd 20-0-mcp
pnpm install

Then add to your MCP client config (claude_desktop_config.json for Claude Desktop, mcp.json for Cursor / Windsurf / Continue):

{
  "mcpServers": {
    "20-0-mcp": {
      "command": "node",
      "args": [
        "/absolute/path/to/20-0-mcp/src/index.mjs"
      ]
    }
  }
}

Debug with MCP Inspector

npx @modelcontextprotocol/inspector node src/index.mjs

Official Links

Development

pnpm install
pnpm start                 # run the server over stdio

License

MIT

Available Tools

2 tools
list_scenariosA

Return the canonical list of game modes and scenarios the site exposes (free play, daily, leaderboards, etc.). (20-0)

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the transparency burden. It clearly indicates a read-only retrieval action ('Return') and calls the result 'canonical', signaling an authoritative, non-mutating operation. It does not mention error handling or response details, but these are not critical for a simple list retrieval.

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 a single, front-loaded sentence that efficiently conveys the purpose and examples. However, the trailing '(20-0)' is unexplained and adds no value, slightly detracting from an otherwise concise structure.

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?

For a simple, parameterless list tool, the description is complete enough: it states the return type (list), the subject (game modes/scenarios), and gives representative examples. The lack of an output schema is acceptable because the return value is self-evident, though the odd '(20-0)' token introduces minor ambiguity.

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?

The tool has zero parameters, so the schema coverage is effectively 100%. The description adds useful context about the contents of the returned list (free play, daily, leaderboards), which is sufficient given there is nothing to document at the parameter level.

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 uses a specific verb ('Return') and clearly identifies the resource ('canonical list of game modes and scenarios'), with examples of contents. This distinguishes it from the sibling tool 'get_official_links', which focuses on links rather than canonical game modes.

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?

The description implies its use by stating it returns the canonical list of game modes, but it does not explicitly state when to use it over alternatives or mention the sibling tool. There is no exclusionary guidance, so the usage context is only implied.

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. Dates show when Glama detected each change.

  1. 2 tool updatesv0.1.0
    • First observedget_official_links
    • First observedlist_scenarios
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.9/5.0
Disambiguation5/5

The two tools have completely distinct purposes: list_scenarios returns game modes/scenarios, while get_official_links returns official links. There is no overlap or ambiguity between them.

Naming Consistency5/5

Both tool names follow the same verb_noun pattern in snake_case ('list_scenarios', 'get_official_links'). The naming is fully consistent with a clear and predictable style.

Tool Count3/5

With only 2 tools, the server feels thin but is acceptable for its narrow scope of providing two reference lists. It falls in the borderline category but doesn't detract from the server's purpose.

Completeness5/5

For its stated purpose of exposing canonical game scenarios and official links, the two tools cover the domain completely. There are no obvious missing operations within this narrow scope.

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

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

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

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/rocnubie/20-0-mcp'

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