widescreen-research: Command for Claude Code

.claude/commands/games/mcp-server-implementation-game.md

mcp-server-implementation-game is a command for Claude Code from glassBead-tc/widescreen-research. It costs 0 tokens per session (1,577 once invoked), scanned A, original, MIT.

A command for building and validating a new MCP server from a written specification. It covers the server's tools, errors, security, testing workflow, and registration.

In plain words
What is it for?
Use it to implement a new MCP server, connect it to a registry, add instrumentation, and test each exposed capability.
Why use it?
It gives a defined process for taking an MCP server from an initial specification through implementation and validation.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is glassBead-tc/widescreen-research's own configuration. It tells Claude Code how to work on widescreen-research itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything widescreen-research configures →

Reuse

Borrowing it

Nothing to install: this file belongs to glassBead-tc/widescreen-research. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/glassBead-tc/widescreen-research/main/.claude/commands/games/mcp-server-implementation-game.md
Clone the repo
git clone --depth 1 https://github.com/glassBead-tc/widescreen-research

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mcp-server-implementation-game

README.md
[![agentmods](https://agentmods.dev/badge/commands/glassbead-tc/widescreen-research/mcp-server-implementation-game.svg)](https://agentmods.dev/commands/glassbead-tc/widescreen-research/mcp-server-implementation-game)
Your own site
<a href="https://agentmods.dev/commands/glassbead-tc/widescreen-research/mcp-server-implementation-game"><img src="https://agentmods.dev/badge/commands/glassbead-tc/widescreen-research/mcp-server-implementation-game.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,577 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01577
Opus 5 $0.00000 $0.00788
Sonnet 5 $0.00000 $0.00315
Haiku 4.5 $0.00000 $0.00158

Measured 7d ago against content hash 16502e4995f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mcp-server-implementation-game scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/games/mcp-server-implementation-game.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/mcp-server-implementation-game

Implement and validate a new MCP server end-to-end with instrumentation, registry integration, and a first-class dogfooding workflow that exercises every exposed capability through the agent.

Usage

/mcp-server-implementation-game $ARGUMENTS [ship_deadline] [risk_level] [transport] [registry_visibility]

Arguments

  • $ARGUMENTS (required): High-information server specification (PRD/RFC/URL/brief); see Variables
  • ship_deadline (optional): ISO 8601 deadline (default: 1 week from now)
  • risk_level (optional): "low" | "medium" | "high" (default: "medium")
  • transport (optional): "stdio" | "shttp" (default: "stdio")
  • registry_visibility (optional): "local" | "team" | "public" (default: "local")

Variables

  • SPEC_DOCUMENT: $ARGUMENTS (prewritten specification document)
    • Must include: tool/resource schemas, prompts/models (if any), auth/secret handling, error taxonomy, retries/timeouts, perf goals, observability, rollout
  • SERVER_ID: derived from spec first line, slugged
  • TRANSPORT: stdio/shttp per argument
  • REGISTRY: where to register (local/team/public)

Algorithm

Phase 0: Initialize Server Game Space

mkdir -p .mcp-server-game/{state,artifacts,checks,logs}

cat > .mcp-server-game/state.json << EOF
{
  "server_id": "$SERVER_ID",
  "transport": "$TRANSPORT",
  "registry_visibility": "$REGISTRY",
  "deadline": "$SHIP_DEADLINE",
  "risk_level": "$RISK_LEVEL",
  "phase": 0,
  "budgets": { "error_budget": 0.02, "p95_latency_ms": 250 },
  "instrumentation": { "metrics": true, "events": true, "traces": true },
  "connectivity": { "configured": false, "verified": false },
  "dogfood": { "planned": false, "executed": false, "results_path": null }
}
EOF

# Persist raw spec
cat > .mcp-server-game/spec.raw.txt << 'EOF'
$ARGUMENTS
EOF

Phase 1: Readiness Gate (Spec-Provided Contracts)

cat > .mcp-server-game/checks/readiness.json << 'EOF'
{
  "contracts": [
    "Spec provides tool schemas (names, params, result types)",
    "Spec provides resource schemas (uris, mime types, metadata)",
    "Spec provides error taxonomy + retry/timeout strategy",
    "Spec documents auth/secret handling",
    "Transport selected (stdio/shttp) with bootstrap",
    "Observability plan (metrics/events/traces) present in spec"
  ],
  "registry": [
    "Server metadata prepared for registry",
    "Visibility chosen (local/team/public)"
  ]
}
EOF

echo "✅ Readiness checklist created"

Read the full file on GitHub · 204 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 204 lines · 0 tokens per session scan A 16502e4995f8

Subscribe to this mod's changes

mcp-server-implementation-game is a command published in the GitHub repository glassBead-tc/widescreen-research (6 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,577 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.