What this kind of tool is for
- Hand your agent a structured way to call a model or an inference API.
- Compare outputs from two different providers on the same prompt.
- Wire retrieval, embeddings, or generation into an existing agent workflow.
How to compare servers like this
- Provider coverage:
- Match the tool's supported providers and models to the ones your project uses.
- Cost exposure:
- Model-backed tools spend real API budget; check how usage and limits are configured.
- Maintenance signal:
- The provider landscape shifts weekly; prefer tools updated within the last few months.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the Brotato Coach MCP server?
Deterministic Brotato theorycrafter MCP server: facts and math, not guesses.
How to install Brotato Coach
Copy-paste configuration for popular MCP clients.
SPUDCOACH_DATAPath to a locally built brotato.json dataset (see README for how to build one — the game data itself is never distributed). Equivalent to the --data CLI flag.
{
"mcpServers": {
"spudcoach": {
"command": "uvx",
"args": [
"spudcoach"
],
"env": {
"SPUDCOACH_DATA": "<YOUR_SPUDCOACH_DATA>"
}
}
}
}Related MCP servers

Darwin RAG
Local-first RAG engine with MCP server for AI agent integration.
Persistent 5-level hierarchical memory for AI agents—survive session boundaries with token-efficient, portable knowledge.

NIM Key Manager
Self-hosted NVIDIA NIM API-key manager with a Claude MCP connector; deploy your own instance.

McpOrchestrator
Route one agent through one MCP server to many, with progressive tool discovery to shrink context.
European business data — French company check, EU VAT validation, legal search.
View repository →
Checks agent traces for evidence-readiness: verifies evidence is present, not that it is true.

