cfb-recruiting-mcp
Diagnoses and fixes CFB 27 dynasty recruiting by editing the save file to remove low-star recruit bloat, ensuring top prospects receive scholarship offers.
README
cfb-recruiting-mcp
An MCP (Model Context Protocol) server that diagnoses and fixes CFB 27 dynasty recruiting by editing the dynasty save. It targets the community's biggest recruiting complaint: the game floods the class with 1–2 star recruits, so a huge share of real 4–5 star prospects never get scholarship offers, never sign, and disappear.
The reverse-engineered recruiting data model is baked into the tools, so any model — not just a top-tier one — can run the whole workflow by calling a few high-level tools. It does the table joins, the star-by-signing math, and the pool edits for you.
┌────────────┐ MCP (stdio) ┌───────────────────┐ ┌──────────────────┐
│ LLM client │ ◄─────────────► │ cfb-recruiting-mcp │ ◄────► │ madden-franchise │ ◄── DYNASTY-* save
└────────────┘ └───────────────────┘ └──────────────────┘
What it found on a real save (verified)
Running recruiting_diagnose on a real dynasty reproduced the complaint exactly:
- 3,764 high-school recruits; 55% of them 1–2 star — massive pool bloat.
- 45% of 4-star recruits unsigned (195 of 430). Even 12% of 5-stars unsigned.
- 66 unsigned 4–5 star recruits with ZERO scholarship offers — including the #5 recruit in the country with no offers. These never sign and vanish.
Tools
- recruiting_open
{ file_path }— open a DYNASTY-* save (full CFB 27 schema applied automatically). - recruiting_diagnose
{ file_path }— full pool health report: star distribution, signed-vs-unsigned per star tier, unsigned recruits with zero offers, and a plain-English interpretation. Read-only. - recruiting_list_recruits
{ file_path, stars?, signed?, zero_offers_only? }— drill into a specific cohort (e.g. unsigned 4–5 stars). Read-only. - recruiting_prune_low_stars
{ file_path, stars?, dry_run }— remove low-star recruits (default 1–2 star, HS only) to unclog the pool. Dry-run by default. - recruiting_save
{ file_path }— write edits to disk (timestamped backup). - recruiting_close
{ file_path }.
Setup
# alongside a clone of bep713/madden-franchise (this depends on it via file:)
npm install
npm run build
Register with an MCP client (e.g. Claude Code .mcp.json):
{
"mcpServers": {
"cfb-recruiting": { "command": "node", "args": ["<path>/cfb-recruiting-mcp/dist/index.js"] }
}
}
Important: what this can and cannot do
- The recruiting AI/engine is compiled into the game — not moddable. This tool changes the save-file data the AI works on (the recruit pool), not its behavior. Fewer junk recruits ⇒ the AI spreads itself less thin.
- Every change is a save edit with an automatic backup. Verify results
in-game and restore the
.backup-*file if anything looks wrong. recruiting_prune_low_starsis experimental: it removes recruits by setting their stage toInvalidand burying rank/offers. Whether that fully clears them from in-game boards needs playtesting — feedback welcome.
Credits
Built on bep713/madden-franchise. Full CFB 27 schema (major 809) extraction method by brooksg357-a11y/cfb27-dynasty-modding. Part of a free community modding suite by @RoamingAnalyst.
License
MIT.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.