Categories › AI & Agents › Multi-agent, orchestration & workflows
Free sports slate and matchup research for AI agents over MCP and REST. Research only; 21+.
Remote server: your requests and data go to deepchampai.com. Claude Code: claude mcp add --transport http deepchamp-for-agents https://deepchampai.com/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
get_daily_slate — Games for a sport and Eastern date with start times, status, and plain-language rest and schedule context. Research intelligence (probabilitget_matchup_context — Schedule context for one game: each team's last result, rest, and next game. Facts and our computed context only. Research intelligence (prorequest_capability — Tell us what you need that is missing: a category, sport, market, format and urgency, with an optional short plain-text note. Enumerated fierate_response — Say whether a response was useful, with a reason code, tied to its request id. No free text. Free, never charged, no signup. Research intellcalc_fair_value — No-margin fair probability from one or two of your own prices. Arithmetic on your own numbers only: nothing is stored and no outside data iscalc_parlay — Combined price, and combined probability if you supply yours, for two to twenty legs. Arithmetic on your own numbers only: nothing is storedcalc_best_price — Rank up to 50 prices you supply for the same outcome by payout. Arithmetic on your own numbers only: nothing is stored and no outside data icalc_ev_scan — Expected value per unit for up to 50 price and probability pairs you supply. Arithmetic on your own numbers only: nothing is stored and no oNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.