BodeSim — Analytics engines for humans and AI agents
BodeSim
BodeSim builds advanced simulation platforms that model complex systems — powering predictions, decisions, and autonomous reasoning at scale.
This listing identifies a third-party MCP server. MCPBundles is not affiliated with, sponsored by, or endorsed by the service or its operator unless stated on this page.
This server may ask you to sign in when your AI client connects.
Last probed Nov 3, 2026 · api.bodesim.com
19tools discovered
For AI agents — MCPBundles Directory API
For MCP client apps (human connect):
MCP connect URL: https://api.bodesim.com/mcp
Skill page: https://www.mcpbundles.com/skills/bodesim-mcp-e86f4a2933
Explore capabilities (19)
read 15
other 4
Get
15
Other capabilities
4
Get Todays Games
read
get_todays_games
Get today's schedule with game IDs and tip-off times.
Use this first to discover what games are available today.
The game_id from each result is used as input to predict_game and get_injury_report.
Returns a list of games with home_team, away_team, tip_off_utc, and game_id.
No token cost.
Args:
api_key: User's DunkSim API key (ds_live_...). Optional when connected via the hosted endpoint — the key from your connector URL/headers is used automatically
sport_
Description may be truncated on the public preview.
Get Todays Games — Get today's schedule with game IDs and tip-off times.
Use this first to discover what games are available today.
The game_id from each result is used as input to predict_game and get_injury_report.
Returns a list of games with home_team, away_team, tip_off_utc, and game_id.
No token cost.
Args:
api_key: User's DunkSim API key (ds_live_...). Optional when connected via the hosted endpoint — the key from your connector URL/headers is used automatically
sport_
Predict Game — Run a Monte Carlo simulation of a game and optionally commit an official prediction.
Use get_todays_games first to get valid game_id, team1_id, team2_id, and exact
player_name / team_key strings needed for player_scenarios.
Returns win probabilities, projected scores, and key_factors — a plain-English list
of the top 3 factors that drove the simulation outcome. Narrate these to the user.
If player_scenarios were applied, scenario_summary confirms what was simulated.
co
Get Injury Report — Get current player availability for a specific game (Pro/Premium only).
Call this before predict_game when the user asks about injuries, who's playing,
or wants to know if key players are available.
If the user is on Free tier, returns 403 with upgrade_url — mention it naturally
and suggest upgrading to Pro for injury report access.
Args:
api_key: User's DunkSim API key (ds_live_...). Optional when connected via the hosted endpoint — the key from your connector URL
Get My Predictions — Get the user's prediction history and accuracy stats for the given sport.
Use this when the user asks how they're doing, what their record is,
or wants to review past predictions. Filter by game_date or game_id.
Use game_id to check the user's prediction for a specific game
(e.g. after selecting a played game from get_season_matchups).
Returns total predictions, accuracy percentage, and a list of recent predictions
with outcomes. accuracy_pct is null until at least 5 p
Get My Simulations — Get the user's recent simulation history for the given sport.
Use this when the user asks:
- "Show me my simulations from the past X days"
- "What did I simulate recently?"
- "Show me my last N simulations"
- "Show me my sims for Lakers vs Celtics"
- "What did I sim for today's games?"
Filter options (all optional, combine as needed):
- game_date (YYYY-MM-DD) — sims for a specific date
- team1, team2 — home / away team name filter (e.g. "Lakers", "Celtics")
Get your MCP into directories
A working endpoint is step one. Directory coverage is the coordinated launch across ChatGPT, Claude, Cursor, the MCP Registry, and community indexes.
What is the BodeSim — Analytics engines for humans and AI agents MCP server?
BodeSim builds advanced simulation platforms that model complex systems — powering predictions, decisions, and autonomous reasoning at scale.
How do I connect BodeSim — Analytics engines for humans and AI agents to my AI agent?
Use the MCP endpoint listed on this page in your MCP client configuration. One-click install pills support Claude, Cursor, VS Code, and other hosts. Copy the remote MCP URL if your client needs a manual entry.
Operate this server?
Request removal if you do not want BodeSim — Analytics engines for humans and AI agents listed here, or claim the listing if you want to manage it on MCPBundles.
Operate BodeSim — Analytics engines for humans and AI agents?
This server appears in the MCPBundles directory. Verify you operate it to take over the listing — name, description, logo, contact email, and skill content. We email a 6-digit code to a maintainer address your server publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.
MCPBundles publishes this directory for MCP discovery. Except where we host or operate an offering, third-party services run under their own terms. Product and company names on this page are used in a descriptive, identifying way (including under nominative fair use where applicable); they remain the property of their owners. Nothing here grants you rights in those marks, and nothing here is an offer to sell a third party's services. Terms · Request removal
More in developer tools
Other MCP servers in this category from the directory index
Get My Models — Get the user's saved prediction models for the given sport.
Use this before predict_game when the user references a saved model by name,
e.g. "load the LeBron out model" or "use my Warriors defense model".
Workflow:
1. Call get_my_models to get the list with model IDs
2. Find the model whose name matches what the user described
3. Call predict_game with that model_id
Returns model names, win rates (null until 5+ predictions), and usage counts.
win_rate is the p
Get My Tokens — Get the user's current token balance and recent transaction history.
Token balances are account-wide (not per-sport), so no sport_type param.
Use this when the user asks:
- "How many tokens do I have?"
- "What's my token balance?"
- "Show me my recent token transactions"
- "Did I get tokens for my last correct prediction?"
Returns current balance and last 10 transactions with type, amount, and description.
Does NOT support purchasing tokens — tell the user to
Get Historical Games — Browse historical games available for "What If" simulations.
Use this when the user wants to simulate a past game, explore historical matchups,
or find a specific game from a previous season.
Filter by season (e.g. '2023-24') and/or team name (substring match).
Returns game IDs that can be used with predict_game via schedule_game_id.
Args:
api_key: User's DunkSim API key (ds_live_...). Optional when connected via the hosted endpoint — the key from your connector UR
Get Season Matchups — Find games from the current-season schedule between one or two teams.
One team (team2 omitted): returns that team's full season schedule.
Two teams: returns only head-to-head matchups between team1 and team2.
Optional date_from / date_to narrow results to a date range
(e.g. all Lakers games in November: team1='LAL', date_from='2026-11-01', date_to='2026-11-30').
Each game shows status (1=scheduled, 2=live, 3=final), scores for completed games,
and user_has_simulation /
Get Free Agency Events — Get recent free agency events (signings, trades, releases) for the given sport.
Use this when the user asks about roster moves, free agency, trades,
or wants to simulate the impact of a player changing teams.
Leave official_only=False (the default) to see ALL real moves. `official_only`
is a data-PROVENANCE filter, NOT a "confirmed real" filter: True returns ONLY
events an admin hand-entered and therefore HIDES the auto-detected real league
moves (which are the majority
Get Daily Challenge — Get today's daily challenge — 7 historical games to simulate and match.
Use this when the user asks about the daily challenge, wants to see today's games,
or asks "what's the challenge today?"
Each sport has its own daily challenge. Returns 7 games with team matchups.
Users simulate each game (1 token per sim) and try to predict the correct winner
with a score within +/-5 of the actual result.
Rewards are tiered by attempt number: 1st attempt match = 5 tokens + 10 point
Get Simulation Insights — Compare a simulation's predictions against actual game results.
Returns parameter adjustment suggestions ranked by impact — tells the user
which parameters to tweak and by how much to better match reality.
Requires the game to have actual results (status=final).
No token cost.
Args:
api_key: User's DunkSim API key (ds_live_...). Optional when connected via the hosted endpoint — the key from your connector URL/headers is used automatically
simulation_id: ID o
Get Simulation Detail — Get full simulation detail including projected player props and actual results.
Use this when the user selects a specific past simulation to review in full.
Returns the same format as a simulation run — projected scores, win probabilities,
player props (Premium), and actual game results with player box scores (Premium).
After discovery via get_season_matchups or get_my_simulations, use the
simulation_id to retrieve full detail.
No token cost — this is a retrieval endpo
Get Upcoming Games — Get scheduled games for today plus the next N days from the persistent season schedule.
Use this when the user asks about future games ("what's on this week?",
"when do the Lakers play next?"), not just today.
team filters to a specific team tricode (e.g. "LAL", "BOS", "GSW") —
pass exactly the tricode, not the full team name.
Returns a list of games with game_id (schedule_game_id), tip-off, and team codes.
Pass the returned game_id into predict_game via schedule_game_
Get Games By Date — Get games for a specific calendar date, optionally filtered by status.
Use this to look up games on a specific day — past, present, or future:
- status=1: scheduled (future / not-yet-started)
- status=2: live / in-progress
- status=3: final (past games with actual results)
When the user wants to iterate on a past game (what-if re-simulation),
call this with status=3 to find the game, then get_roster_preview, then
predict_game with player_scenarios.
Args:
Get Roster Preview — Get the enriched roster preview for a game — blended per-player parameters
and base stats, before any overrides or scenarios are applied.
Use this to inspect what the engine "thinks" a player will do before
constructing player_scenarios or override adjustments. Useful when the user
wants to tweak a specific player's parameters by a small amount rather than
applying a preset scenario like "bad_night" or "out".
The returned parameters (scoring_impact, rebounding_impact, e
Preview Sweep — Preview a sensitivity sweep before running it. Free — no tokens deducted.
A sweep varies one parameter across N steps and reports the token cost,
sims per step, and whether the user can afford it. Always call this first
so the user knows what they are about to spend.
Sweep knobs:
- sweep_team: 'team1' or 'team2' — which team owns the swept parameter
- sweep_level: 'player' or 'team'
player: varies a PlayerOverride field (scoring_impact_adj, rebounding_impact_adj
Run Sweep — Execute a sensitivity sweep. Token cost: 1 token per step (max 20 steps).
Always call preview_sweep first to show the user the cost and confirm
before charging tokens. Same parameters as preview_sweep.
include_player_props=true requires Premium — returns 403 with upgrade_url
for Free/Pro users.
Returns one result row per step: step index, swept value, win_pct_team1,
win_pct_team2, predicted_score_team1, predicted_score_team2, and optionally
player_props when includ
Save Model From Simulation — Save a new named prediction model by extracting overrides from an existing simulation.
Use this after the user has iterated on a simulation (player_scenarios,
team adjustments, sweeps) and wants to persist the adjustments as a
reusable named model. Later, predict_game can load it via model_id.
Tier quota: Free gets 3 free saves before 1 token/save; Pro gets 10;
Premium is unlimited. Name must be unique per user per sport.
Args:
api_key: User's DunkSim API key (
How many tools does BodeSim — Analytics engines for humans and AI agents provide?
MCPBundles probed 19 tools on the live server. The tool list on this page reflects what was discovered at the last refresh — connect your client to see the full set available to your session.
What authentication does BodeSim — Analytics engines for humans and AI agents require?
BodeSim — Analytics engines for humans and AI agents may require signing in to the provider before tools can run. Connect through MCPBundles or your MCP client and complete any provider login when prompted.
Don't want this listed?
Request removal from the MCPBundles directory. We stop publishing this listing on mcpbundles.com.
MCPBundles is an independent platform built on the open Model Context Protocol standard. MCPBundles is not affiliated with, sponsored by, or endorsed by Anthropic PBC.