About BanditDB
BanditDB is an MCP server published by dynamicpricing-ai in the Data category: persistent decision memory for agents — learns which action works in which context.
Recent commit activity is the strongest signal that reported issues will get attention.
Install
uvx banditdb-pythonpip install banditdb-pythonThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (9)
archive_campaignSoft-delete a campaign. Pauses predictions/rewards but preserves all learned weights.
Parameters not published.
batch_get_intuitionGet decisions for multiple campaigns in a single round-trip. Pass a list of `{campaign_id, context}` dicts.
Parameters not published.
campaign_diagnosticsInspect per-arm learning state: `theta_norm`, prediction counts, reward rates, and entropy health. Use when a campaign doesn't seem to be learning or one arm is dominating.
Parameters not published.
campaign_reportBusiness-level convergence report. Tells you whether the campaign has statistically converged and which arm is winning with confidence intervals.
Parameters not published.
create_campaignCreate a new decision campaign. Accepts `algorithm` (`"linucb"` or `"thompson_sampling"`) and `alpha`. Use Thompson Sampling for natural Bayesian exploration with no tuning needed.
Parameters not published.
get_intuitionAsk BanditDB which arm to pick for a given context. Returns the arm and an `interaction_id` to save.
Parameters not published.
list_campaignsList all active campaigns (shows `algorithm` and `alpha`) — useful to check what exists before calling `get_intuition`.
Parameters not published.
record_outcomeReport whether the chosen action succeeded (1.0) or failed (0.0). Updates the shared model.
Parameters not published.
restore_campaignRestore an archived campaign to active status with all weights intact.
Parameters not published.
Ask AI
Ask AI about BanditDB
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.