io.github.CloudCorpRecords/banditkeep
OCI · GHCR.IO/CLOUDCORPRECORDS/BANDITKEEP · 2 COMPONENTS
Decision memory for agents: bandit campaigns that learn which action works in which context.
Available components
Last scanned (29 minutes ago)
Scores higher than 42% of OCI servers
Category AI and Machine Learning
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security0
- No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.Unverified
- Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.Unverified
- Install-script risk not yet assessed.Unverified
- Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.Unverified
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 1 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability69
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 770 tokens (~64/item across 12 items; 12 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management3
- Stability observed for 1 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 5 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 0 to 3. That category is still filling its 30-day observation window: 0 days of observed history at the previous scan, 1 at this one. The score rises as the window fills, whether or not the server changes.
- 4 Nov 26 39
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed oci/ghcr.io/cloudcorprecords/banditkeep@0.1.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | oci |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
add_arm ~91
Add an action to a live campaign, optionally warm-started from existing arms and with budget costs.
| Name | Type | Req | Description |
|---|---|---|---|
| arm_id | string | yes | The arm identifier for this call. |
| campaign_id | string | yes | Identifier of the campaign. |
| costs | object | – | Costs payload. |
| group | string | – | Group identifier or name. |
| warm_start | array | – | Array of string values for this parameter (optional). |
No output schema declared.
No examples provided.
archive_campaign ~36
Soft-delete a campaign. Pauses predictions/rewards but preserves all learned weights.
| Name | Type | Req | Description |
|---|---|---|---|
| campaign_id | string | yes | Identifier of the campaign. |
No output schema declared.
No examples provided.
batch_get_intuition ~43
Get decisions for multiple campaigns in a single round-trip. Pass a list of {campaign_id, context} dicts.
| Name | Type | Req | Description |
|---|---|---|---|
| predictions | array | yes | Predictions payload. |
No output schema declared.
No examples provided.
campaign_budget ~36
Budget spend per resource: consumed, remaining, utilization, shadow price, exhaustion.
| Name | Type | Req | Description |
|---|---|---|---|
| campaign_id | string | yes | Identifier of the campaign. |
No output schema declared.
No examples provided.
campaign_diagnostics ~55
Inspect 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.
| Name | Type | Req | Description |
|---|---|---|---|
| campaign_id | string | yes | Identifier of the campaign. |
No output schema declared.
No examples provided.
campaign_report ~44
Business-level convergence report. Tells you whether the campaign has statistically converged and which arm is winning with confidence intervals.
| Name | Type | Req | Description |
|---|---|---|---|
| campaign_id | string | yes | Identifier of the campaign. |
No output schema declared.
No examples provided.
create_campaign ~171
Create a new decision campaign. Accepts algorithm ("linucb" or "thompson_sampling"), alpha, and optional budgets for actions that cost something limited. Use Thompson Sampling for natural Bayesian exploration with no tuning needed.
| Name | Type | Req | Description |
|---|---|---|---|
| algorithm | string | – | Algorithm to use. |
| alpha | number | – | Alpha parameter for the algorithm. |
| arms | array | yes | Array of string values for this parameter (optional). |
| budgets | array | – | Budget allocation per arm. |
| campaign_id | string | yes | Identifier of the campaign. |
| decay_half_life_hours | number | – | Decay half-life in hours. |
| feature_dim | integer | – | Feature dimension size. |
| features | array | – | Array of string values for this parameter (optional). |
| metadata | object | – | Metadata for this call (optional). |
No output schema declared.
No examples provided.
get_intuition ~115
Ask BanditDB which arm to pick for a given context. Optional exclude_arms / eligible_arms narrow the choice for this request only. Returns the arm and an interaction_id to save.
| Name | Type | Req | Description |
|---|---|---|---|
| campaign_id | string | yes | Identifier of the campaign. |
| context | – | yes | Context for the decision: an object of features or an array of values. |
| eligible_arms | array | – | Array of string values for this parameter (optional). |
| exclude_arms | array | – | Array of string values for this parameter (optional). |
No output schema declared.
No examples provided.
list_campaigns ~31
List all active campaigns (shows algorithm and alpha) — useful to check what exists before calling get_intuition.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
record_outcome ~53
Report whether the chosen action succeeded (1.0) or failed (0.0). Updates the shared model.
| Name | Type | Req | Description |
|---|---|---|---|
| interaction_id | string | yes | Identifier of the interaction. |
| reward | number | yes | Reward value. |
No output schema declared.
No examples provided.
restore_campaign ~32
Restore an archived campaign to active status with all weights intact.
| Name | Type | Req | Description |
|---|---|---|---|
| campaign_id | string | yes | Identifier of the campaign. |
No output schema declared.
No examples provided.
set_arm_status ~63
Pause, retire, or reactivate an action. It keeps everything it learned.
| Name | Type | Req | Description |
|---|---|---|---|
| arm_id | string | yes | The arm identifier for this call. |
| campaign_id | string | yes | Identifier of the campaign. |
| status | string | yes | Status filter for this call. |
No output schema declared.
No examples provided.
How do I install the io.github.CloudCorpRecords/banditkeep MCP server?
io.github.CloudCorpRecords/banditkeep runs locally as a container image, launched with docker run --rm -i ghcr.io/cloudcorprecords/banditkeep:0.1.0. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.
oci · ghcr.io/cloudcorprecords/banditkeep
claude mcp add cloudcorprecords-banditkeep -- docker run --rm -i ghcr.io/cloudcorprecords/banditkeep:0.1.0
What is the io.github.CloudCorpRecords/banditkeep MCP server?
io.github.CloudCorpRecords/banditkeep is an MCP server listed in the public MCP registry as io.github.CloudCorpRecords/banditkeep. Decision memory for agents: bandit campaigns that learn which action works in which context. This page covers its container image (ghcr.io/cloudcorprecords/banditkeep).
Is the io.github.CloudCorpRecords/banditkeep MCP server safe to use?
io.github.CloudCorpRecords/banditkeep scores 40 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the io.github.CloudCorpRecords/banditkeep MCP server expose?
io.github.CloudCorpRecords/banditkeep exposes 12 tools: create_campaign, list_campaigns, campaign_diagnostics, campaign_report, get_intuition, and 7 more. Their descriptions and schemas cost roughly 770 tokens of context every time the server is loaded.
Is the io.github.CloudCorpRecords/banditkeep MCP server still maintained?
io.github.CloudCorpRecords/banditkeep is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the io.github.CloudCorpRecords/banditkeep MCP server under?
io.github.CloudCorpRecords/banditkeep declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.