# io.github.CloudCorpRecords/banditkeep (npm · @reneturcios/banditkeep)

Decision memory for agents: bandit campaigns that learn which action works in which context.

- Trust score: 69/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `@reneturcios/banditkeep`: 69/100 (this document), [markdown](https://verifymcp.io/servers/cloudcorprecords-banditkeep/reneturcios-banditkeep.md), [page](https://verifymcp.io/servers/cloudcorprecords-banditkeep/reneturcios-banditkeep)
- oci · `ghcr.io/cloudcorprecords/banditkeep`: 40/100, [markdown](https://verifymcp.io/servers/cloudcorprecords-banditkeep/ghcr-io-cloudcorprecords-banditkeep.md), [page](https://verifymcp.io/servers/cloudcorprecords-banditkeep/ghcr-io-cloudcorprecords-banditkeep)

## Channel facts

- Registry: `npm`
- Package: `@reneturcios/banditkeep`
- Version: `0.1.0`
- Transport: `stdio`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 30 of 92 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 1 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 69/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 770 tokens (~64/item across 12 items; 12 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**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.

## Install

### How do I install the io.github.CloudCorpRecords/banditkeep MCP server?

io.github.CloudCorpRecords/banditkeep runs locally as an npm package, launched with npx -y @reneturcios/banditkeep. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add cloudcorprecords-banditkeep -- npx -y @reneturcios/banditkeep
```

### Cursor

```json
{
  "mcpServers": {
    "cloudcorprecords-banditkeep": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/banditkeep"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "cloudcorprecords-banditkeep": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/banditkeep"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add cloudcorprecords-banditkeep -- npx -y @reneturcios/banditkeep
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "cloudcorprecords-banditkeep": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@reneturcios/banditkeep"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add cloudcorprecords-banditkeep --command npx --arg -y --arg @reneturcios/banditkeep
```

### Hermes

```yaml
mcp_servers:
  cloudcorprecords-banditkeep:
    command: "npx"
    args: ["-y", "@reneturcios/banditkeep"]
```

### Netclaw

```json
{
  "McpServers": {
    "cloudcorprecords-banditkeep": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@reneturcios/banditkeep"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add cloudcorprecords-banditkeep -t stdio -c npx -a -y @reneturcios/banditkeep
```

### Other

```json
{
  "mcpServers": {
    "cloudcorprecords-banditkeep": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/banditkeep"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 69)

First indexed and scored.

## MCP tools (12)

### `create_campaign` (~171 tokens)

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.

Input parameters:

- `algorithm` (string): Algorithm to use.
- `alpha` (number): Alpha parameter for the algorithm.
- `arms` (array, required): Array of string values for this parameter (optional).
- `budgets` (array): Budget allocation per arm.
- `campaign_id` (string, required): 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).

### `list_campaigns` (~31 tokens)

List all active campaigns (shows algorithm and alpha) — useful to check what exists before calling get_intuition.

### `campaign_diagnostics` (~55 tokens)

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.

Input parameters:

- `campaign_id` (string, required): Identifier of the campaign.

### `campaign_report` (~44 tokens)

Business-level convergence report. Tells you whether the campaign has statistically converged and which arm is winning with confidence intervals.

Input parameters:

- `campaign_id` (string, required): Identifier of the campaign.

### `get_intuition` (~115 tokens)

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.

Input parameters:

- `campaign_id` (string, required): Identifier of the campaign.
- `context` (required): 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).

### `batch_get_intuition` (~43 tokens)

Get decisions for multiple campaigns in a single round-trip. Pass a list of {campaign_id, context} dicts.

Input parameters:

- `predictions` (array, required): Predictions payload.

### `record_outcome` (~53 tokens)

Report whether the chosen action succeeded (1.0) or failed (0.0). Updates the shared model.

Input parameters:

- `interaction_id` (string, required): Identifier of the interaction.
- `reward` (number, required): Reward value.

### `archive_campaign` (~36 tokens)

Soft-delete a campaign. Pauses predictions/rewards but preserves all learned weights.

Input parameters:

- `campaign_id` (string, required): Identifier of the campaign.

### `restore_campaign` (~32 tokens)

Restore an archived campaign to active status with all weights intact.

Input parameters:

- `campaign_id` (string, required): Identifier of the campaign.

### `campaign_budget` (~36 tokens)

Budget spend per resource: consumed, remaining, utilization, shadow price, exhaustion.

Input parameters:

- `campaign_id` (string, required): Identifier of the campaign.

### `add_arm` (~91 tokens)

Add an action to a live campaign, optionally warm-started from existing arms and with budget costs.

Input parameters:

- `arm_id` (string, required): The arm identifier for this call.
- `campaign_id` (string, required): 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).

### `set_arm_status` (~63 tokens)

Pause, retire, or reactivate an action. It keeps everything it learned.

Input parameters:

- `arm_id` (string, required): The arm identifier for this call.
- `campaign_id` (string, required): Identifier of the campaign.
- `status` (string, required): Status filter for this call.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/cloudcorprecords-banditkeep/reneturcios-banditkeep#diagnostics

## Score history

- 2026-11-05: 69
- 2026-11-04: 69

## Common questions

### 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 npm package (@reneturcios/banditkeep).

### Is the io.github.CloudCorpRecords/banditkeep MCP server safe to use?

io.github.CloudCorpRecords/banditkeep scores 69 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. 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.

## Links

- npm package: https://www.npmjs.com/package/@reneturcios/banditkeep
- Socket report: https://socket.dev/npm/package/@reneturcios/banditkeep
- Repository: https://github.com/CloudCorpRecords/banditkeep
- Changelog RSS feed: https://verifymcp.io/servers/cloudcorprecords-banditkeep/reneturcios-banditkeep.xml
- Changelog JSON feed: https://verifymcp.io/servers/cloudcorprecords-banditkeep/reneturcios-banditkeep.json
- HTML version of this page: https://verifymcp.io/servers/cloudcorprecords-banditkeep/reneturcios-banditkeep