# Bestie Check (npm · @mybestie/check)

Document reasoning checks: a helicopter view of claims and assumptions before handoff.

- Trust score: 80/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- remote · `www.hirebestie.com`: 39/100, [markdown](https://verifymcp.io/servers/hirebestie-bestie-check/api-check-mcp.md), [page](https://verifymcp.io/servers/hirebestie-bestie-check/api-check-mcp)
- npm · `@mybestie/check`: 80/100 (this document), [markdown](https://verifymcp.io/servers/hirebestie-bestie-check/mybestie-check.md), [page](https://verifymcp.io/servers/hirebestie-bestie-check/mybestie-check)

## Channel facts

- Registry: `npm`
- Package: `@mybestie/check`
- Version: `0.3.0`
- 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 2026-10-23.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **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**: 78/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 1320 tokens (~73/item across 18 items; 18 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 70/100
  - Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 87/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 56% of tool parameters carry a description.
  - Structured output schemas are declared (28% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 19 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.

## Install

### How do I install the Bestie Check MCP server?

Bestie Check runs locally as an npm package, launched with npx -y @mybestie/check. 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 hirebestie-bestie-check -- npx -y @mybestie/check
```

### Cursor

```json
{
  "mcpServers": {
    "hirebestie-bestie-check": {
      "command": "npx",
      "args": [
        "-y",
        "@mybestie/check"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "hirebestie-bestie-check": {
      "command": "npx",
      "args": [
        "-y",
        "@mybestie/check"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add hirebestie-bestie-check -- npx -y @mybestie/check
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "hirebestie-bestie-check": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@mybestie/check"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add hirebestie-bestie-check --command npx --arg -y --arg @mybestie/check
```

### Hermes

```yaml
mcp_servers:
  hirebestie-bestie-check:
    command: "npx"
    args: ["-y", "@mybestie/check"]
```

### Netclaw

```json
{
  "McpServers": {
    "hirebestie-bestie-check": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@mybestie/check"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add hirebestie-bestie-check -t stdio -c npx -a -y @mybestie/check
```

### Other

```json
{
  "mcpServers": {
    "hirebestie-bestie-check": {
      "command": "npx",
      "args": [
        "-y",
        "@mybestie/check"
      ]
    }
  }
}
```

## 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.

### 2026-10-23 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-21 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-19 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-16 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-14 (score 76, +6)

- [functional improvement] Stability: unverified → 0.40

### 2026-10-13 (score 70, 0)

- [functional regression] Security disclosure: unverified → fail

### 2026-10-12 (score 70, 0)

- [functional regression] Security disclosure: fail → unverified

### 2026-10-03 (score 70, +15)

- [security improvement] Malware scan: unverified → pass

## MCP tools (18)

### `inspect_capabilities` (~69 tokens)

Inspect Check capabilities

Read what this Check deployment can do for the caller right now: input formats that are ready (and why others are not), the routed verification profile, presets with the pack stack the server resolves for you, admitted packs, and whether paid execution is available through this client. Call first. Read-only.

### `inspect_packs` (~80 tokens)

List admitted verifier packs

List admitted verifier packs available to the caller. Packs test mechanism-bearing claims — assumptions, warrants, evidence, and rebuttals — not grammar or generic style. Use to choose packRefs before quote_check and verify_deliverable. There is no list_packs tool. Read-only.

Input parameters:

- `query` (string): Optional substring filter over pack display names.

### `prepare_deliverable` (~108 tokens)

Prepare a deliverable (text or URL)

Put pasted text or a public HTTPS URL into Check custody. Ingestion starts, and the server then runs the Claim and Assumption Quick Look automatically. Returns uploadHandleId and preparation state immediately. Do not wait on this call; poll get_preparation. Never send local file bytes through this tool.

Input parameters:

- `text` (string): Pasted source text. Mutually exclusive with url.
- `url` (string): Public HTTPS URL. Mutually exclusive with text. Not a local file.

Output parameters:

- `acceptedMediaTypes` (array)
- `artifactRef` (string)
- `checkId` (string)
- `expiresAt` (string)
- `ingestion` (object)
- `kind` (string)
- `nextAction`
- `partial` (boolean)
- `quickLook` (object)
- `requiredHeaders` (object)
- `retryable` (boolean)
- `uploadHandleId` (string)
- `uploadUrl` (string)
- `warnings` (array)

### `prepare_file_upload` (~98 tokens)

Start a file upload

Create a file-kind Check upload handle and return a signed PUT descriptor including uploadUrl and requiredHeaders. PUT bytes directly to uploadUrl with those headers. Do not send file contents through MCP. After the PUT, call confirm_file_upload.

Input parameters:

- `byteLength` (integer, required)
- `filename` (string, required)
- `mediaType` (string, required)
- `sha256` (string, required): SHA-256 of the exact bytes that will be PUT.

Output parameters:

- `acceptedMediaTypes` (array)
- `artifactRef` (string)
- `checkId` (string)
- `expiresAt` (string)
- `ingestion` (object)
- `kind` (string)
- `nextAction`
- `partial` (boolean)
- `quickLook` (object)
- `requiredHeaders` (object)
- `retryable` (boolean)
- `uploadHandleId` (string)
- `uploadUrl` (string)
- `warnings` (array)

### `confirm_file_upload` (~52 tokens)

Confirm a file upload

Confirm that bytes were PUT to the signed upload URL, then start ingestion (the Quick Look follows automatically). Returns preparation state. Poll get_preparation; do not block.

Input parameters:

- `uploadHandleId` (string, required)

Output parameters:

- `acceptedMediaTypes` (array)
- `artifactRef` (string)
- `checkId` (string)
- `expiresAt` (string)
- `ingestion` (object)
- `kind` (string)
- `nextAction`
- `partial` (boolean)
- `quickLook` (object)
- `requiredHeaders` (object)
- `retryable` (boolean)
- `uploadHandleId` (string)
- `uploadUrl` (string)
- `warnings` (array)

### `get_preparation` (~113 tokens)

Read preparation and Quick Look

Read-only preparation snapshot for an uploadHandleId: ingestion state, the Quick Look operation (progress, claim and assumption counts and previews, graph identity, failed units), partial, warnings, retryable and nextAction. Never starts or retries anything. Poll while nextAction is wait; claim previews appear as work units finish. nextAction review means the Quick Look is done; retry means retry_preparation is available; replace_source means ingestion failed and the source must be prepared again.

Input parameters:

- `uploadHandleId` (string, required)

Output parameters:

- `acceptedMediaTypes` (array)
- `artifactRef` (string)
- `checkId` (string)
- `expiresAt` (string)
- `ingestion` (object)
- `kind` (string)
- `nextAction`
- `partial` (boolean)
- `quickLook` (object)
- `requiredHeaders` (object)
- `retryable` (boolean)
- `uploadHandleId` (string)
- `uploadUrl` (string)
- `warnings` (array)

### `retry_preparation` (~70 tokens)

Retry a failed Quick Look

Explicit write: re-queue the Quick Look for an upload whose last attempt ended incomplete or failed (or completed with failed units), or start it if ingestion is ready and none exists. Refused otherwise. Never call it to poll; use get_preparation.

Input parameters:

- `uploadHandleId` (string, required)

Output parameters:

- `acceptedMediaTypes` (array)
- `artifactRef` (string)
- `checkId` (string)
- `expiresAt` (string)
- `ingestion` (object)
- `kind` (string)
- `nextAction`
- `partial` (boolean)
- `quickLook` (object)
- `requiredHeaders` (object)
- `retryable` (boolean)
- `uploadHandleId` (string)
- `uploadUrl` (string)
- `warnings` (array)

### `get_check` (~35 tokens)

Read a Check run

Read the current status and scorecard for a Check run by checkId.

Input parameters:

- `checkId` (string, required): Durable Check run identity.

### `get_tasks` (~39 tokens)

Read Check progress

Read execution progress (started/completed/failed phases) for a Check run by checkId.

Input parameters:

- `checkId` (string, required): Durable Check run identity.

### `get_findings` (~61 tokens)

Read Check findings

Read findings for a Check run by checkId. Returns locators and disposition summaries on claims, assumptions, warrants, evidence, and rebuttals — not document excerpts.

Input parameters:

- `checkId` (string, required): Durable Check run identity returned by verify_deliverable.

### `get_fix_list` (~82 tokens)

Read what to change

Read what to change in the document for a finished Check run, as a short list and a ready-to-use revision prompt. Same list the Bestie workspace shows. Use it after get_findings when you are going to revise the document, then check the revised document again.

Input parameters:

- `checkId` (string, required): Durable Check run identity returned by verify_deliverable.

### `get_artifacts` (~33 tokens)

Read Check artifacts

Read committed backing artifacts for a Check run by checkId.

Input parameters:

- `checkId` (string, required): Durable Check run identity.

### `get_receipt` (~55 tokens)

Read a Check receipt

Read the execution receipt for a terminal Check run by checkId. Records what argument-structure criteria were tested and what was explicitly not engaged.

Input parameters:

- `checkId` (string, required): Durable Check run identity returned by verify_deliverable.

### `create_ruling` (~96 tokens)

Record a ruling on a finding

Record a human or agent ruling (accept_concern / reject_concern / defer) on a finding or an entire run. Never re-interprets the finding — records a disposition.

Input parameters:

- `checkId` (string, required): Durable Check run identity.
- `evidenceLocators` (array, required)
- `findingId` (string, required)
- `outcome` (string, required)
- `rationale` (string)
- `scope` (string, required)

### `get_diff` (~44 tokens)

Compare a repair with its parent

Compare a repair/rerun's findings against its parent: cleared, persisted, and new findings.

Input parameters:

- `checkId` (string, required): Child Check run to diff against its parent.

### `get_lineage` (~38 tokens)

Read Check lineage

Read the full rerun/repair lineage tree for a Check run.

Input parameters:

- `checkId` (string, required): Any Check run in the lineage chain.

### `export_check` (~42 tokens)

Export a Check run

Export a terminal Check run as json, sarif, or pdf_summary.

Input parameters:

- `checkId` (string, required): Durable Check run identity.
- `format` (string, required)

### `delete_check` (~61 tokens)

Delete a Check run

Permanently delete a Check run and its custody artifacts. Irreversible; denies every subsequent route for this checkId on every surface.

Input parameters:

- `checkId` (string, required): Durable Check run identity. Deletion is irreversible and denies every subsequent route for this checkId.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/hirebestie-bestie-check/mybestie-check#diagnostics

## Score history

- 2026-10-23: 80
- 2026-10-22: 79
- 2026-10-21: 79
- 2026-10-20: 78
- 2026-10-19: 78
- 2026-10-18: 77
- 2026-10-17: 77
- 2026-10-16: 77
- 2026-10-15: 76
- 2026-10-14: 76
- 2026-10-13: 70
- 2026-10-12: 70
- 2026-10-08: 70
- 2026-10-04: 70
- 2026-10-03: 70
- 2026-10-02: 55

## Common questions

### What is the Bestie Check MCP server?

Bestie Check is an MCP server listed in the public MCP registry as io.github.HireBestie/bestie-check. Document reasoning checks: a helicopter view of claims and assumptions before handoff. This page covers its npm package (@mybestie/check).

### Is the Bestie Check MCP server safe to use?

Bestie Check scores 80 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 23 October 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 Bestie Check MCP server expose?

Bestie Check exposes 18 tools: inspect_capabilities, inspect_packs, prepare_deliverable, prepare_file_upload, confirm_file_upload, and 13 more. Their descriptions and schemas cost roughly 1,176 tokens of context every time the server is loaded.

### Is the Bestie Check MCP server still maintained?

Bestie Check is still listed as active in the MCP registry. We last reached this channel on 23 October 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 Bestie Check MCP server under?

Bestie Check 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/@mybestie/check
- Socket report: https://socket.dev/npm/package/@mybestie/check
- Repository: https://github.com/HireBestie/bestie-check
- Website: https://www.hirebestie.com/docs/connect
- Changelog RSS feed: https://verifymcp.io/servers/hirebestie-bestie-check/mybestie-check.xml
- Changelog JSON feed: https://verifymcp.io/servers/hirebestie-bestie-check/mybestie-check.json
- HTML version of this page: https://verifymcp.io/servers/hirebestie-bestie-check/mybestie-check