# io.github.ag3ntlab-ai/negbit (npm · negbit-mcp)

Buy negbit's curated, provenance-verified knowledge bundles with your own x402 wallet. Read-only.

- Trust score: 70/100 (medium)
- Change this week: +45
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-04

## Components

- npm · `negbit-mcp`: 70/100 (this document), [markdown](https://verifymcp.io/servers/ag3ntlab-ai-negbit/negbit-mcp.md), [page](https://verifymcp.io/servers/ag3ntlab-ai-negbit/negbit-mcp)

## Channel facts

- Registry: `npm`
- Package: `negbit-mcp`
- 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 2026-08-04.

- **Supply Chain Security**: 83/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known medium-severity CVE affects hono 4.12.33, reached via @modelcontextprotocol/sdk > hono. A fixed version is available.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
- **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 24 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 85/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 598 tokens (~99/item across 6 items; 4 tools + 2 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **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.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add ag3ntlab-ai-negbit -- npx -y negbit-mcp
```

### Codex

```bash
codex mcp add ag3ntlab-ai-negbit -- npx -y negbit-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ag3ntlab-ai-negbit": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "negbit-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ag3ntlab-ai-negbit --command npx --arg -y --arg negbit-mcp
```

### Hermes

```yaml
mcp_servers:
  ag3ntlab-ai-negbit:
    command: "npx"
    args: ["-y", "negbit-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "ag3ntlab-ai-negbit": {
      "command": "npx",
      "args": [
        "-y",
        "negbit-mcp"
      ]
    }
  }
}
```

## 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.

### 2026-08-04 (score 70, +3)

- [security regression] CVE-2026-69207 affects this package: medium
- [security regression] Known CVEs: partial → fail
- [functional improvement] Stability: unverified → 0.30

### 2026-08-03 (score 67, +7)

- [security improvement] Known CVEs: unverified → partial
- [functional improvement] Dependency health: unverified → partial

### 2026-08-02 (score 60, −10)

- [security regression] Known CVEs: partial → unverified
- [functional regression] Dependency health: partial → unverified

### 2026-08-01 (score 70, +35)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-31 (score 35, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-30 (score 53, +28)

- [functional regression] Dependency health: partial → unverified
- [functional improvement] Schema quality: unverified → 100
- [functional improvement] Tool coverage: unverified → 100

### 2026-07-28 (score 25, −28)

- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional improvement] Dependency health: unverified → partial

### 2026-07-27 (score 53)

First indexed and scored.

## MCP tools (4)

### `search_bundles` (~156 tokens)

Search negbit bundles

Search negbit's live catalog of OKF knowledge bundles. Omit all args to browse the full catalog. `query` matches (case-insensitive substring) the id, title, and pitch. `domain` is an extra keyword narrowing the same text (negbit's catalog has no formal per-bundle domain field — it is treated as an additional filter, not a taxonomy lookup). Returns each match with title, id@version, price (USD + micro-USDC), one-line pitch, short sha256, preview URL, and security verdict.

Input parameters:

- `domain` (string): Extra keyword filter (matched against bundle text; not a formal taxonomy).
- `query` (string): Free-text search over id/title/pitch.

### `get_bundle` (~79 tokens)

Get a bundle record

Return the full live catalog record for one bundle by id (price, sha256, concept/token/file counts, half-life, security scan, preview + purchase URLs, and the authorization brief). 404-safe: an unknown id returns the list of available ids.

Input parameters:

- `id` (string, required): Bundle id, e.g. 'okf-knowledge-format'.

### `get_preview` (~63 tokens)

Read a bundle's free preview

Fetch the free preview text for a bundle (the anti-lemon look-inside: index/README, concept list, structure) so you can judge fit BEFORE paying. Verifies the id exists in the catalog first.

Input parameters:

- `id` (string, required): Bundle id to preview.

### `how_to_buy` (~111 tokens)

How to buy a bundle (x402 contract)

Return the EXACT x402 purchase contract for a bundle, read live from negbit's 402 endpoint: the endpoint URL, network, USDC asset, exact micro-USDC amount, and the seller pay-to address. Explains that YOU pay with your OWN x402-capable client — negbit takes no custody — then verify the returned bytes' sha256 against the catalog and keep the X-Negbit-Receipt for 90-day re-download.

Input parameters:

- `id` (string, required): Bundle id to buy.

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/ag3ntlab-ai-negbit/negbit-mcp#diagnostics

## Score history

- 2026-08-04: 70
- 2026-08-03: 67
- 2026-08-02: 60
- 2026-08-01: 70
- 2026-07-31: 35
- 2026-07-30: 53
- 2026-07-28: 25
- 2026-07-27: 53

## Links

- npm package: https://www.npmjs.com/package/negbit-mcp
- Socket report: https://socket.dev/npm/package/negbit-mcp
- Repository: https://github.com/ag3ntlab-ai/negbit
- Website: https://negbit.com/
- Changelog RSS feed: https://verifymcp.io/servers/ag3ntlab-ai-negbit/negbit-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/ag3ntlab-ai-negbit/negbit-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/ag3ntlab-ai-negbit/negbit-mcp