# GhostPaw Codex (npm · @ghostpaw/codex)

Local belief and memory engine with evidence, certainty, and honest revision history.

- Trust score: 49/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-24

## Components

- npm · `@ghostpaw/codex`: 49/100 (this document), [markdown](https://verifymcp.io/servers/ghostpawjs-codex/ghostpaw-codex.md), [page](https://verifymcp.io/servers/ghostpawjs-codex/ghostpaw-codex)

## Channel facts

- Registry: `npm`
- Package: `@ghostpaw/codex`
- Version: `0.3.2`
- 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 2026-10-24.

- **Supply Chain Security**: 13/100
  - Malware scan not yet available for this package.
  - Known CVEs could not be checked: the version this server declares is not published in its registry.
  - No install/post-install scripts declared.
  - Dependency health could not be checked: the version this server declares is not published in its registry.
- **Provenance & Transparency**: 71/100
  - Repository check failed: the declared repository URL redirects; it must resolve directly.
  - Cryptographically verified build provenance (signed, bound to GhostPawJS/codex).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 0 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 72/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1118 tokens (~159/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params.
  - 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 7 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (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 GhostPaw Codex MCP server?

GhostPaw Codex runs locally as an npm package, launched with npx -y @ghostpaw/codex. 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 ghostpawjs-codex -- npx -y @ghostpaw/codex
```

### Cursor

```json
{
  "mcpServers": {
    "ghostpawjs-codex": {
      "command": "npx",
      "args": [
        "-y",
        "@ghostpaw/codex"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ghostpawjs-codex": {
      "command": "npx",
      "args": [
        "-y",
        "@ghostpaw/codex"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add ghostpawjs-codex -- npx -y @ghostpaw/codex
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add ghostpawjs-codex --command npx --arg -y --arg @ghostpaw/codex
```

### Hermes

```yaml
mcp_servers:
  ghostpawjs-codex:
    command: "npx"
    args: ["-y", "@ghostpaw/codex"]
```

### Netclaw

```json
{
  "McpServers": {
    "ghostpawjs-codex": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@ghostpaw/codex"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add ghostpawjs-codex -t stdio -c npx -a -y @ghostpaw/codex
```

### Other

```json
{
  "mcpServers": {
    "ghostpawjs-codex": {
      "command": "npx",
      "args": [
        "-y",
        "@ghostpaw/codex"
      ]
    }
  }
}
```

## 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.

### 2026-10-24 (score 49)

First indexed and scored.

## MCP tools (7)

### `search_codex` (~133 tokens)

Search active beliefs by natural language query. Returns ranked matches with recall scores and transparency metadata.

Use when: Use this to find beliefs about a topic before acting on them. Always search before creating a new belief to avoid duplicates.
Not for: Do not use this for browsing all beliefs — use review_codex with the status or flags view instead.

Input parameters:

- `category` (string): Optional category filter.
- `limit` (integer): Maximum number of results.
- `minScore` (number): Minimum recall score threshold.
- `query` (string, required): Free-form natural language query.
- `source` (string): Optional source filter.

### `review_codex` (~154 tokens)

Load a codex review surface: flags for beliefs needing attention, status for portfolio health, log for recent activity, or trends for time-based patterns.

Use when: Use this when you need an overview of the codex state rather than a specific belief. Start with flags for maintenance, status for a dashboard, or log for recent changes.
Not for: Do not use this to find a specific belief by topic — use search_codex instead. Do not use this to inspect one belief deeply — use inspect_codex_item.

Input parameters:

- `limit` (integer): Maximum entries for the log view.
- `now` (integer): Optional timestamp override for freshness computation.
- `view` (string, required): Which codex review surface to load.

### `inspect_codex_item` (~113 tokens)

Inspect one belief in full detail: certainty, freshness, strength, source, category, lineage chain, proximity to similar beliefs, and version diff when applicable.

Use when: Use this after finding a belief through search_codex or review_codex to understand it deeply before deciding whether to confirm, correct, or forget it.
Not for: Do not use this for bulk browsing — use review_codex for lists. Do not call this without a specific belief id.

Input parameters:

- `beliefId` (integer, required): Belief identifier.

### `remember_belief` (~156 tokens)

Create a new belief from a claim, source, and category. Automatically detects nearby beliefs for duplicate awareness.

Use when: Use this when a new proposition should enter the codex. Always search first to check whether the belief already exists — prefer confirming or correcting an existing belief over creating a duplicate.
Not for: Do not use this to update an existing belief. Use revise_belief with the correct, confirm, or merge action instead.

Input parameters:

- `category` (string, required): What kind of claim.
- `certainty` (number): Optional initial certainty 0–1.
- `claim` (string, required): The proposition being asserted.
- `provenance` (string): Optional origin reference.
- `source` (string, required): Where the belief came from.

### `revise_belief` (~230 tokens)

Revise an existing belief: confirm it still holds, correct it with a new claim, merge multiple beliefs into one, forget it from active recall, or defer its next flag review.

Use when: Use this after inspecting a belief to act on it. Choose the action that matches the situation: confirm for reinforcement, correct for changed understanding, merge for consolidation, forget for removal from active recall, defer for postponing review.
Not for: Do not use this to create a new belief — use remember_belief. Do not use this to permanently delete a belief — use retire_belief.

Input parameters:

- `action` (string, required): Revision action.
- `beliefId` (integer): Single belief id.
- `beliefIds` (array): Belief ids for merge.
- `category` (string): Optional replacement category.
- `certainty` (number): Optional certainty override.
- `claim` (string): Replacement or merged claim.
- `deferredUntil` (integer): Future timestamp for deferred review.
- `source` (string): Optional replacement source.
- `successorId` (integer): Existing active successor belief id.

### `retire_belief` (~110 tokens)

Permanently delete a belief and its entire lineage chain. No trace remains. This is for privacy and hard erasure, not normal revision.

Use when: Use this only for privacy cleanup or hard erasure. The belief and all of its lineage (predecessors and successors) will be destroyed.
Not for: Do not use this for normal belief lifecycle — use revise_belief with the forget action to preserve the audit trail.

Input parameters:

- `beliefId` (integer, required): Belief id to delete.

### `dismiss_proximity` (~123 tokens)

Record that two beliefs are not meaningfully related despite proximity detection. Uses exponential backoff — the pair will resurface less frequently with each dismissal.

Use when: Use this after inspecting two proximate beliefs and determining they are not duplicates or in conflict. The dismissal suppresses the pair in future proximity results.
Not for: Do not use this if the beliefs are genuinely related — instead use revise_belief to merge, correct, or forget one of them.

Input parameters:

- `beliefA` (integer, required): First belief id.
- `beliefB` (integer, required): Second belief id.

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/ghostpawjs-codex/ghostpaw-codex#diagnostics

## Score history

- 2026-10-24: 49

## Common questions

### What is the GhostPaw Codex MCP server?

GhostPaw Codex is an MCP server listed in the public MCP registry as io.github.GhostPawJS/codex. Local belief and memory engine with evidence, certainty, and honest revision history. This page covers its npm package (@ghostpaw/codex).

### Is the GhostPaw Codex MCP server safe to use?

GhostPaw Codex scores 49 out of 100 on VerifyMCP. It declares no install or post-install scripts. Its build provenance is signed and verified. 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 GhostPaw Codex MCP server expose?

GhostPaw Codex exposes 7 tools: search_codex, review_codex, inspect_codex_item, remember_belief, revise_belief, and 2 more. Their descriptions and schemas cost roughly 1,019 tokens of context every time the server is loaded.

### Is the GhostPaw Codex MCP server still maintained?

GhostPaw Codex is still listed as active in the MCP registry. We last reached this channel on 24 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 GhostPaw Codex MCP server under?

GhostPaw Codex 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/@ghostpaw/codex
- Socket report: https://socket.dev/npm/package/@ghostpaw/codex
- Website: https://ghostpaw.dev/agent-memory/
- Changelog RSS feed: https://verifymcp.io/servers/ghostpawjs-codex/ghostpaw-codex.xml
- Changelog JSON feed: https://verifymcp.io/servers/ghostpawjs-codex/ghostpaw-codex.json
- HTML version of this page: https://verifymcp.io/servers/ghostpawjs-codex/ghostpaw-codex