# codexwatch (pypi · codexwatch-cli)

OpenAI Codex usage from your local logs: tokens, API-equivalent cost and plan limits.

- Trust score: 79/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-06

## Components

- pypi · `codexwatch-cli`: 79/100 (this document), [markdown](https://verifymcp.io/servers/psychofict-codexwatch/codexwatch-cli.md), [page](https://verifymcp.io/servers/psychofict-codexwatch/codexwatch-cli)

## Channel facts

- Registry: `pypi`
- Package: `codexwatch-cli`
- Version: `1.0.2`
- 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 2026-11-06.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to psychofict/codexwatch).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 1 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 64/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 367 tokens (~61/item across 6 items; 6 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 7/100
  - Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 83/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 50% 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 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 7 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 codexwatch MCP server?

codexwatch runs locally as a PyPI package, launched with uvx codexwatch-cli mcp. 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 psychofict-codexwatch -- uvx codexwatch-cli mcp
```

### Cursor

```json
{
  "mcpServers": {
    "psychofict-codexwatch": {
      "command": "uvx",
      "args": [
        "codexwatch-cli",
        "mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "psychofict-codexwatch": {
      "command": "uvx",
      "args": [
        "codexwatch-cli",
        "mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add psychofict-codexwatch -- uvx codexwatch-cli mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "psychofict-codexwatch": {
      "type": "local",
      "command": [
        "uvx",
        "codexwatch-cli",
        "mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add psychofict-codexwatch --command uvx --arg codexwatch-cli --arg mcp
```

### Hermes

```yaml
mcp_servers:
  psychofict-codexwatch:
    command: "uvx"
    args: ["codexwatch-cli", "mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "psychofict-codexwatch": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "codexwatch-cli",
        "mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add psychofict-codexwatch -t stdio -c uvx -a codexwatch-cli mcp
```

### Other

```json
{
  "mcpServers": {
    "psychofict-codexwatch": {
      "command": "uvx",
      "args": [
        "codexwatch-cli",
        "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.

### 2026-11-05 (score 79, +1)

- [functional] Package version: 1.0.1 → 1.0.2

### 2026-11-04 (score 78)

First indexed and scored.

## MCP tools (6)

### `usage_summary` (~82 tokens)

Codex token usage and its API-equivalent dollar value for a period: totals, cache hit rate, and the top models and projects. Dollar figures are estimates at OpenAI API prices; tokens of models with no published price are counted separately.

Input parameters:

- `period` (string): today, the last 7 or 30 days, this calendar month, or all history

### `plan_limits` (~70 tokens)

Where the ChatGPT plan's Codex limits stand now: each window's percent used, reset time, burn rate per hour and projected time it fills, read from the newest session log. With codexhop installed, also every saved account's last reading and the account with the most 5-hour room.

### `quota_forensics` (~77 tokens)

What each percentage point of the plan cost in API-equivalent dollars and tokens, per window and per day, plus rises in a window that the local logs cannot explain (usage from another machine, ChatGPT itself or cloud tasks, or a metering change).

Input parameters:

- `window` (string): only windows of this length; both when omitted

### `sessions` (~34 tokens)

The most recent Codex sessions with title, project, models, turns, tokens and dollar value.

Input parameters:

- `limit` (integer)

### `daily` (~32 tokens)

Tokens and API-equivalent dollars per local day, oldest first, with empty days included.

Input parameters:

- `days` (integer)

### `budget_status` (~41 tokens)

The user's codexwatch budgets (dollar, token or plan-window caps) with how much of each is used and whether it is near or over its limit.

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/psychofict-codexwatch/codexwatch-cli#diagnostics

## Score history

- 2026-11-06: 79
- 2026-11-05: 79
- 2026-11-04: 78

## Common questions

### What is the codexwatch MCP server?

codexwatch is an MCP server listed in the public MCP registry as io.github.psychofict/codexwatch. OpenAI Codex usage from your local logs: tokens, API-equivalent cost and plan limits. This page covers its PyPI package (codexwatch-cli).

### Is the codexwatch MCP server safe to use?

codexwatch scores 79 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 6 November 2026. 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 codexwatch MCP server expose?

codexwatch exposes 6 tools: usage_summary, plan_limits, quota_forensics, sessions, daily, budget_status. Their descriptions and schemas cost roughly 336 tokens of context every time the server is loaded.

### Is the codexwatch MCP server still maintained?

codexwatch is still listed as active in the MCP registry. We last reached this channel on 6 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 codexwatch MCP server under?

codexwatch declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the codexwatch MCP server?

VerifyMCP ran 16 checks on codexwatch, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- PyPI project: https://pypi.org/project/codexwatch-cli/
- Socket report: https://socket.dev/pypi/package/codexwatch-cli
- Repository: https://github.com/psychofict/codexwatch
- Changelog RSS feed: https://verifymcp.io/servers/psychofict-codexwatch/codexwatch-cli.xml
- Changelog JSON feed: https://verifymcp.io/servers/psychofict-codexwatch/codexwatch-cli/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/psychofict-codexwatch/codexwatch-cli.json
- HTML version of this page: https://verifymcp.io/servers/psychofict-codexwatch/codexwatch-cli