# io.github.batchwatch/batchwatch-mcp (npm · batchwatch-mcp)

Ask batchwatch whether to batch a job and get the real measured queue evidence, not a guess.

- Trust score: 76/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- npm · `batchwatch-mcp`: 76/100 (this document), [markdown](https://verifymcp.io/servers/batchwatch-batchwatch-mcp/batchwatch-mcp.md), [page](https://verifymcp.io/servers/batchwatch-batchwatch-mcp/batchwatch-mcp)

## Channel facts

- Registry: `npm`
- Package: `batchwatch-mcp`
- Version: `0.1.1`
- 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 2026-09-20.

- **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.
  - 31 of 95 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 19 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 59/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1470 tokens (~245/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 67/100
  - Stability observed for 20 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 89/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 67% 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 6 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 io.github.batchwatch/batchwatch-mcp server?

io.github.batchwatch/batchwatch-mcp runs locally as an npm package, launched with npx -y batchwatch-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 batchwatch-batchwatch-mcp -- npx -y batchwatch-mcp
```

### Cursor

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

### VS Code

```json
{
  "servers": {
    "batchwatch-batchwatch-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "batchwatch-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add batchwatch-batchwatch-mcp -- npx -y batchwatch-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add batchwatch-batchwatch-mcp --command npx --arg -y --arg batchwatch-mcp
```

### Hermes

```yaml
mcp_servers:
  batchwatch-batchwatch-mcp:
    command: "npx"
    args: ["-y", "batchwatch-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "batchwatch-batchwatch-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "batchwatch-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add batchwatch-batchwatch-mcp -t stdio -c npx -a -y batchwatch-mcp
```

### Other

```json
{
  "mcpServers": {
    "batchwatch-batchwatch-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "batchwatch-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.

### 2026-09-20 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-18 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-16 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-14 (score 73, +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.

### 2026-09-12 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-10 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-08 (score 70, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-08-31 (score 66)

First indexed and scored.

## MCP tools (6)

### `should_i_batch` (~366 tokens)

The verdict: given a model and your own max_wait, does the batch queue currently honour it? Returns the batch p50/p90 wait, the sync comparison if known, the cost saving basis, and a graded confidence + why + freshness. It does not decide for you — it reports whether the queue fits YOUR tolerance. batchwatch measures how long jobs ACTUALLY wait in LLM providers' async batch queues. It reports distributions and current conditions, never a point ETA — a personal history of 3-minute medians once produced a 480-minute job, so "your job finishes at 14:32" is a lie the one time it matters. batchwatch does NOT decide for you: you pass your own max_wait and it says whether the queue currently honours it. Every answer carries n (how many measurements), a graded confidence with a plain-English why, a basis naming the evidence, and freshness (how old the newest measurement is). Without an API key the data is delayed, not absent. Absence is reported as absence, never as zero.

Input parameters:

- `input_tokens` (integer): Optional. Prompt tokens, used to compute the cost saving. Omit if unknown — do NOT send 0.
- `max_wait` (string): How long you can tolerate waiting, e.g. "15m", "2h", "24h". This is the whole question — send it.
- `model` (string, required): Exact model name, e.g. "gpt-5.6-sol". Required.
- `output_tokens` (integer): Optional. Completion tokens, or max_tokens as an upper bound.
- `provider` (string): Defaults to openai.
- `risk` (string): Which percentile to judge against. p90 is the cautious planning number.

### `estimate_batchtime` (~244 tokens)

How long is MY job likely to wait? Returns the batch-wait distribution (p50/p90) for the model, with n, confidence and freshness. A distribution, never a single ETA. batchwatch measures how long jobs ACTUALLY wait in LLM providers' async batch queues. It reports distributions and current conditions, never a point ETA — a personal history of 3-minute medians once produced a 480-minute job, so "your job finishes at 14:32" is a lie the one time it matters. batchwatch does NOT decide for you: you pass your own max_wait and it says whether the queue currently honours it. Every answer carries n (how many measurements), a graded confidence with a plain-English why, a basis naming the evidence, and freshness (how old the newest measurement is). Without an API key the data is delayed, not absent. Absence is reported as absence, never as zero.

Input parameters:

- `input_tokens` (integer): Optional. Omit if unknown — do not send 0.
- `model` (string, required): Exact model name. Required.
- `provider` (string)
- `risk` (string)

### `conditions` (~210 tokens)

Current queue conditions for a model right now vs its recent norm — "is it me or them?". Traffic report, not arrival time. Carries n, confidence, freshness. batchwatch measures how long jobs ACTUALLY wait in LLM providers' async batch queues. It reports distributions and current conditions, never a point ETA — a personal history of 3-minute medians once produced a 480-minute job, so "your job finishes at 14:32" is a lie the one time it matters. batchwatch does NOT decide for you: you pass your own max_wait and it says whether the queue currently honours it. Every answer carries n (how many measurements), a graded confidence with a plain-English why, a basis naming the evidence, and freshness (how old the newest measurement is). Without an API key the data is delayed, not absent. Absence is reported as absence, never as zero.

Input parameters:

- `model` (string, required): Exact model name. Required.
- `provider` (string)

### `distribution` (~239 tokens)

The full measured wait distribution for a model + mode over a window. The raw evidence behind the verdict. Returns absence as absence (never zero) when there is no data. batchwatch measures how long jobs ACTUALLY wait in LLM providers' async batch queues. It reports distributions and current conditions, never a point ETA — a personal history of 3-minute medians once produced a 480-minute job, so "your job finishes at 14:32" is a lie the one time it matters. batchwatch does NOT decide for you: you pass your own max_wait and it says whether the queue currently honours it. Every answer carries n (how many measurements), a graded confidence with a plain-English why, a basis naming the evidence, and freshness (how old the newest measurement is). Without an API key the data is delayed, not absent. Absence is reported as absence, never as zero.

Input parameters:

- `mode` (string)
- `model` (string, required): Exact model name. Required.
- `provider` (string)
- `window` (string): Time window, e.g. "30d", "7d". Optional.

### `coverage` (~194 tokens)

Which provider+model combinations batchwatch currently has data for, and how answerable each is (n, contributors, confidence). Call this first if you are unsure whether a model is measured. batchwatch measures how long jobs ACTUALLY wait in LLM providers' async batch queues. It reports distributions and current conditions, never a point ETA — a personal history of 3-minute medians once produced a 480-minute job, so "your job finishes at 14:32" is a lie the one time it matters. batchwatch does NOT decide for you: you pass your own max_wait and it says whether the queue currently honours it. Every answer carries n (how many measurements), a graded confidence with a plain-English why, a basis naming the evidence, and freshness (how old the newest measurement is). Without an API key the data is delayed, not absent. Absence is reported as absence, never as zero.

### `wait` (~217 tokens)

The public "is the queue moving now?" reading for a model (delayed without a key). Lighter than should_i_batch — no max_wait judgement, just the current wait numbers with confidence + freshness. batchwatch measures how long jobs ACTUALLY wait in LLM providers' async batch queues. It reports distributions and current conditions, never a point ETA — a personal history of 3-minute medians once produced a 480-minute job, so "your job finishes at 14:32" is a lie the one time it matters. batchwatch does NOT decide for you: you pass your own max_wait and it says whether the queue currently honours it. Every answer carries n (how many measurements), a graded confidence with a plain-English why, a basis naming the evidence, and freshness (how old the newest measurement is). Without an API key the data is delayed, not absent. Absence is reported as absence, never as zero.

Input parameters:

- `model` (string, required): Exact model name. Required.
- `provider` (string)

## Diagnostics

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

## Score history

- 2026-09-20: 76
- 2026-09-19: 75
- 2026-09-18: 75
- 2026-09-17: 74
- 2026-09-16: 74
- 2026-09-15: 73
- 2026-09-14: 73
- 2026-09-13: 72
- 2026-09-12: 72
- 2026-09-11: 71
- 2026-09-10: 71
- 2026-09-09: 70
- 2026-09-08: 70
- 2026-09-07: 66
- 2026-09-06: 66
- 2026-09-05: 66
- 2026-09-04: 66
- 2026-09-03: 66
- 2026-09-02: 66
- 2026-09-01: 66
- 2026-08-31: 66

## Common questions

### What is the io.github.batchwatch/batchwatch-mcp server?

io.github.batchwatch/batchwatch-mcp is listed in the public MCP registry as io.github.batchwatch/batchwatch-mcp. Ask batchwatch whether to batch a job and get the real measured queue evidence, not a guess. This page covers its npm package (batchwatch-mcp).

### Is the io.github.batchwatch/batchwatch-mcp server safe to use?

io.github.batchwatch/batchwatch-mcp scores 76 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 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.batchwatch/batchwatch-mcp server expose?

io.github.batchwatch/batchwatch-mcp exposes 6 tools: should_i_batch, estimate_batchtime, conditions, distribution, coverage, wait. Their descriptions and schemas cost roughly 1,470 tokens of context every time the server is loaded.

### Is the io.github.batchwatch/batchwatch-mcp server still maintained?

io.github.batchwatch/batchwatch-mcp is still listed as active in the MCP registry. We last reached this channel on 20 September 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.batchwatch/batchwatch-mcp server under?

io.github.batchwatch/batchwatch-mcp 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/batchwatch-mcp
- Socket report: https://socket.dev/npm/package/batchwatch-mcp
- Repository: https://github.com/batchwatch/client
- Website: https://batchwatch.dev/
- Changelog RSS feed: https://verifymcp.io/servers/batchwatch-batchwatch-mcp/batchwatch-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/batchwatch-batchwatch-mcp/batchwatch-mcp.json
- HTML version of this page: https://verifymcp.io/servers/batchwatch-batchwatch-mcp/batchwatch-mcp