# Pitroom (npm · pitroom)

Hands bounded coding work to cheaper worker agents: verified answers, exact diffs, cost receipts.

- Trust score: 90/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-06

## Components

- npm · `pitroom`: 90/100 (this document), [markdown](https://verifymcp.io/servers/atastech-pitroom/pitroom.md), [page](https://verifymcp.io/servers/atastech-pitroom/pitroom)

## Channel facts

- Registry: `npm`
- Package: `pitroom`
- Version: `0.29.0`
- 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 2026-11-06.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 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 ATASTECH/pitroom).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 7 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 74/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1594 tokens (~159/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 80/100
  - Stability observed for 24 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 88/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 65% 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.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the Pitroom MCP server?

Pitroom runs locally as an npm package, launched with npx -y pitroom 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 atastech-pitroom -- npx -y pitroom mcp
```

### Cursor

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

### VS Code

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

### Codex

```bash
codex mcp add atastech-pitroom -- npx -y pitroom mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add atastech-pitroom --command npx --arg -y --arg pitroom --arg mcp
```

### Hermes

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

### Netclaw

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

### Vellum

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

### Other

```json
{
  "mcpServers": {
    "atastech-pitroom": {
      "command": "npx",
      "args": [
        "-y",
        "pitroom",
        "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 90, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 89, +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.

### 2026-11-01 (score 88, +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.

### 2026-10-30 (score 87, +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.

### 2026-10-29 (score 86, 0)

- [security regression] Stability: 0.50 → unverified
- [security regression] Tool safety: pass → unverified
- [functional regression] Capabilities: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional] Package version: 0.27.0 → 0.29.0

### 2026-10-27 (score 86, +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.

### 2026-10-25 (score 85, +1)

- [security regression] Stability: 0.37 → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] Malware scan: pass → unverified
- [functional regression] Capabilities: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional] Package version: 0.25.0 → 0.27.0
- [functional] Package version: 0.25.0 → 0.26.0

### 2026-10-23 (score 84, +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.

## MCP tools (10)

### `pitroom_run` (~488 tokens)

Run a worker

Hand a bounded task to a cheaper worker agent. mode "read" (default): read-only research, an answer with verified file:line references. "isolate": the worker edits a private copy and you get the exact diff (then pitroom_review, pitroom_apply or pitroom_discard). "write": edits the working tree (undo: pitroom_revert). "tasks" or "scopes" run workers in parallel (read or isolate). Returns the report(s) and a receipt (a read question asked before on the same code comes back cached), or "still running" for pitroom_wait. The using-pitroom skill (or prompt) says when and how to delegate. Cancelling the call stops the run.

Input parameters:

- `audit` (boolean): Read: have another worker re-check the answer (each one, with tasks).
- `continue` (string): A finished run to follow up in the same worker session.
- `dir` (string): Project directory (default: the server's).
- `effort` (string): low, medium, high, xhigh.
- `files` (array): Files to attach.
- `fresh` (boolean): Read: ask a worker even if this question was answered on the same code.
- `group` (string): Group name for related runs.
- `inPlace` (boolean): Read: read the directory itself, not a snapshot without secret-looking files.
- `link` (array): Ignored dirs to link into an isolated copy, e.g. ["node_modules"].
- `mode` (string)
- `model` (string): Model for that worker.
- `scopes` (array): Or "task" per part ({scope}): paths that do not overlap, or "src/*/".
- `task` (string): What to do, with the context the worker needs.
- `tasks` (array): Or independent tasks, one worker each.
- `tier` (string): cheap, standard or capable (from the config).
- `verify` (string): Command run afterwards, e.g. "npm test".
- `waitSeconds` (number): Seconds before returning "still running" (default 50, max 540).
- `web` (boolean): Allow web tools.
- `worker` (string): Worker "backend[:model]", e.g. "opencode", "claude:haiku".

### `pitroom_wait` (~61 tokens)

Wait for runs

Wait for runs that came back "still running" and return their reports.

Input parameters:

- `group` (string)
- `runs` (array)
- `waitSeconds` (number): Seconds before returning "still running" (default 50, max 540).

### `pitroom_show` (~61 tokens)

Show a run

A run's report (live progress while it runs); patch: the exact diff; full: the untruncated answer.

Input parameters:

- `full` (boolean)
- `patch` (boolean)
- `run` (string): Run id, or "last".

### `pitroom_info` (~213 tokens)

Pitroom information

Reports, changing nothing. topic: runs (latest runs; running, group), history (search earlier answers before asking again; text, state, model, since, limit), stats (success rate, time, tokens, audits per worker; since), savings (since, perModel), models (a backend's models and costs; worker, all), prices (USD per 1M tokens: the primary the savings are measured against, and each worker in use or the one named; worker), cooldown (rate-limited models being skipped), config, doctor (setup check).

Input parameters:

- `all` (boolean)
- `group` (string)
- `limit` (number)
- `model` (string)
- `perModel` (boolean)
- `running` (boolean)
- `since` (string): 7d, 30d, … or all.
- `state` (string)
- `text` (string)
- `topic` (string, required)
- `worker` (string)

### `pitroom_review` (~179 tokens)

Review a change

A read-only reviewer (another worker by default) judges a run's change or a commit range ("main..HEAD"): findings with severities and a SPEC / QUALITY verdict.

Input parameters:

- `dir` (string): Project directory (default: the server's).
- `group` (string): Group name for related runs.
- `plan` (string): With range: the plan file it implements.
- `range` (string): Or a commit range "A..B".
- `run` (string): Run id, or "last".
- `tier` (string): cheap, standard or capable (from the config).
- `waitSeconds` (number): Seconds before returning "still running" (default 50, max 540).
- `worker` (string): Worker "backend[:model]", e.g. "opencode", "claude:haiku".

### `pitroom_audit` (~98 tokens)

Audit an answer

Another worker re-checks a read run's answer: AGREE, PARTIAL or DISAGREE, with the disputed claims.

Input parameters:

- `run` (string, required): Run id, or "last".
- `waitSeconds` (number): Seconds before returning "still running" (default 50, max 540).
- `worker` (string): Worker "backend[:model]", e.g. "opencode", "claude:haiku".

### `pitroom_apply` (~79 tokens)

Apply an isolated change

Land an isolated run's patch (or a group's, in order) on the working tree; checked first. A patch deleting files needs allowDelete: pass it only after checking the deletions were asked for.

Input parameters:

- `allowDelete` (boolean)
- `group` (string)
- `run` (string): Run id, or "last".

### `pitroom_discard` (~36 tokens)

Discard an isolated change

Drop an isolated run's private copy (the patch is kept).

Input parameters:

- `run` (string, required): Run id, or "last".

### `pitroom_revert` (~41 tokens)

Undo an in-place change

Undo a mode "write" run's changes (refused if the files changed since).

Input parameters:

- `run` (string, required): Run id, or "last".

### `pitroom_stop` (~59 tokens)

Stop runs

Stop a running or queued run, or a group; cooldowns: try rate-limited models again now.

Input parameters:

- `cooldowns` (boolean)
- `group` (string)
- `run` (string): Run id, or "last".

## Diagnostics

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

## Score history

- 2026-11-06: 90
- 2026-11-05: 90
- 2026-11-04: 89
- 2026-11-03: 89
- 2026-11-02: 88
- 2026-11-01: 88
- 2026-10-31: 87
- 2026-10-30: 87
- 2026-10-29: 86
- 2026-10-28: 86
- 2026-10-27: 86
- 2026-10-26: 85
- 2026-10-25: 85
- 2026-10-24: 84
- 2026-10-23: 84
- 2026-10-22: 83
- 2026-10-21: 83
- 2026-10-20: 82
- 2026-10-19: 71
- 2026-10-18: 81
- 2026-10-17: 81
- 2026-10-16: 80
- 2026-10-15: 80
- 2026-10-14: 50
- 2026-10-13: 79
- 2026-10-12: 49
- 2026-10-08: 50

## Common questions

### What is the Pitroom MCP server?

Pitroom is an MCP server listed in the public MCP registry as io.github.ATASTECH/pitroom. Hands bounded coding work to cheaper worker agents: verified answers, exact diffs, cost receipts. This page covers its npm package (pitroom).

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

Pitroom scores 90 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 6 November 2026. 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 Pitroom MCP server expose?

Pitroom exposes 10 tools: pitroom_run, pitroom_wait, pitroom_show, pitroom_info, pitroom_review, and 5 more. Their descriptions and schemas cost roughly 1,315 tokens of context every time the server is loaded.

### Is the Pitroom MCP server still maintained?

Pitroom 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 Pitroom MCP server under?

Pitroom 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 Pitroom MCP server?

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

## Links

- npm package: https://www.npmjs.com/package/pitroom
- Socket report: https://socket.dev/npm/package/pitroom
- Repository: https://github.com/ATASTECH/pitroom
- Changelog RSS feed: https://verifymcp.io/servers/atastech-pitroom/pitroom.xml
- Changelog JSON feed: https://verifymcp.io/servers/atastech-pitroom/pitroom/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/atastech-pitroom/pitroom.json
- HTML version of this page: https://verifymcp.io/servers/atastech-pitroom/pitroom