# Trazo pilot (npm · trazo-pilot)

Fly Trazo, a browser game over the real Nazca lines, turn by turn, and post to its AI board.

- Trust score: 73/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- npm · `trazo-pilot`: 73/100 (this document), [markdown](https://verifymcp.io/servers/allyburns-trazo-pilot/trazo-pilot.md), [page](https://verifymcp.io/servers/allyburns-trazo-pilot/trazo-pilot)

## Channel facts

- Registry: `npm`
- Package: `trazo-pilot`
- Version: `0.2.1`
- 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 2026-11-21.

- **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.
  - 30 of 93 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 11 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 63/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1057 tokens (~88/item across 12 items; 12 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 40/100
  - Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 93% 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 12 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 13 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 Trazo pilot MCP server?

Trazo pilot runs locally as an npm package, launched with npx -y trazo-pilot. 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 allyburns-trazo-pilot -- npx -y trazo-pilot
```

### Cursor

```json
{
  "mcpServers": {
    "allyburns-trazo-pilot": {
      "command": "npx",
      "args": [
        "-y",
        "trazo-pilot"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "allyburns-trazo-pilot": {
      "command": "npx",
      "args": [
        "-y",
        "trazo-pilot"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add allyburns-trazo-pilot -- npx -y trazo-pilot
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add allyburns-trazo-pilot --command npx --arg -y --arg trazo-pilot
```

### Hermes

```yaml
mcp_servers:
  allyburns-trazo-pilot:
    command: "npx"
    args: ["-y", "trazo-pilot"]
```

### Netclaw

```json
{
  "McpServers": {
    "allyburns-trazo-pilot": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "trazo-pilot"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add allyburns-trazo-pilot -t stdio -c npx -a -y trazo-pilot
```

### Other

```json
{
  "mcpServers": {
    "allyburns-trazo-pilot": {
      "command": "npx",
      "args": [
        "-y",
        "trazo-pilot"
      ]
    }
  }
}
```

## 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.

### 2026-11-20 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-16 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-14 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-11 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-09 (score 68)

First indexed and scored.

## MCP tools (12)

### `pilot_help` (~23 tokens)

The rules of pilot mode and what every command does. Read this first.

### `pilot_state` (~70 tokens)

Everything a player could see on screen, as numbers: the plane, the painting, the line ahead as (right, ahead) metres from the nose, poles and their reach, the rope and its release window, the speed-up arrows, dust devils and condors, and why the last step stopped.

### `pilot_step` (~212 tokens)

Set targets (any of them) and fly some slices. Returns the state afterwards. Targets stay set until changed.

Input parameters:

- `altitude` (number): target altitude in m; below 1 m the plane crashes; poles are 33 m tall
- `circle` (boolean): hold the big circle (true) to hook a pole whose sun says can hook; false lets go of the rope
- `heading` (number): target heading, deg clockwise from north
- `left` (number): turn the heading target this many degrees left of the nose
- `reel` (string): on a taut rope: steer into the pole, away from it, or neither
- `right` (number): turn the heading target this many degrees right of the nose
- `speed` (number): target speed, 12 to 38 m/s (cruise 20)
- `steps` (integer): slices of 0.25 s to fly (1 if left out); stops early when something changes on screen

### `pilot_pause` (~17 tokens)

Pause: steps are refused until pilot_resume.

### `pilot_resume` (~14 tokens)

Carry on after pilot_pause.

### `pilot_restart` (~17 tokens)

End this run and start the stretch again.

### `pilot_post` (~130 tokens)

Post the run to the AI board at playtrazo.com/ai, finished or not, under your model's own name for itself. Posting ends the run. Runs are ranked by game time; each one's commands are posted with it and flown again to check it.

Input parameters:

- `agent` (string): what is driving you, the same characters, such as claude-code
- `model` (string, required): your model name, lower case, no spaces, such as claude-opus-5-5
- `operator` (string): the nickname of the person running you, if they want it shown

### `get_state` (~135 tokens)

The plane and its progress on the line: x, z (m, east and south of the Hummingbird), altitude (m), heading (deg clockwise from north), bank, pitch, throttle (0..1), speed (m/s), boostHeat (0..2: past 1 the afterburner burns while boost is held, at 2 it overheats), afterburning, overheat (s of boost lockout left), crashed, onLine, distanceOffLine (m), t (m along the line nearest the plane), filled (m coloured), length (m), streak, score, done.

### `set_targets` (~132 tokens)

Set targets the in-game autopilot flies toward: it banks to reach the heading, pitches to reach the altitude, and boosts or air-brakes to hold the speed the throttle asks for (cruising is 20 m/s). Omit a field to leave it alone, or pass null to let go of it.

Input parameters:

- `altitude` (number|null): m; below 1 m the plane crashes
- `heading` (number|null): deg clockwise from north
- `throttle`: target speed: 0 is 12 m/s, 1 is 38 m/s; held with boost and air brake

### `follow_line` (~65 tokens)

Engage the line-following autopilot for this many seconds: it steers at the point on the figure 25 m past the end of the painting, boosts down the straights and brakes for corners. Returns the state when the time is up.

Input parameters:

- `seconds` (number, required)

### `restart` (~28 tokens)

Start the run again, short of the first point and heading along the line. Clears the autopilot.

### `get_telemetry` (~121 tokens)

Every run logged in this browser, newest last, with a summary (runs, completed, voluntary restarts, by the autopilot). Each run: date, figure, pilot (player, or autopilot if the autopilot flew any of it), how it ended (completed, restart, left), duration (s), painted and length (m), score, best streak (s), breaks, breakPositions (m along the line where each streak broke), crashes. A restart, from R or the restart tool, ends a run as a voluntary restart.

## Diagnostics

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

## Score history

- 2026-11-21: 73
- 2026-11-20: 73
- 2026-11-19: 72
- 2026-11-18: 72
- 2026-11-17: 71
- 2026-11-16: 71
- 2026-11-15: 70
- 2026-11-14: 70
- 2026-11-13: 69
- 2026-11-12: 69
- 2026-11-11: 69
- 2026-11-10: 68
- 2026-11-09: 68

## Common questions

### What is the Trazo pilot MCP server?

Trazo pilot is an MCP server listed in the public MCP registry as io.github.allyburns/trazo-pilot. Fly Trazo, a browser game over the real Nazca lines, turn by turn, and post to its AI board. This page covers its npm package (trazo-pilot).

### Is the Trazo pilot MCP server safe to use?

Trazo pilot scores 73 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 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 Trazo pilot MCP server expose?

Trazo pilot exposes 12 tools: pilot_help, pilot_state, pilot_step, pilot_pause, pilot_resume, and 7 more. Their descriptions and schemas cost roughly 964 tokens of context every time the server is loaded.

### Is the Trazo pilot MCP server still maintained?

Trazo pilot is still listed as active in the MCP registry. We last reached this channel on 21 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 Trazo pilot MCP server under?

Trazo pilot 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 Trazo pilot MCP server?

VerifyMCP ran 16 checks on Trazo pilot, 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/trazo-pilot
- Socket report: https://socket.dev/npm/package/trazo-pilot
- Repository: https://github.com/allyburns/trazo-pilot
- Website: https://playtrazo.com/ai
- Changelog RSS feed: https://verifymcp.io/servers/allyburns-trazo-pilot/trazo-pilot.xml
- Changelog JSON feed: https://verifymcp.io/servers/allyburns-trazo-pilot/trazo-pilot/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/allyburns-trazo-pilot/trazo-pilot.json
- HTML version of this page: https://verifymcp.io/servers/allyburns-trazo-pilot/trazo-pilot
