# Practonaut (npm · practonaut)

Local practice gym for AI agents on real apps: practice Excalidraw tasks, get a reproducible score.

- Trust score: 84/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `practonaut`: 84/100 (this document), [markdown](https://verifymcp.io/servers/godarg-practonaut/practonaut.md), [page](https://verifymcp.io/servers/godarg-practonaut/practonaut)

## Channel facts

- Registry: `npm`
- Package: `practonaut`
- Version: `0.2.0`
- 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 2026-11-05.

- **Supply Chain Security**: 82/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects zod 4.6.5, a direct dependency. A fixed version is available.
  - No install/post-install scripts declared.
  - 1 of 7 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to godarg/practonaut).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 19 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 76/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 824 tokens (~103/item across 8 items; 7 tools + 1 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 73/100
  - Stability observed for 22 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% 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 9 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).

## Install

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

Practonaut runs locally as an npm package, launched with npx -y practonaut mcp --task excalidraw/connect. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add godarg-practonaut -- npx -y practonaut mcp --task excalidraw/connect
```

### Cursor

```json
{
  "mcpServers": {
    "godarg-practonaut": {
      "command": "npx",
      "args": [
        "-y",
        "practonaut",
        "mcp",
        "--task",
        "excalidraw/connect"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "godarg-practonaut": {
      "command": "npx",
      "args": [
        "-y",
        "practonaut",
        "mcp",
        "--task",
        "excalidraw/connect"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add godarg-practonaut -- npx -y practonaut mcp --task excalidraw/connect
```

### opencode

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

### Hermes

```yaml
mcp_servers:
  godarg-practonaut:
    command: "npx"
    args: ["-y", "practonaut", "mcp", "--task", "excalidraw/connect"]
```

### Netclaw

```json
{
  "McpServers": {
    "godarg-practonaut": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "practonaut",
        "mcp",
        "--task",
        "excalidraw/connect"
      ]
    }
  }
}
```

### Other

```json
{
  "mcpServers": {
    "godarg-practonaut": {
      "command": "npx",
      "args": [
        "-y",
        "practonaut",
        "mcp",
        "--task",
        "excalidraw/connect"
      ]
    }
  }
}
```

## 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 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 83, +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.

### 2026-10-31 (score 82, +2)

- [functional improvement] Security disclosure: unverified → pass

### 2026-10-30 (score 80, −1)

- [functional regression] Security disclosure: pass → unverified

### 2026-10-29 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 79, +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.

### 2026-10-24 (score 78, −5)

- [security regression] CVE-2023-54404 affects this package: high
- [security regression] Known CVEs: pass → fail

## MCP tools (7)

### `observe` (~152 tokens)

Start here and call again whenever unsure. Returns the shared practice session as JSON: task (title, prompt and the goal conditions, each a sentence plus its formal form), state.objects (the live frames, steps and arrows keyed by id, with labels, positions, styles and arrow ends), step and revision (copy both into act), recent history, the last check and player-visible error explanations. Optional: detail "full" adds the action definitions, rules, task list and complete history; lang "en" (default), "de" or "both"; history = how many recent history items (default 5).

Input parameters:

- `detail` (string)
- `history` (integer)
- `lang` (string)

### `list_actions` (~69 tokens)

List the actions this session accepts, each with its parameters: type (id, nullable-id, string, integer, enum, end), bounds and allowed values. Id parameters take ids from observe's state.objects; ids of new objects appear in the created list of the reply to the action that creates them.

### `act` (~161 tokens)

Apply exactly one action. Arguments: name (an action from list_actions), params (exactly that action's parameters), baseStep (the current step) and expectedRevision (the current revision), both from the latest observe or act reply; optional lang. On success the reply gives the new step and revision, the objects that changed (as they are now), the ids created and removed, and the current error explanations. A rejected action changes nothing: read error.code and error.message (a stale step or revision names the current ones), then choose a valid action. Never guess step or revision.

Input parameters:

- `baseStep` (integer, required)
- `expectedRevision` (integer, required)
- `lang` (string)
- `name` (string, required)
- `params` (required)

### `undo` (~49 tokens)

Undo the most recent action. Argument: expectedRevision (the current revision); optional lang. The reply lists what changed, like act.

Input parameters:

- `expectedRevision` (integer, required)
- `lang` (string)

### `reset` (~69 tokens)

Discard every action of this attempt and return to the starting state. Arguments: expectedRevision (the current revision) and confirmed: true; optional lang. The reply lists what changed, like act.

Input parameters:

- `confirmed` (boolean, required)
- `expectedRevision` (integer, required)
- `lang` (string)

### `explain_result` (~46 tokens)

Read the result of the last check and the player-visible explanations of errors in the current state. Optional lang. Changes nothing and never reveals hidden evaluation data.

Input parameters:

- `lang` (string)

### `check_result` (~112 tokens)

Check whether the current state meets the task's goal conditions: passed plus one met/unmet entry per condition with its sentence and formal form, the same check a human player gets. Argument: expectedRevision (the current revision); optional lang. Checking changes nothing on the board. If observe shows limits.checks, each check uses one (checksRemaining says how many are left) and a used-up limit is refused with check_budget_exhausted.

Input parameters:

- `expectedRevision` (integer, required)
- `lang` (string)

## Diagnostics

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

## Score history

- 2026-11-05: 84
- 2026-11-04: 83
- 2026-11-03: 83
- 2026-11-02: 82
- 2026-11-01: 82
- 2026-10-31: 82
- 2026-10-30: 80
- 2026-10-29: 81
- 2026-10-28: 80
- 2026-10-27: 80
- 2026-10-26: 79
- 2026-10-25: 79
- 2026-10-24: 78
- 2026-10-23: 83
- 2026-10-22: 83
- 2026-10-21: 82
- 2026-10-20: 82
- 2026-10-19: 81
- 2026-10-18: 81
- 2026-10-17: 80
- 2026-10-16: 80
- 2026-10-15: 66
- 2026-10-14: 66

## Common questions

### What is the Practonaut MCP server?

Practonaut is an MCP server listed in the public MCP registry as io.github.godarg/practonaut. Local practice gym for AI agents on real apps: practice Excalidraw tasks, get a reproducible score. This page covers its npm package (practonaut).

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

Practonaut scores 84 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 5 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 Practonaut MCP server expose?

Practonaut exposes 7 tools: observe, list_actions, act, undo, reset, and 2 more. Their descriptions and schemas cost roughly 658 tokens of context every time the server is loaded.

### Is the Practonaut MCP server still maintained?

Practonaut is still listed as active in the MCP registry. We last reached this channel on 5 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 Practonaut MCP server under?

Practonaut declares the Apache-2.0 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 Practonaut MCP server?

VerifyMCP ran 16 checks on Practonaut, 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/practonaut
- Socket report: https://socket.dev/npm/package/practonaut
- Repository: https://github.com/godarg/practonaut
- Changelog RSS feed: https://verifymcp.io/servers/godarg-practonaut/practonaut.xml
- Changelog JSON feed: https://verifymcp.io/servers/godarg-practonaut/practonaut/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/godarg-practonaut/practonaut.json
- HTML version of this page: https://verifymcp.io/servers/godarg-practonaut/practonaut