# toolprint by JEStats (npm · toolprint)

package-lock.json for MCP trust: catch MCP rug-pulls, tool poisoning, and leaked secrets.

- Trust score: 82/100 (high trust)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-24

## Components

- npm · `toolprint`: 82/100 (this document), [markdown](https://verifymcp.io/servers/jestatsio-toolprint/toolprint.md), [page](https://verifymcp.io/servers/jestatsio-toolprint/toolprint)

## Channel facts

- Registry: `npm`
- Package: `toolprint`
- Version: `0.4.1`
- 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 2026-10-24.

- **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**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to jestatsio/toolprint).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 8 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 57/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1002 tokens (~501/item across 2 items; 2 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% 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 2 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 3 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 toolprint by JEStats MCP server?

toolprint by JEStats runs locally as an npm package, launched with npx -y toolprint. 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 jestatsio-toolprint -- npx -y toolprint
```

### Cursor

```json
{
  "mcpServers": {
    "jestatsio-toolprint": {
      "command": "npx",
      "args": [
        "-y",
        "toolprint"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "jestatsio-toolprint": {
      "command": "npx",
      "args": [
        "-y",
        "toolprint"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add jestatsio-toolprint -- npx -y toolprint
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add jestatsio-toolprint --command npx --arg -y --arg toolprint
```

### Hermes

```yaml
mcp_servers:
  jestatsio-toolprint:
    command: "npx"
    args: ["-y", "toolprint"]
```

### Netclaw

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

### Vellum

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

### Other

```json
{
  "mcpServers": {
    "jestatsio-toolprint": {
      "command": "npx",
      "args": [
        "-y",
        "toolprint"
      ]
    }
  }
}
```

## 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.

### 2026-10-24 (score 82, +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.

### 2026-10-23 (score 81, +3)

- [functional improvement] Stability: unverified → 0.27

### 2026-10-16 (score 78, +11)

- [security improvement] Known CVEs: unverified → pass
- [functional improvement] Dependency health: unverified → 0.85

### 2026-10-15 (score 67)

First indexed and scored.

## MCP tools (2)

### `scan` (~457 tokens)

Scan MCP servers and skills

Connect to MCP servers (or read skill bundles), compare every capability against toolprint.lock, and report tool-poisoning, secret-leak, and rug-pull findings. Read-only: never writes the lockfile. Findings at or above `failOn` set `failing: true` and `exitCode: 2` in the structured result.

Input parameters:

- `allClients` (boolean): Discover and scan the MCP config of every agent client installed on this machine (Claude Code, Claude Desktop, Cursor, Zed, and more).
- `baseline` (string): Path to a prior JSON report, to show findings new or resolved since then.
- `clients` (array): Scan only these agent client ids, for example `cursor` or `zed`.
- `config` (string): Path to an MCP client config file (Claude Desktop / VS Code / Cursor).
- `failOn` (string): Minimum severity that counts as failing: info, low, medium, high, or critical. Default high.
- `failOnNew` (boolean): With `baseline`, count only newly introduced findings as failing.
- `ignoreFile` (string): Path to toolprint.ignore.json with reviewed false positives.
- `lockfile` (string): Path to toolprint.lock (default: nearest one).
- `probe` (boolean): Call tools the server annotates as read-only (a self-report, not verified) with empty arguments and inspect what they return. Off by default; only probe servers the user trusts to execute.
- `probeTools` (array): Call these tools by name regardless of annotation. Enables probing on its own.
- `skills` (boolean|string): Scan SKILL.md skill bundles on disk instead of MCP servers: `true` for the default skill roots, or a directory path.
- `target` (string): What to scan: an MCP config path, an http(s) MCP URL, an `npx:<package>` spec, or a raw server command. Omit to auto-discover the project's MCP config.
- `timeoutMs` (integer): Per-server timeout in milliseconds. Default 30000.
- `workingDirectory` (string): Project directory for relative paths and lockfile discovery. Default: this process's working directory.

### `pin` (~445 tokens)

Pin current definitions into toolprint.lock

Scan, then write the current capability definitions into toolprint.lock as the trusted baseline for future scans. Pinning accepts drift, so only call this after the user reviews the changes; poisoning and leaked-secret findings still set `failing: true`. The user should commit the lockfile after a pin.

Input parameters:

- `allClients` (boolean): Discover and scan the MCP config of every agent client installed on this machine (Claude Code, Claude Desktop, Cursor, Zed, and more).
- `baseline` (string): Path to a prior JSON report, to show findings new or resolved since then.
- `clients` (array): Scan only these agent client ids, for example `cursor` or `zed`.
- `config` (string): Path to an MCP client config file (Claude Desktop / VS Code / Cursor).
- `failOn` (string): Minimum severity that counts as failing: info, low, medium, high, or critical. Default high.
- `failOnNew` (boolean): With `baseline`, count only newly introduced findings as failing.
- `ignoreFile` (string): Path to toolprint.ignore.json with reviewed false positives.
- `lockfile` (string): Path to toolprint.lock (default: nearest one).
- `probe` (boolean): Call tools the server annotates as read-only (a self-report, not verified) with empty arguments and inspect what they return. Off by default; only probe servers the user trusts to execute.
- `probeTools` (array): Call these tools by name regardless of annotation. Enables probing on its own.
- `skills` (boolean|string): Scan SKILL.md skill bundles on disk instead of MCP servers: `true` for the default skill roots, or a directory path.
- `target` (string): What to scan: an MCP config path, an http(s) MCP URL, an `npx:<package>` spec, or a raw server command. Omit to auto-discover the project's MCP config.
- `timeoutMs` (integer): Per-server timeout in milliseconds. Default 30000.
- `workingDirectory` (string): Project directory for relative paths and lockfile discovery. Default: this process's working directory.

## Diagnostics

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

## Score history

- 2026-10-24: 82
- 2026-10-23: 81
- 2026-10-22: 78
- 2026-10-21: 78
- 2026-10-20: 78
- 2026-10-19: 78
- 2026-10-18: 78
- 2026-10-17: 78
- 2026-10-16: 78
- 2026-10-15: 67

## Common questions

### What is the toolprint by JEStats MCP server?

toolprint by JEStats is an MCP server listed in the public MCP registry as io.github.jestatsio/toolprint. package-lock.json for MCP trust: catch MCP rug-pulls, tool poisoning, and leaked secrets. This page covers its npm package (toolprint).

### Is the toolprint by JEStats MCP server safe to use?

toolprint by JEStats scores 82 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 24 October 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 toolprint by JEStats MCP server expose?

toolprint by JEStats exposes 2 tools: scan, pin. Their descriptions and schemas cost roughly 902 tokens of context every time the server is loaded.

### Is the toolprint by JEStats MCP server still maintained?

toolprint by JEStats is still listed as active in the MCP registry. We last reached this channel on 24 October 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 toolprint by JEStats MCP server under?

toolprint by JEStats 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.

## Links

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