# Trustabl Probe (npm · @trustabl/agent-network-access-probe)

Drafts a network allow list for agent tools and runs them in a network-blocked sandbox.

- Trust score: 82/100 (high trust)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- mcpb · `trustabl-agent-network-access-probe-0.5.0.mcpb`: 56/100, [markdown](https://verifymcp.io/servers/trustabl-agent-network-access-probe/trustabl-agent-network-access-probe.md), [page](https://verifymcp.io/servers/trustabl-agent-network-access-probe/trustabl-agent-network-access-probe)
- npm · `@trustabl/agent-network-access-probe`: 82/100 (this document), [markdown](https://verifymcp.io/servers/trustabl-agent-network-access-probe/trustabl-agent-network-access-probe-3.md), [page](https://verifymcp.io/servers/trustabl-agent-network-access-probe/trustabl-agent-network-access-probe-3)

## Channel facts

- Registry: `npm`
- Package: `@trustabl/agent-network-access-probe`
- Version: `0.5.0`
- 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**: 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**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to trustabl/agent-network-access-probe).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 9 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 79/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 470 tokens (~156/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **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 3 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.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the Trustabl Probe MCP server?

Trustabl Probe runs locally as an npm package, launched with npx -y @trustabl/agent-network-access-probe. 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 trustabl-agent-network-access-probe -- npx -y @trustabl/agent-network-access-probe
```

### Cursor

```json
{
  "mcpServers": {
    "trustabl-agent-network-access-probe": {
      "command": "npx",
      "args": [
        "-y",
        "@trustabl/agent-network-access-probe"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "trustabl-agent-network-access-probe": {
      "command": "npx",
      "args": [
        "-y",
        "@trustabl/agent-network-access-probe"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add trustabl-agent-network-access-probe -- npx -y @trustabl/agent-network-access-probe
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "trustabl-agent-network-access-probe": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@trustabl/agent-network-access-probe"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add trustabl-agent-network-access-probe --command npx --arg -y --arg @trustabl/agent-network-access-probe
```

### Hermes

```yaml
mcp_servers:
  trustabl-agent-network-access-probe:
    command: "npx"
    args: ["-y", "@trustabl/agent-network-access-probe"]
```

### Netclaw

```json
{
  "McpServers": {
    "trustabl-agent-network-access-probe": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@trustabl/agent-network-access-probe"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add trustabl-agent-network-access-probe -t stdio -c npx -a -y @trustabl/agent-network-access-probe
```

### Other

```json
{
  "mcpServers": {
    "trustabl-agent-network-access-probe": {
      "command": "npx",
      "args": [
        "-y",
        "@trustabl/agent-network-access-probe"
      ]
    }
  }
}
```

## 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.

### 2026-10-28 (score 82, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-27 (score 67)

First indexed and scored.

## MCP tools (3)

### `probe_check_setup` (~71 tokens)

Check what Probe needs on this machine

Read-only. Reports whether the Probe binary, Docker (running), the sandbox images, and the optional OpenShell runner are ready, which languages can run in the sandbox, and the exact command to fix each missing piece. Changes nothing. Run it before probe_install or when a scan says the sandbox is unavailable.

### `probe_install` (~136 tokens)

Install Probe's own pieces

Downloads the Probe binary from its GitHub release (checksum-verified) and, when Docker is running, pulls the sandbox base images. It never installs system software: for Docker, OpenShell or Python it returns the exact command and its caveats (admin rights, restarts, licensing) for you to show the user and run only with their permission. Pulling all images can take a few minutes; pass `languages` to pull only what the tool needs.

Input parameters:

- `languages` (array): Sandbox images to pull. Default: all four.
- `pull_images` (boolean): Pull the sandbox images when Docker is running. Default true.

### `probe_scan` (~263 tokens)

Scan an agent tool with Probe

Runs Trustabl Probe on a directory of agent tool code (Python, Go, JavaScript/TypeScript, Ruby, Shell). Static analysis always runs; with sandbox 'auto' (default) the tool is also run in an isolated, network-blocked sandbox when Docker or OpenShell is ready, which catches problems that only show up at runtime. Returns a readiness score, the draft network allow list (an OpenShell network policy), and findings worst-first, each with a fix hint for you to apply. Writes network_policies.draft.yaml, probe.findings.json, probe.profile.json and autofix-attestation.json into the scanned directory.

Input parameters:

- `allow_write_tools` (boolean): Run tools that look destructive (network writes, deletes, payments) in the sandbox too. Default false: they are skipped and only analyzed statically. Only set true when the user asks.
- `entrypoints` (array): Entry point files inside the directory, e.g. ['tool.py']. Default: Probe discovers them.
- `path` (string): Directory with the tool code. Defaults to the current directory.
- `sandbox` (string): 'auto' (default) uses the sandbox when a runner is ready; 'on' fails without one; 'off' is static only.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/trustabl-agent-network-access-probe/trustabl-agent-network-access-probe-3#diagnostics

## Score history

- 2026-11-05: 82
- 2026-11-04: 82
- 2026-11-03: 82
- 2026-11-02: 82
- 2026-11-01: 82
- 2026-10-31: 82
- 2026-10-30: 82
- 2026-10-29: 82
- 2026-10-28: 82
- 2026-10-27: 67

## Common questions

### What is the Trustabl Probe MCP server?

Trustabl Probe is an MCP server listed in the public MCP registry as io.github.trustabl/agent-network-access-probe. Drafts a network allow list for agent tools and runs them in a network-blocked sandbox. This page covers its npm package (@trustabl/agent-network-access-probe).

### Is the Trustabl Probe MCP server safe to use?

Trustabl Probe scores 82 out of 100 on VerifyMCP. We found no known CVEs affecting 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 Trustabl Probe MCP server expose?

Trustabl Probe exposes 3 tools: probe_check_setup, probe_install, probe_scan. Their descriptions and schemas cost roughly 470 tokens of context every time the server is loaded.

### Is the Trustabl Probe MCP server still maintained?

Trustabl Probe 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 Trustabl Probe MCP server under?

Trustabl Probe 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/@trustabl/agent-network-access-probe
- Socket report: https://socket.dev/npm/package/@trustabl/agent-network-access-probe
- Repository: https://github.com/trustabl/agent-network-access-probe
- Website: https://trustabl.ai/
- Changelog RSS feed: https://verifymcp.io/servers/trustabl-agent-network-access-probe/trustabl-agent-network-access-probe-3.xml
- Changelog JSON feed: https://verifymcp.io/servers/trustabl-agent-network-access-probe/trustabl-agent-network-access-probe-3.json
- HTML version of this page: https://verifymcp.io/servers/trustabl-agent-network-access-probe/trustabl-agent-network-access-probe-3