# TrustScan

> Security scanner for MCP servers and skills: Unicode injection, patterns, secrets.

- name: io.github.entradox/trust-scan
- version: 0.1.0
- connection class: R0 (autonomous)
- trust: 94/100
- quality: 86/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.entradox%2Ftrust-scan
- tools: https://api.protogrid.dev/v1/servers/io.github.entradox%2Ftrust-scan/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "trust-scan": {
      "type": "http",
      "url": "https://trust-scan-production.up.railway.app/mcp/"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 99
- freshness: 85
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-98% ~updated-43d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 86/100 (good)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 79 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- warn `tools.annotations`: only 2 of 4 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: read_skill (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); trust_scan_file (openWorldHint); skills_list_tool (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 452 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 4, about 452 tokens to load them all
- tool set hash: d2fb864503355dae2313f941c7b023e4
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.entradox/trust-scan.svg)](https://protogrid.dev/servers/io.github.entradox/trust-scan)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://trust-scan-production.up.railway.app/mcp/ (streamable-http, auth none, reachable true, uptime30d 0.9831933)

## Packages

_none_

## Tools (4)

- `read_skill`: Read a product skill file by its skill:// URI.
- `skills_list_tool`: List this product's skills. Each entry carries the SKILL.md URI,
its name and description, verbatim frontmatter, and a per-file
sha256 manifest. Read a body with `read_skill`.
- `trust_scan_file`: Security-scan a single file for invisible Unicode, dangerous patterns, and secrets.

Returns a severity-weighted score and per-finding detail (rule, severity,
location). Read-only: the file is never modified.
- `trust_scan_server`: Security-scan an MCP server or skill package before trusting it.

Runs all four checks — invisible Unicode prompt-injection, dangerous code
patterns (MCP001–006), hardcoded secrets, typosquat package names — and
returns a 0-100 score, letter grade, and detailed findings. Run this on
any directory BEFORE wiring it into your agent. Read-only: never modifies
the scanned target.