# FlowSentry

> Security scanner for n8n workflows + live MCP Trust-Check. 18 rules, OWASP mapped. Paid x402 API.

- name: io.github.vasilicasijarvis/flowsentry
- version: 0.3.0
- connection class: unknown (unknown)
- trust: 61/100 flags: unreachable
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.vasilicasijarvis%2Fflowsentry
- tools: https://api.protogrid.dev/v1/servers/io.github.vasilicasijarvis%2Fflowsentry/tools

**Not classified yet.** The remote endpoints have not been probed successfully, or the listing has nothing to connect to.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "flowsentry": {
      "type": "http",
      "url": "https://flowsentry-agentpay2.vercel.app/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 0
- freshness: 85
- provenance: 80
- drivers: +repository +namespace-matches-repo -unreachable(13 failures) ~updated-33d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (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 carries no ttlMs, so clients re-fetch it

### 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: 71 (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
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: list_rules (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); scan_workflow (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); trust_check (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
- pass `tools.token_cost`: about 271 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

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

- n/a `stability.changes`, `stability.rug_pull`: tool history not recorded yet

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

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

- tools: 3, about 271 tokens to load them all
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.vasilicasijarvis/flowsentry.svg)](https://protogrid.dev/servers/io.github.vasilicasijarvis/flowsentry)
- 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://flowsentry-agentpay2.vercel.app/mcp (streamable-http, auth none, reachable false, uptime30d 0.13333334)

## Packages

_none_

## Tools (3)

- `list_rules`: List all 18 FlowSentry security rules with severity and OWASP Agentic mapping.
- `scan_workflow`: Scan one n8n workflow JSON export (string) and return the findings report.

Accepts the raw workflow object ({'nodes': [...], ...}) or the CLI export
wrapper ({'name':..., 'workflow': {...}}). Max 512 KB.
- `trust_check`: Live security Trust-Check of a remote MCP server URL (streamable HTTP).

Sends one benign MCP initialize handshake and inspects auth posture,
header hygiene, version disclosure and reachability. Returns trust score
0-100, grade A-F, verdict (trusted/acceptable/caution/unsafe/unreachable)
and structured findings. Paid unlimited lane: POST /v1/trust-check on the
same host ($0.25 USDC per check, x402 on Base).