# 72hours security check (remote · oboe-handiness-enroll.ngrok-free.dev)

Scan a public GitHub repo, explain risks, get fix prompts and rescan to confirm fixes.

- Trust score: 63/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-04

## Components

- remote · `oboe-handiness-enroll.ngrok-free.dev`: 63/100 (this document), [markdown](https://verifymcp.io/servers/maebsy-72hours/mcp-service-rpc.md), [page](https://verifymcp.io/servers/maebsy-72hours/mcp-service-rpc)

## Channel facts

- Endpoint: `https://oboe-handiness-enroll.ngrok-free.dev/mcp/service/rpc`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, 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 2026-11-04.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (close_workspace).
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 71/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (fair).
  - Context-footprint check failed: tool/resource definitions use about 1967 tokens (~131/item across 15 items; 15 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (7% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 16 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 72hours security check MCP server?

72hours security check is a hosted endpoint at https://oboe-handiness-enroll.ngrok-free.dev/mcp/service/rpc, so there is nothing to install locally. 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 --transport http maebsy-72hours 'https://oboe-handiness-enroll.ngrok-free.dev/mcp/service/rpc'
```

### Cursor

```json
{
  "mcpServers": {
    "maebsy-72hours": {
      "url": "https://oboe-handiness-enroll.ngrok-free.dev/mcp/service/rpc"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "maebsy-72hours": {
      "type": "http",
      "url": "https://oboe-handiness-enroll.ngrok-free.dev/mcp/service/rpc"
    }
  }
}
```

### Codex

```toml
[mcp_servers.maebsy-72hours]
url = "https://oboe-handiness-enroll.ngrok-free.dev/mcp/service/rpc"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "maebsy-72hours": {
      "type": "remote",
      "url": "https://oboe-handiness-enroll.ngrok-free.dev/mcp/service/rpc",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add maebsy-72hours --url 'https://oboe-handiness-enroll.ngrok-free.dev/mcp/service/rpc' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  maebsy-72hours:
    url: "https://oboe-handiness-enroll.ngrok-free.dev/mcp/service/rpc"
```

### Netclaw

```json
{
  "McpServers": {
    "maebsy-72hours": {
      "Transport": "http",
      "Url": "https://oboe-handiness-enroll.ngrok-free.dev/mcp/service/rpc"
    }
  }
}
```

### Vellum

```bash
assistant mcp add maebsy-72hours -t streamable-http -u 'https://oboe-handiness-enroll.ngrok-free.dev/mcp/service/rpc'
```

### Other

```json
{
  "mcpServers": {
    "maebsy-72hours": {
      "type": "http",
      "url": "https://oboe-handiness-enroll.ngrok-free.dev/mcp/service/rpc"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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.

### 2026-11-03 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 62, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-31 (score 61)

First indexed and scored.

## MCP tools (15)

### `service_info` (~20 tokens)

Learn the whole workflow and available service capabilities before creating work.

### `create_workspace` (~26 tokens)

Create a private, expiring workspace. Save its capability only in the user's AI conversation.

### `close_workspace` (~33 tokens)

Revoke this workspace and its result access. Does not cancel already submitted backend jobs.

Input parameters:

- `workspace_token` (string, required)

### `start_scan` (~59 tokens)

Start a REAL public GitHub scan. User authorization required. Reuse request_id on identical retries.

Input parameters:

- `authorized` (boolean)
- `repository_url` (string, required)
- `request_id` (string, required)
- `workspace_token` (string, required)

### `get_scan` (~47 tokens)

Poll every >=10 seconds; on done return actual commit, coverage and up to 50 LLM-input findings.

Input parameters:

- `scan_id` (string, required)
- `workspace_token` (string, required)

### `start_analysis` (~48 tokens)

Start GPU Red/Blue review of one real scan finding. Same inputs deduplicate.

Input parameters:

- `fingerprint` (string, required)
- `scan_id` (string, required)
- `workspace_token` (string, required)

### `get_analysis` (~42 tokens)

Poll GPU status and delivery gates; inference can take several minutes. Never fake ready results.

Input parameters:

- `analysis_id` (string, required)
- `workspace_token` (string, required)

### `get_fix_prompt` (~50 tokens)

Get a gated real LLM proposal. Agent must inspect code, check repo/commit, fix and test in its workspace.

Input parameters:

- `analysis_id` (string, required)
- `workspace_token` (string, required)

Output parameters:

- `result` (string)

### `rescan` (~61 tokens)

Rescan the SAME repository default branch. Only published changes are visible; unpushed edits are not.

Input parameters:

- `authorized` (boolean)
- `previous_scan_id` (string, required)
- `request_id` (string, required)
- `workspace_token` (string, required)

### `generate_report` (~41 tokens)

Generate the service's report from owned server scan and available analyses, indicating incomplete work.

Input parameters:

- `scan_id` (string, required)
- `workspace_token` (string, required)

### `incident_report` (~113 tokens)

Draft only; NEVER submits. kind: assess/incident-24h/privacy-72h. incident requires discovered_at ISO time;
        optional organization {name,service_name,contact_email}, summary, incident_types, damage, actions_taken,
        personal_info {leaked: confirmed/suspected/none, affected_count, items}. Use only user-confirmed facts.

Input parameters:

- `incident` (object, required)
- `kind` (string, required)
- `scan_id` (string, required)
- `workspace_token` (string, required)

### `audit_repository` (~127 tokens)

One call security audit of a PUBLIC GitHub repo the user is authorized to scan. Creates a workspace if
        workspace_token is empty (keep the returned token private), scans, waits up to 90 s, starts GPU analysis for the
        top max_analyses (0-5) findings and returns summary + next steps. Reuse request_id only for the SAME request.

Input parameters:

- `authorized` (boolean)
- `max_analyses` (integer)
- `repository_url` (string, required)
- `request_id` (string, required)
- `workspace_token` (string)

### `audit_status` (~45 tokens)

Scan summary, analysis statuses and which fix prompts (get_fix_prompt) are ready, in one call.

Input parameters:

- `scan_id` (string, required)
- `workspace_token` (string, required)

### `check_fix` (~83 tokens)

After fixes are PUSHED to the default branch: rescan the same repo against scan_id and list resolved,
        persisting, new and key-reissue-needed findings. Same commit means the fix was not pushed yet.

Input parameters:

- `authorized` (boolean)
- `request_id` (string, required)
- `scan_id` (string, required)
- `workspace_token` (string, required)

### `verify_demo` (~96 tokens)

Runtime proof on the DEMO target only: isolated sandbox replays attacks before/after the fix and runs
        functional tests. mode: reference (human fix) or ai (Red/Blue generated attacks and fix). Not the user's repo.
        If a previous call returned status queued/running, pass its verify_job_id to keep polling the same job.

Input parameters:

- `mode` (string)
- `verify_job_id` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/maebsy-72hours/mcp-service-rpc#diagnostics

## Score history

- 2026-11-04: 63
- 2026-11-03: 63
- 2026-11-02: 62
- 2026-11-01: 62
- 2026-10-31: 61

## Common questions

### What is the 72hours security check MCP server?

72hours security check is an MCP server listed in the public MCP registry as io.github.maebsy/72hours. Scan a public GitHub repo, explain risks, get fix prompts and rescan to confirm fixes. This page covers its hosted endpoint (https://oboe-handiness-enroll.ngrok-free.dev/mcp/service/rpc).

### Is the 72hours security check MCP server safe to use?

72hours security check scores 63 out of 100 on VerifyMCP. 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 72hours security check MCP server expose?

72hours security check exposes 15 tools: service_info, create_workspace, close_workspace, start_scan, get_scan, and 10 more. Their descriptions and schemas cost roughly 891 tokens of context every time the server is loaded.

### Does the 72hours security check MCP server require authentication?

No. We connected to 72hours security check without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the 72hours security check MCP server still maintained?

72hours security check is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://oboe-handiness-enroll.ngrok-free.dev/mcp/service/rpc
- Repository: https://github.com/maebsy/YMCA-hackathon-2026
- Changelog RSS feed: https://verifymcp.io/servers/maebsy-72hours/mcp-service-rpc.xml
- Changelog JSON feed: https://verifymcp.io/servers/maebsy-72hours/mcp-service-rpc.json
- HTML version of this page: https://verifymcp.io/servers/maebsy-72hours/mcp-service-rpc