# BrainFlow (remote · alpichack-3c740d01.alpic.live)

AI-powered ticket triage and workflow automation

- Trust score: 75/100 (medium)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `alpichack-3c740d01.alpic.live`: 75/100 (this document), [markdown](https://verifymcp.io/servers/live-alpic-alpichack-3c740d01-alpichack/alpichack-3c740d01.md), [page](https://verifymcp.io/servers/live-alpic-alpichack-3c740d01-alpichack/alpichack-3c740d01)

## Channel facts

- Endpoint: `https://alpichack-3c740d01.alpic.live`
- Transports: `streamable-http, sse`
- Auth: `none`
- Version: `0.0.1`

## 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 2026-08-03.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - 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**: 81/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 875 tokens (~54/item across 16 items; 12 tools + 4 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 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.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.
  - Supports UI / widget rendering.

## Install

### Claude

```bash
claude mcp add --transport http live-alpic-alpichack-3c740d01-alpichack https://alpichack-3c740d01.alpic.live/
```

### Codex

```toml
[mcp_servers.live-alpic-alpichack-3c740d01-alpichack]
url = "https://alpichack-3c740d01.alpic.live/"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "live-alpic-alpichack-3c740d01-alpichack": {
      "type": "remote",
      "url": "https://alpichack-3c740d01.alpic.live/",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add live-alpic-alpichack-3c740d01-alpichack --url https://alpichack-3c740d01.alpic.live/ --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  live-alpic-alpichack-3c740d01-alpichack:
    url: "https://alpichack-3c740d01.alpic.live/"
```

### Other

```json
{
  "mcpServers": {
    "live-alpic-alpichack-3c740d01-alpichack": {
      "type": "http",
      "url": "https://alpichack-3c740d01.alpic.live/"
    }
  }
}
```

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.

### 2026-08-03 (score 75, +1)

- [security] Resource “triage” now points somewhere else: ui://views/apps-sdk/triage.html?v=2bcb0532 → ui://views/ext-apps/triage.html?v=2bcb0532
- [security] Resource “setup” now points somewhere else: ui://views/apps-sdk/setup.html?v=050a9d25 → ui://views/ext-apps/setup.html?v=050a9d25

### 2026-08-02 (score 74, 0)

- [security] Resource “setup” now points somewhere else: ui://views/apps-sdk/setup.html?v=050a9d25 → ui://views/ext-apps/setup.html?v=050a9d25
- [security] Resource “triage” now points somewhere else: ui://views/apps-sdk/triage.html?v=2bcb0532 → ui://views/ext-apps/triage.html?v=2bcb0532

### 2026-08-01 (score 74, +1)

- [security] Resource “triage” now points somewhere else: ui://views/apps-sdk/triage.html?v=2bcb0532 → ui://views/ext-apps/triage.html?v=2bcb0532
- [security] Resource “setup” now points somewhere else: ui://views/apps-sdk/setup.html?v=050a9d25 → ui://views/ext-apps/setup.html?v=050a9d25

### 2026-07-31 (score 73, +2)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 71, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 71, +1)

- [security] Resource “triage” now points somewhere else: ui://views/apps-sdk/triage.html?v=2bcb0532 → ui://views/ext-apps/triage.html?v=2bcb0532
- [security] Resource “setup” now points somewhere else: ui://views/apps-sdk/setup.html?v=050a9d25 → ui://views/ext-apps/setup.html?v=050a9d25

### 2026-07-28 (score 70, +1)

- [security] Resource “triage” now points somewhere else: ui://views/apps-sdk/triage.html?v=2bcb0532 → ui://views/ext-apps/triage.html?v=2bcb0532
- [security] Resource “setup” now points somewhere else: ui://views/apps-sdk/setup.html?v=050a9d25 → ui://views/ext-apps/setup.html?v=050a9d25

### 2026-07-27 (score 69, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

## MCP tools (12)

### `setup` (~59 tokens)

Open the BrainFlow onboarding wizard. Use this when the user wants to configure BrainFlow, connect a task system (GitHub, Jira, or Slack), or change their role. Guides the user through role selection and OAuth connection in a step-by-step widget.

Output parameters:

- `step` (string): The initial wizard step to display

### `triage` (~123 tokens)

Show open tickets from connected task systems with triage classification. When the user asks for tickets from a specific system (e.g. 'show Jira tickets' or 'GitHub issues'), pass the matching source in the sources array.

Input parameters:

- `jira_project` (string): Jira project/space key to filter tickets (e.g. KAN). Only used when sources includes jira.
- `sources` (array): Filter tickets to specific sources. Pass ['jira'] for Jira only, ['github'] for GitHub only, etc. Omit to show tickets from all connected sources.

Output parameters:

- `loading` (boolean): True when the view is fetching fresh data in background
- `tickets` (array): Classified open tickets

### `open-ticket` (~81 tokens)

Open a specific ticket to see its details, MCP findings, and candidate solutions.

Input parameters:

- `role` (string): User role — determines Jira tickets (PM) or GitHub issues (engineer)
- `ticketId` (string, required): The ticket ID to open, e.g. sc-1842 or GH-123. Use the id field from triage results.

Output parameters:

- `role` (string): User role
- `ticket` (object)

### `get-agent-config` (~40 tokens)

Internal — load saved agent.md content for a role.

Input parameters:

- `role` (string, required): Role identifier, e.g. 'engineer' or 'pm'

Output parameters:

- `content` (string): The saved agent.md content, or empty string if none
- `role` (string)

### `save-agent-config` (~52 tokens)

Internal — save agent.md content for a role.

Input parameters:

- `content` (string, required): The agent.md content to save
- `role` (string, required): Role identifier, e.g. 'engineer' or 'pm'

Output parameters:

- `role` (string)
- `saved` (boolean)

### `connect-provider` (~29 tokens)

Internal — initiate an OAuth connection flow for a provider.

Input parameters:

- `provider` (string, required): Provider to connect

Output parameters:

- `redirectUrl` (string): OAuth authorization URL to redirect the user to

### `fetch-analysis` (~42 tokens)

Fetch LLM analysis (findings + solutions) for a ticket.

Input parameters:

- `ticketId` (string, required): The ticket source_id, e.g. KAN-1

Output parameters:

- `findings` (array)
- `solutions` (array)

### `get-connection-status` (~20 tokens)

Internal — get current connection status for all providers.

Output parameters:

- `connections` (object): Connection status for each supported provider

### `hitl-execute` (~221 tokens)

Internal — approve a candidate solution and create issues on the target platform (Jira stories or GitHub issues).

Input parameters:

- `jira_project_key` (string): Jira project key, e.g. KAN (Jira only)
- `notes` (string): PM/engineer notes
- `owner` (string): GitHub repo owner (required when platform=github)
- `platform` (string, required): Target platform. 'jira' for PM creating Jira stories, 'github' for engineer creating GitHub issues.
- `repo` (string): GitHub repo name (required when platform=github)
- `solution_effort` (string): Effort estimate (Jira only)
- `solution_id` (string, required): The chosen solution id
- `solution_risk` (string): Risk level (Jira only)
- `solution_summary` (string): Summary of the chosen solution
- `solution_title` (string): Title of the chosen solution
- `source` (string, required): Source system the ticket came from
- `ticket_id` (string, required): The ticket identifier

Output parameters:

- `createdIssues` (array)
- `creationErrors` (array)
- `selectedSolution` (object)

### `hitl-reject` (~83 tokens)

Internal — reject a BrainFlow HITL item with a rework reason.

Input parameters:

- `reason` (string, required): Short explanation of why all candidate solutions were rejected and what needs to change
- `source` (string, required): The source system the ticket came from
- `ticket_id` (string, required): The ticket identifier, e.g. GH-123 or sc-1842

Output parameters:

- `rejected` (boolean): True when the rejection was persisted successfully
- `ticketId` (string)

### `list-github-repos` (~23 tokens)

Internal — list the user's GitHub repositories for repo selection.

Output parameters:

- `repos` (array): User's GitHub repositories

### `list-jira-projects` (~22 tokens)

Internal — list the user's Jira projects for project selection.

Output parameters:

- `projects` (array): User's Jira projects

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/live-alpic-alpichack-3c740d01-alpichack/alpichack-3c740d01#diagnostics

## Score history

- 2026-08-03: 75
- 2026-08-02: 74
- 2026-08-01: 74
- 2026-07-31: 73
- 2026-07-30: 71
- 2026-07-29: 71
- 2026-07-28: 70
- 2026-07-27: 69
- 2026-07-26: 69

## Links

- Remote endpoint: https://alpichack-3c740d01.alpic.live/
- Changelog RSS feed: https://verifymcp.io/servers/live-alpic-alpichack-3c740d01-alpichack/alpichack-3c740d01/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/live-alpic-alpichack-3c740d01-alpichack/alpichack-3c740d01/changelog.json
- HTML version of this page: https://verifymcp.io/servers/live-alpic-alpichack-3c740d01-alpichack/alpichack-3c740d01