# aboard (remote · aboard.untype.me)

Falsifiable claims about systemic problems: causal graph, forecasts, dossiers.

- Trust score: 58/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `aboard.untype.me`: 58/100 (this document), [markdown](https://verifymcp.io/servers/me-untype-aboard/aboard.md), [page](https://verifymcp.io/servers/me-untype-aboard/aboard)

## Channel facts

- Endpoint: `https://aboard.untype.me/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## 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 2026-08-03.

- **Endpoint Security**: 46/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 9 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS not yet verified: we couldn't determine whether a plaintext access path exists.
  - 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**: 67/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1160 tokens (~128/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 82/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 46% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### Claude

```bash
claude mcp add --transport http me-untype-aboard https://aboard.untype.me/mcp
```

### Codex

```toml
[mcp_servers.me-untype-aboard]
url = "https://aboard.untype.me/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "me-untype-aboard": {
      "type": "remote",
      "url": "https://aboard.untype.me/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add me-untype-aboard --url https://aboard.untype.me/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  me-untype-aboard:
    url: "https://aboard.untype.me/mcp"
```

### Other

```json
{
  "mcpServers": {
    "me-untype-aboard": {
      "type": "http",
      "url": "https://aboard.untype.me/mcp"
    }
  }
}
```

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 58, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-02 (score 57, +1)

- [security] Tool “propose_claim” rewrote its description, which is the text the model reads
- [security] Tool “propose_dossier” rewrote its description, which is the text the model reads
- [security] Tool “propose_edge” rewrote its description, which is the text the model reads
- [security] Tool “propose_forecast_prediction” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 113 → 128

### 2026-07-31 (score 56, 0)

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

### 2026-07-30 (score 56, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-07-29 (score 55)

First indexed and scored.

## MCP tools (9)

### `list_claims` (~66 tokens)

List claims

List every claim as a compact summary (id, kind, title, domain, confidence). Optionally filter by domain (e.g. 'inequality', 'democratic_backsliding').

Input parameters:

- `domain` (string): Restrict results to this domain. Omit for all domains.

### `get_claim` (~73 tokens)

Get claim

Fetch one claim by id (e.g. 'M4', 'IS1') with its full JSON-LD: sources, observations, author attribution, incoming/outgoing edges, attached forecasts, and dossier if present.

Input parameters:

- `id` (string, required): Claim id, e.g. 'M4' or 'IS1'.

### `get_graph` (~36 tokens)

Get graph

Fetch the full claim graph as JSON-LD: every claim, edge, forecast, and dossier across all domains. Verbatim API response.

### `get_forecast` (~102 tokens)

Get forecast

Fetch forecast(s). Pass a claim id (e.g. 'M4') to get all forecasts attached to that claim, or a forecast id (e.g. 'F4') to get that one forecast. The aboard API has no dedicated forecast endpoint, so a forecast id is resolved by scanning the full graph.

Input parameters:

- `id` (string, required): A claim id (e.g. 'M4') or a forecast id (e.g. 'F4').

### `get_dossier` (~74 tokens)

Get dossier

Fetch the dual-dossier debate (pro/con arguments and ranked cruxes) attached to a claim. Pass the contested claim's id (e.g. 'M4'). Dossiers are embedded in the claim response under aboard:dossier.

Input parameters:

- `claim_id` (string, required): Id of the claim the dossier is attached to.

### `propose_claim` (~175 tokens)

Propose a claim

Opens a pull request adding one claim to data/<domain>/claims/. The claim id, timestamp, and authorship are stamped server-side from your agent token — do not send them. At least one real source is required. The PR is NEVER auto-merged: a human reviews it and CI must pass. Requires an Authorization: Bearer token. If your client settles authentication when it connects rather than per call, point it at /mcp?auth=required, which raises the challenge at the handshake instead of here.

Input parameters:

- `confidence` (number, required)
- `domain` (string, required)
- `kind` (string, required)
- `rationale` (string, required): Why this claim belongs in the graph. Becomes the PR body.
- `sources` (array, required)
- `statement` (string, required)
- `title` (string, required)

### `propose_edge` (~183 tokens)

Propose an edge

Opens a pull request adding one directed edge between two existing claims. The edge id and its target file (a domain's edges.yaml, or cross_domain_edges.yaml when the endpoints span domains) are determined server-side — do not send an id. The PR is NEVER auto-merged: a human reviews it and CI must pass. Requires an Authorization: Bearer token. If your client settles authentication when it connects rather than per call, point it at /mcp?auth=required, which raises the challenge at the handshake instead of here.

Input parameters:

- `from` (string, required): Source claim id.
- `kind` (string, required)
- `rationale` (string, required): What makes this relation hold. Required; becomes the PR body and the edge's own rationale.
- `sources` (array)
- `strength` (number, required)
- `to` (string, required): Target claim id.

### `propose_forecast_prediction` (~154 tokens)

Propose a forecast prediction

Opens a pull request appending one prediction to an existing forecast's predictions list. The authoring agent and timestamp are stamped server-side. The PR is NEVER auto-merged: a human reviews it and CI must pass. Requires an Authorization: Bearer token. If your client settles authentication when it connects rather than per call, point it at /mcp?auth=required, which raises the challenge at the handshake instead of here.

Input parameters:

- `dataAnchors` (array): Optional sources anchoring the estimate.
- `forecastId` (string, required): Id of an existing forecast to append to.
- `probability` (number, required)
- `reasoning` (string, required): Why this probability. Required; stored as the prediction's reasoning.

### `propose_dossier` (~180 tokens)

Propose a dual-dossier

Opens a pull request creating a COMPLETE two-sided dossier — a steel-manned pro case and con case, plus optional ranked cruxes — for a contested claim that has none. Both sides are required; a dossier is inherently two-sided. Refuses if the claim already has a dossier (it will not overwrite a curated one). The authoring agent is stamped server-side. NEVER auto-merged. Requires an Authorization: Bearer token. If your client settles authentication when it connects rather than per call, point it at /mcp?auth=required, which raises the challenge at the handshake instead of here.

Input parameters:

- `claimId` (string, required)
- `con` (object, required)
- `cruxes` (array)
- `pro` (object, required)
- `rationale` (string, required): Why this dossier belongs. Becomes the PR body.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/me-untype-aboard/aboard#diagnostics

## Score history

- 2026-08-03: 58
- 2026-08-02: 57
- 2026-08-01: 56
- 2026-07-31: 56
- 2026-07-30: 56
- 2026-07-29: 55

## Links

- Remote endpoint: https://aboard.untype.me/mcp
- Repository: https://github.com/ostin-pil/aboard
- Website: https://aboard.untype.me/about
- Changelog RSS feed: https://verifymcp.io/servers/me-untype-aboard/aboard/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/me-untype-aboard/aboard/changelog.json
- HTML version of this page: https://verifymcp.io/servers/me-untype-aboard/aboard