# AsDecided (oci · ghcr.io/asdecided/core:mcp-v0.26.2)

Read-only access to deterministic engineering decisions stored in a local repository.

- Trust score: 35/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- oci · `ghcr.io/asdecided/core:mcp-v0.26.2`: 35/100 (this document), [markdown](https://verifymcp.io/servers/asdecided-core/ghcr-io-asdecided-core-mcp-v0-26-2.md), [page](https://verifymcp.io/servers/asdecided-core/ghcr-io-asdecided-core-mcp-v0-26-2)

## Channel facts

- Registry: `oci`
- Package: `ghcr.io/asdecided/core:mcp-v0.26.2`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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.

- **Supply Chain Security**: 0/100
  - Malware scan not yet available for this package.
  - CVE data not yet available for this package.
  - Install-script risk not yet assessed.
  - Dependency-health data not yet available.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 1 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 68/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 807 tokens (~134/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **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 (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

**Unverified: 2 categories.** Categories scored 0 because we could not verify them: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add asdecided-core -- docker run --rm -i ghcr.io/asdecided/core:mcp-v0.26.2
```

### Codex

```bash
codex mcp add asdecided-core -- docker run --rm -i ghcr.io/asdecided/core:mcp-v0.26.2
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "asdecided-core": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "ghcr.io/asdecided/core:mcp-v0.26.2"
      ],
      "enabled": true
    }
  }
}
```

### Hermes

```yaml
mcp_servers:
  asdecided-core:
    command: "docker"
    args: ["run", "--rm", "-i", "ghcr.io/asdecided/core:mcp-v0.26.2"]
```

### Other

```json
{
  "mcpServers": {
    "asdecided-core": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/asdecided/core:mcp-v0.26.2"
      ]
    }
  }
}
```

## 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.

### 2026-08-02 (score 35, +26)

- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Tool coverage: 0
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: good
- [functional] First check of Tool coverage: 100

### 2026-08-01 (score 9)

First indexed and scored.

## MCP tools (6)

### `get_artifact` (~103 tokens)

Retrieve one artifact from this repository's recorded product knowledge — a requirement, decision (ADR), design, roadmap, or prompt — by its identifier. Call this whenever an artifact ID is mentioned (for example REQ-001, ADR-012, or a RAC-prefixed ID), and before relying on or changing anything a known requirement or decision covers. Returns the artifact's metadata and full Markdown content.

Input parameters:

- `budget` (integer)
- `id` (string, required)

Output parameters:

- `result` (string)

### `search_artifacts` (~142 tokens)

Search this repository's recorded product knowledge — requirements, decisions (ADRs), designs, roadmaps, and prompts — by keyword. Call this before designing or implementing anything that an existing requirement or prior decision might cover, and whenever the user mentions a feature area, so recorded decisions are respected instead of rediscovered. Optionally pass `tags` to narrow the query to artifacts carrying every given frontmatter tag. Returns matching artifact IDs, types, titles, and paths (plus their tags when tagged); use get_artifact to read a match.

Input parameters:

- `live_only` (boolean)
- `query` (string, required)
- `tags`
- `type`

Output parameters:

- `result` (string)

### `retrieve_grounding` (~120 tokens)

One-call grounding for a task from this repository's recorded product knowledge: a ranked, budget-capped set of artifacts with excerpts and provenance, deterministically retrieved. Pass `scope` (a file or directory you will touch) to include the decisions governing that path; superseded matches are replaced by their live successors. Use get_artifact to read an item in full.

Input parameters:

- `budget` (integer)
- `live_only` (boolean)
- `scope` (string)
- `task` (string, required)
- `top_k` (integer)

Output parameters:

- `result` (string)

### `find_decisions` (~238 tokens)

Find the team's already-settled decisions about a topic — or the decisions that govern a specific code path. Call this whenever the user (or you) asks 'what did we decide about X', 'is X ruled out', 'did we already decide this', 'what's our policy on X', or before proposing, changing, or arguing for anything a prior decision might have settled — so you respect recorded decisions instead of re-litigating them. Pass `topic` for a keyword query, or pass `path` (a repository file or directory) to get the decisions whose declared scope governs that code — the recorded decisions that constrain an edit there. Returns the live (Accepted, non-retired) decisions, each with its identifier, title, and path; a topic query ranks by relevance with category and a snippet, a path query reports each decision's status and the matching declared scope. It tells you which decisions bind; read them and judge for yourself — it does not decide whether a change contradicts them. Use get_artifact to read a decision's full text.

Input parameters:

- `path`
- `topic` (string)

Output parameters:

- `result` (string)

### `get_related` (~122 tokens)

List the artifacts connected to one artifact in this repository's product knowledge: the references it declares and the artifacts that reference it. Call this after retrieving an artifact, and before changing anything it covers, to find the decisions, requirements, designs, and roadmaps the change could affect. Pass depth>1 (up to 5) to also return a `neighborhood` of artifacts two or more hops out, each tagged with its hop distance, when you need transitive context rather than immediate neighbours.

Input parameters:

- `depth` (integer)
- `id` (string, required)

Output parameters:

- `result` (string)

### `get_summary` (~64 tokens)

Get an overview of this repository's recorded product knowledge: artifact counts by type, validation state, relationship health, and items needing attention. Call this once at the start of a session, before exploring or changing the repository, to learn what recorded knowledge exists and where it needs care.

Output parameters:

- `result` (string)

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/asdecided-core/ghcr-io-asdecided-core-mcp-v0-26-2#diagnostics

## Score history

- 2026-08-03: 35
- 2026-08-02: 35
- 2026-08-01: 9

## Links

- Repository: https://github.com/asdecided/core
- Website: https://asdecided.com/
- Changelog RSS feed: https://verifymcp.io/servers/asdecided-core/ghcr-io-asdecided-core-mcp-v0-26-2/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/asdecided-core/ghcr-io-asdecided-core-mcp-v0-26-2/changelog.json
- HTML version of this page: https://verifymcp.io/servers/asdecided-core/ghcr-io-asdecided-core-mcp-v0-26-2