# File AI (npm · @flyfish-dev/file-ai)

Agent-ready local document context with stable anchors.

- Trust score: 64/100 (medium)
- Change this week: +45
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-07

## Components

- npm · `@flyfish-dev/file-ai`: 64/100 (this document), [markdown](https://verifymcp.io/servers/flyfish-dev-file-ai/flyfish-dev-file-ai.md), [page](https://verifymcp.io/servers/flyfish-dev-file-ai/flyfish-dev-file-ai)

## Channel facts

- Registry: `npm`
- Package: `@flyfish-dev/file-ai`
- Version: `0.1.1`
- 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 2026-08-07.

- **Supply Chain Security**: 88/100
  - No malware found by supply-chain analysis.
  - A known CVE affects xlsx, but no fixed version has been published, so there is nothing to upgrade to.
  - No install/post-install scripts declared.
  - Dependency health was assessed across the 152 of 156 dependencies we could resolve, so this covers what we could see, not the whole tree.
- **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 43 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 49/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 357 tokens (~71/item across 5 items; 5 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 40/100
  - Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 76/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 29% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add flyfish-dev-file-ai -- npx -y @flyfish-dev/file-ai
```

### Codex

```bash
codex mcp add flyfish-dev-file-ai -- npx -y @flyfish-dev/file-ai
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "flyfish-dev-file-ai": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@flyfish-dev/file-ai"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add flyfish-dev-file-ai --command npx --arg -y --arg @flyfish-dev/file-ai
```

### Hermes

```yaml
mcp_servers:
  flyfish-dev-file-ai:
    command: "npx"
    args: ["-y", "@flyfish-dev/file-ai"]
```

### Other

```json
{
  "mcpServers": {
    "flyfish-dev-file-ai": {
      "command": "npx",
      "args": [
        "-y",
        "@flyfish-dev/file-ai"
      ]
    }
  }
}
```

## 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.

### 2026-08-07 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-05 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-04 (score 62, +4)

- [functional improvement] Stability: unverified → 0.30

### 2026-08-02 (score 58, +39)

- [security regression] CVE-2023-30533 affects this package
- [security regression] CVE-2024-22363 affects this package
- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] License: unverified → pass
- [functional improvement] Schema quality: unverified → fair
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Schema quality: unverified
- [functional] Licence: Apache-2.0

### 2026-07-31 (score 19, −6)

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

### 2026-07-30 (score 25, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-27 (score 43)

First indexed and scored.

## MCP tools (5)

### `doc_analyze` (~103 tokens)

Analyze document

Parse a local document into a read-only profile, anchors, outline, blocks, and chunks for agent context.

Input parameters:

- `chunkOverlap` (integer): Chunk overlap in characters.
- `chunkSize` (integer): Target chunk size in characters.
- `maxTextLength` (integer): Maximum text characters per source anchor before chunking.
- `path` (string, required): Local file path to analyze.
- `refresh` (boolean): Re-parse even if this path is already cached.

### `doc_read` (~89 tokens)

Read document index content

Read blocks, chunks, or anchors from a cached index without inspecting source document internals.

Input parameters:

- `anchorId` (string)
- `blockId` (string)
- `chunkId` (string)
- `indexId` (string): Cached document index id from doc_analyze.
- `limit` (integer)
- `path` (string): Analyze this path if indexId is not supplied.

### `doc_search` (~64 tokens)

Search document content

Search document blocks and return excerpts tied to stable anchors.

Input parameters:

- `caseSensitive` (boolean)
- `contextChars` (integer)
- `indexId` (string)
- `limit` (integer)
- `path` (string)
- `query` (string, required)

### `doc_context` (~73 tokens)

Read contextual document window

Return nearby blocks around an anchor or the first anchors matching a query.

Input parameters:

- `after` (integer)
- `anchorId` (string)
- `before` (integer)
- `indexId` (string)
- `limit` (integer)
- `path` (string)
- `query` (string)

### `doc_list_formats` (~28 tokens)

List supported formats

List File Viewer core registry formats, supported extensions, renderer capabilities, and File AI extractor coverage.

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/flyfish-dev-file-ai/flyfish-dev-file-ai#diagnostics

## Score history

- 2026-08-07: 64
- 2026-08-06: 63
- 2026-08-05: 63
- 2026-08-04: 62
- 2026-08-03: 58
- 2026-08-02: 58
- 2026-08-01: 19
- 2026-07-31: 19
- 2026-07-30: 25
- 2026-07-28: 43
- 2026-07-27: 43

## Links

- npm package: https://www.npmjs.com/package/@flyfish-dev/file-ai
- Socket report: https://socket.dev/npm/package/@flyfish-dev/file-ai
- Repository: https://github.com/flyfish-dev/file-ai
- Changelog RSS feed: https://verifymcp.io/servers/flyfish-dev-file-ai/flyfish-dev-file-ai.xml
- Changelog JSON feed: https://verifymcp.io/servers/flyfish-dev-file-ai/flyfish-dev-file-ai.json
- HTML version of this page: https://verifymcp.io/servers/flyfish-dev-file-ai/flyfish-dev-file-ai