# videoctx (pypi · videoctx)

Read videos like images: index once locally, query the text layer, fetch frames on demand.

- Trust score: 80/100 (high trust)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- pypi · `videoctx`: 80/100 (this document), [markdown](https://verifymcp.io/servers/dunfred-videoctx/videoctx.md), [page](https://verifymcp.io/servers/dunfred-videoctx/videoctx)

## Channel facts

- Registry: `pypi`
- Package: `videoctx`
- Version: `0.1.5`
- 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 2026-10-23.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 3 of 54 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to dunfred/videoctx).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 0 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 67/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 581 tokens (~96/item across 6 items; 6 tools + 0 resources), lean.
  - 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**: 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 (50% 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.
  - We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the videoctx MCP server?

videoctx runs locally as a PyPI package, launched with uvx videoctx. 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 dunfred-videoctx -- uvx videoctx
```

### Cursor

```json
{
  "mcpServers": {
    "dunfred-videoctx": {
      "command": "uvx",
      "args": [
        "videoctx"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "dunfred-videoctx": {
      "command": "uvx",
      "args": [
        "videoctx"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add dunfred-videoctx -- uvx videoctx
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dunfred-videoctx": {
      "type": "local",
      "command": [
        "uvx",
        "videoctx"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dunfred-videoctx --command uvx --arg videoctx
```

### Hermes

```yaml
mcp_servers:
  dunfred-videoctx:
    command: "uvx"
    args: ["videoctx"]
```

### Netclaw

```json
{
  "McpServers": {
    "dunfred-videoctx": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "videoctx"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add dunfred-videoctx -t stdio -c uvx -a videoctx
```

### Other

```json
{
  "mcpServers": {
    "dunfred-videoctx": {
      "command": "uvx",
      "args": [
        "videoctx"
      ]
    }
  }
}
```

## 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.

### 2026-10-23 (score 80, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-10-22 (score 64, +11)

- [security improvement] Provenance: fail → pass
- [security] The attested source repository moved: dunfred/videoctx
- [functional] Package version: 0.1.4 → 0.1.5

### 2026-10-21 (score 53, −14)

- [security regression] Malware scan: pass → unverified
- [functional regression] Schema quality: 464 → 581
- [functional regression] Tool coverage: 60% → 50%
- [functional improvement] Stability: unverified → 0.10
- [functional] Package version: 0.1.2 → 0.1.4

### 2026-10-19 (score 67, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-18 (score 52)

First indexed and scored.

## MCP tools (6)

### `index_video` (~81 tokens)

Index a video file for querying (shots, keyframes, speech transcript).
Runs locally; takes roughly 10-20% of the video's duration. Idempotent -
returns immediately if the video is already indexed. The other tools
auto-index too, so calling this first is only needed to control when the
wait happens.

Input parameters:

- `path` (string, required)

Output parameters:

- `result` (string)

### `video_overview` (~60 tokens)

The cheap text layer of a video: shot list with timestamps and visual
captions (when present), interleaved with the speech transcript. Read this
before fetching any frames: it answers most questions by itself.

Input parameters:

- `path` (string, required)

Output parameters:

- `result` (string)

### `survey_video` (~58 tokens)

One small thumbnail per shot across the whole video (subsampled to at
most 24), each labeled with its timestamp. Cheap visual sweep for locating
the relevant moment before zooming in with get_frames.

Input parameters:

- `path` (string, required)

### `get_frames` (~122 tokens)

Frames evenly spaced across [start_s, end_s]. Frames are expensive: use
the narrowest range the question allows, and raise max_frames (up to 8)
only when a sparse sample missed the moment. Set detail='high' (2x
resolution, ~4x token cost) when small text, colors, patterns, or fine
object details matter.

Input parameters:

- `detail` (string)
- `end_s` (number, required)
- `max_frames` (integer)
- `path` (string, required)
- `start_s` (number, required)

### `find_moments` (~117 tokens)

Semantic visual search: find the moments that best match a natural
language description (e.g. 'a red car at night'), using local CLIP
embeddings. Returns the top matches as timestamped thumbnails: use the
timestamps to zoom in with get_frames. Requires embeddings built once
with `videoctx embed <index>`; cheaper and more targeted than
survey_video when you know what you are looking for.

Input parameters:

- `description` (string, required)
- `path` (string, required)
- `top_k` (integer)

### `transcript_search` (~57 tokens)

Case-insensitive search over the transcript. Returns matching segments
with surrounding context and timestamps: use the timestamps to target
get_frames.

Input parameters:

- `context_s` (number)
- `path` (string, required)
- `query` (string, required)

Output parameters:

- `result` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/dunfred-videoctx/videoctx#diagnostics

## Score history

- 2026-10-23: 80
- 2026-10-22: 64
- 2026-10-21: 53
- 2026-10-20: 67
- 2026-10-19: 67
- 2026-10-18: 52

## Common questions

### What is the videoctx MCP server?

videoctx is an MCP server listed in the public MCP registry as io.github.dunfred/videoctx. Read videos like images: index once locally, query the text layer, fetch frames on demand. This page covers its PyPI package (videoctx).

### Is the videoctx MCP server safe to use?

videoctx scores 80 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 23 October 2026. Its build provenance is signed and verified. 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 videoctx MCP server expose?

videoctx exposes 6 tools: index_video, video_overview, survey_video, get_frames, find_moments, transcript_search. Their descriptions and schemas cost roughly 495 tokens of context every time the server is loaded.

### Is the videoctx MCP server still maintained?

videoctx is still listed as active in the MCP registry. We last reached this channel on 23 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the videoctx MCP server under?

videoctx declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/videoctx/
- Socket report: https://socket.dev/pypi/package/videoctx
- Repository: https://github.com/dunfred/videoctx
- Changelog RSS feed: https://verifymcp.io/servers/dunfred-videoctx/videoctx.xml
- Changelog JSON feed: https://verifymcp.io/servers/dunfred-videoctx/videoctx.json
- HTML version of this page: https://verifymcp.io/servers/dunfred-videoctx/videoctx