Is io.github.wraelen/framescli safe to use?

io.github.wraelen/framescli has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments.

How do I install io.github.wraelen/framescli?

io.github.wraelen/framescli can be installed by cloning its GitHub repository and following the setup instructions in the README.

Is io.github.wraelen/framescli actively maintained?

io.github.wraelen/framescli is actively maintained — last commit was 0 days ago. It has 2 GitHub stars.

io.github.wraelen/framescli

Make videos AI-readable. Extract timestamped frames and transcripts from any video for AI agents.

ActiveNot tested

Entertainment AI / ML

★ 2GitHub

27DNo CVEsactive

Quick Install

{
  "mcpServers": {
    "io-github-wraelen-framescli": {
      "command": "<see-readme>",
      "args": []
    }
  }
}

Setup guide

No install config available. Check the server's README for setup instructions.

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/io-github-wraelen-framescli)](https://mcppedia.org/s/io-github-wraelen-framescli)

Should you use this server?

Make videos AI-readable. Extract timestamped frames and transcripts from any video for AI agents.

✓

Is it safe?

No package registry to scan.

No authentication — any process on your machine can connect.

License not specified.

✓

Is it maintained?

Last commit 0 days ago. 2 stars.

Will it work with my client?

Transport: stdio. Works with Claude Desktop, Cursor, Claude Code, and most MCP clients.

README

FramesCLI

FramesCLI lets AI agents "watch" videos. Extract frames and transcripts from any video so Claude, ChatGPT, or other AI assistants can analyze the visual and audio content.

Tell your AI: "Use framescli to watch this video and tell me what happens" — and it actually can.

Now available in the official MCP Registry! Install FramesCLI in any MCP-compatible client (Claude Desktop, Cursor, Cline, Windsurf, etc.).

What Your AI Can Do

Once FramesCLI extracts frames and transcripts, your AI agent can:

Analyze screen recordings: "What error appeared at 2:30?" → Agent sees the frames and reads the transcript
Understand tutorials: "Summarize the steps in this demo" → Agent follows the visual timeline
Review meetings: "What decisions were made?" → Agent reads transcript + sees presentation slides in frames
Debug issues: "When did the app crash?" → Agent correlates visual state with spoken context
Extract insights: "What was covered in this lecture?" → Agent processes both visual and audio content

How It Works

You provide a video (screen recording, meeting, tutorial, anything)
FramesCLI extracts:
- Visual timeline: frames at configurable intervals (1fps, 4fps, 8fps)
- Audio content: full transcript with word-level timestamps
- Structured metadata: JSON with frame paths, timings, and transcript segments
Your AI agent reads the artifacts and can "watch" the video through the extracted frames + transcript
Local-first: All processing happens on your machine using ffmpeg and whisper (no cloud required)

For AI Coding Assistants

FramesCLI makes any video AI-readable. If you're an AI coding assistant, use FramesCLI to turn videos into structured, searchable artifacts your users can reference and analyze:

Quick Setup (30 seconds)

Verify installation:
```
framescli doctor --json
```

Configure MCP (recommended) in your client config:

{
  "mcpServers": {
    "framescli": {
      "command": "framescli",
      "args": ["mcp"]
    }
  }
}

First extraction workflow:

1. Call: doctor (verify tools)
2. Call: prefs_set (configure paths)
3. Call: preview (estimate cost)
4. Call: extract (process video)
5. Call: get_latest_artifacts (retrieve results)

Why Agents Should Use This

Structured outputs: All commands support --json with stable schema
MCP integration: 10 tools for video analysis via Model Context Protocol
Cost estimation: preview command provides frame count, disk usage, transcript time before extraction
Resumable workflows: Chunked transcription with manifest-based resume
Path safety: MCP enforces allowed input/output roots

Agent-Specific Documentation

Complete integration guide: docs/AGENT_INTEGRATION.md
Copy-paste workflows: [docs/AGENT_RECIPES.md](do

... View full README on GitHub

Test This Server

No automated test available for this server. Check the GitHub README for setup instructions.

Help improve this page

This server is missing a description. Tools and install config are also missing.If you've used it, help the community.

Add information

Score Breakdown

MCPpedia Score

Click each category to see evidence

27D

Last scored 6h ago

How we score →

Security

2/30

No known vulnerabilities.

○

Known CVEs — No package registry to scan

○

Tool safety — No tools to analyze

○

Tool poisoning — No tools to analyze

○

Injection vectors — No tools to analyze

○

Tool stability — First scan — baseline recorded

○

Dependency health — No package to analyze

✗

License — No license specified

○

Authentication — No authentication required

○

Repository — active repo

CVEs checked daily via OSV.dev. Score algorithm is open source.

Reviews

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is io.github.wraelen/framescli safe to use?: io.github.wraelen/framescli has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments.
How do I install io.github.wraelen/framescli?: io.github.wraelen/framescli can be installed by cloning its GitHub repository and following the setup instructions in the README.
What AI clients work with io.github.wraelen/framescli?: io.github.wraelen/framescli is compatible with Claude Desktop, Cursor, Claude Code, and most MCP clients that support stdio transport. It uses stdio transport.
Is io.github.wraelen/framescli actively maintained?: io.github.wraelen/framescli is actively maintained — last commit was 0 days ago. It has 2 GitHub stars.

Similar servers

View all →

Sequential Thinking MCP Server

Official

No CVEs98A

Dynamic problem-solving through sequential thought chains

1 toolsstdio83.8k111.0k/wk1d ago

XcodeBuildMCP

Official

No CVEs97A

A Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.

2 toolsremote5.2k46.6k/wk1d ago

Python Sdk

Official

No CVEs95A

The official Python SDK for Model Context Protocol servers and clients

1 toolsremote22.6k156.5k/wk21h ago

Gemini Cli

No CVEs95A

An open-source AI agent that brings the power of Gemini directly into your terminal.

8 toolsremote101.3k814.6k/wk12h ago

MCP Security Weekly

Get CVE alerts and security updates for io.github.wraelen/framescli and similar servers.

Discussion

Start a conversation

Ask a question, share a tip, or report an issue.

Has anyone used this with Cursor?How do you handle auth?Any alternatives?

FramesCLI

FramesCLI lets AI agents "watch" videos. Extract frames and transcripts from any video so Claude, ChatGPT, or other AI assistants can analyze the visual and audio content.

Tell your AI: "Use framescli to watch this video and tell me what happens" — and it actually can.

Now available in the official MCP Registry! Install FramesCLI in any MCP-compatible client (Claude Desktop, Cursor, Cline, Windsurf, etc.).

What Your AI Can Do

Once FramesCLI extracts frames and transcripts, your AI agent can:

Analyze screen recordings: "What error appeared at 2:30?" → Agent sees the frames and reads the transcript
Understand tutorials: "Summarize the steps in this demo" → Agent follows the visual timeline
Review meetings: "What decisions were made?" → Agent reads transcript + sees presentation slides in frames
Debug issues: "When did the app crash?" → Agent correlates visual state with spoken context
Extract insights: "What was covered in this lecture?" → Agent processes both visual and audio content

How It Works

You provide a video (screen recording, meeting, tutorial, anything)
FramesCLI extracts:
- Visual timeline: frames at configurable intervals (1fps, 4fps, 8fps)
- Audio content: full transcript with word-level timestamps
- Structured metadata: JSON with frame paths, timings, and transcript segments
Your AI agent reads the artifacts and can "watch" the video through the extracted frames + transcript
Local-first: All processing happens on your machine using ffmpeg and whisper (no cloud required)

For AI Coding Assistants

FramesCLI makes any video AI-readable. If you're an AI coding assistant, use FramesCLI to turn videos into structured, searchable artifacts your users can reference and analyze:

Quick Setup (30 seconds)

Verify installation:
```
framescli doctor --json
```

Configure MCP (recommended) in your client config:

{
  "mcpServers": {
    "framescli": {
      "command": "framescli",
      "args": ["mcp"]
    }
  }
}

First extraction workflow:

1. Call: doctor (verify tools)
2. Call: prefs_set (configure paths)
3. Call: preview (estimate cost)
4. Call: extract (process video)
5. Call: get_latest_artifacts (retrieve results)

Why Agents Should Use This

Structured outputs: All commands support --json with stable schema
MCP integration: 10 tools for video analysis via Model Context Protocol
Cost estimation: preview command provides frame count, disk usage, transcript time before extraction
Resumable workflows: Chunked transcription with manifest-based resume
Path safety: MCP enforces allowed input/output roots

Agent-Specific Documentation

Complete integration guide: docs/AGENT_INTEGRATION.md
Copy-paste workflows: [docs/AGENT_RECIPES.md](do

... View full README on GitHub