ilinxa-captureSAFE
Extract video frames and compose AI-readable grid sheets for multimodal LLM pipelines, self-hosted via REST, Web UI, or MCP.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Video frame extraction & composition service for AI vision pipelines.
[](https://raw.githubusercontent.com/yuniirhm/ilinxa-capture/main/ui/capture-ilinxa-3.7.zip) [](LICENSE)
ilinxa capture extracts video frames and tiles them into 2×2 or 4×4 grid sheets a multimodal LLM can read in one image — self-hosted, via a REST API, a Web UI, or an MCP server. Instead of sending a model dozens of separate frames, you send one contact sheet, with optional frame-number and timestamp overlays so the model can still reason about time. One core engine backs all three interfaces, reachable however your pipeline prefers:
Table of contents
- Demo
- Features
- Quick start
- Usage
- REST API
- Web UI
- MCP server
- Configuration
- Architecture
- Development
- Testing
- Security model
- FAQ
- Contributing
- Support
- License
Demo
9dec2fee688dOBSERVED · 2026-10-12Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add ilinxa-capture-ui -- npx -y [email protected]
{
"mcpServers": {
"ilinxa-capture-ui": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (8)
8 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
capture_compose | read | |
capture_extract | read | |
capture_extract_and_compose | read | |
capture_hls_discover | read | |
capture_job_status | read | |
capture_metadata | read | |
capture_video_download | read | |
capture_video_formats | read |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (3 observation(s))
- Network
- declared (3 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (13)
capture-ilinxa-3.7.zip
.prettierignore
url: `/api/v1/files/${jobId}/frames/../../../etc/passwd`,import type { JobManager, TaskFunction } from "../../core/job-manager.js";import { ValidationError } from "../../utils/errors.js";storage.fileExists("cap_abc", "../../../etc/passwd"),storage.getFileStream("cap_abc", "../../etc/passwd"),baseUrl = `http://127.0.0.1:${address.port}`;const baseUrl = new URL(`http://127.0.0.1:${address.port}/mcp`);@fastify/cors, @fastify/error, @fastify/helmet, @fastify/multipart, @fastify/sensible, @fastify/static, @modelcontextprotocol/sdk, archiver
@tanstack/react-query, @tanstack/react-query-devtools, class-variance-authority, clsx, lucide-react, radix-ui, react, react-dom
Sessions are tracked via the `mcp-session-id` header (UUID format). The server creates a session on the first `POST` and returns the session ID in the response header.
assets/brand/demo.gif
Gates applied: no_behavioural_pass.
9dec2fee688dfull audit observations/trust-audit/mcp-server/yuniirhm__ilinxa-capture.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-12 | 9dec2fee688d | SAFE | B | 89 | first audit |
Questions
What is the ilinxa-capture MCP server?
Extract video frames and compose AI-readable grid sheets for multimodal LLM pipelines, self-hosted via REST, Web UI, or MCP.
What tools does ilinxa-capture expose?
8 in total: 8 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is ilinxa-capture safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does ilinxa-capture need?
No credential environment variables were found in its source, so it appears to need none.
How does ilinxa-capture run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as ilinxa-capture-ui at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (9dec2fee688d), read on 2026-10-12. The repository is watched and re-audited when it changes.