mcpField
C
clipquery

clipquery

Local
github.com/CloudCorpRecordsSearch0Updated 1w ago
Repository

About clipquery

clipquery is a natural-language search client for personal video libraries processed by Flashback. It returns matching segments with descriptions, relevance scores, viewing links, and link expiry times.

Key features

  1. 01Search video segments in natural language
  2. 02Return AI-generated segment descriptions
  3. 03Include relevance scores and viewing URLs
  4. 04Provide URL expiry times
  5. 05CLI and stdio MCP server

Use cases

  1. 01Find a segment showing a person talking
  2. 02Locate a discussion about deadlines
  3. 03Review matching clips with their relevance scores

MCP support

Its MCP server provides query_videos for searching clips and get_setup_instructions for local setup guidance. Video queries require FLASHBACK_USER_ID and FLASHBACK_API_BASE_URL.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "cloudcorprecords-clipquery": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/clipquery"
      ]
    }
  }
}
Run commandnpx -y @reneturcios/clipquery

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@reneturcios/clipquery0.1.0
ocighcr.io/cloudcorprecords/clipquery:0.1.0

Tools

2

Saved tool list · updated 1w ago

ParameterTypeRequiredDescription
querystringYesNatural language description of what you're looking for
max_resultsintegerNoMaximum number of results to return (1-15)

Details

From the project README

clipquery

Search a personal video library with natural language. Videos processed by the Flashback system are split into ~30-second segments, analysed for visual content, transcribed, and embedded; a query is matched semantically against those segments, and each result comes back with an AI-generated description, a relevance score (0–1), a direct URL to view the segment, and the time that URL expires. Presigned URLs expire after 1 hour — run the query again for fresh ones.

Configuration

Two environment variables are required for query_videos:

  • FLASHBACK_USER_ID — your unique Flashback account identifier (e.g. 4087fce3-3d86-4047-b35f-4004b4c19192)
  • FLASHBACK_API_BASE_URL — the base URL of the Flashback video processing API. The upstream publishes no default, so this must be set; a missing value is an error naming the variable, raised before any request.

get_setup_instructions is local and needs no configuration.

CLI

npx @reneturcios/clipquery query "person talking" --max-results 5
npx @reneturcios/clipquery query "meeting discussion about deadlines"
npx @reneturcios/clipquery setup
npx @reneturcios/clipquery --version

Exit codes: 0 on success, 1 on a runtime error (including missing configuration), 2 on a usage error.

MCP server

npx -y @reneturcios/clipquery mcp

MCP client config:

{
  "mcpServers": {
    "clipquery": {
      "command": "npx",
      "args": ["-y", "@reneturcios/clipquery", "mcp"],
      "env": {
        "FLASHBACK_USER_ID": "your-flashback-user-id",
        "FLASHBACK_API_BASE_URL": "https://your-flashback-api-host"
      }
    }
  }
}
Tools
  • query_videos — Search for video clips based on natural language query. query (string, required) — natural language description of what you're looking for; max_results (integer, optional, default 10) — maximum number of results to return (1–15).
  • get_setup_instructions — Get detailed setup instructions for the video query system. No parameters.

The server also mirrors the upstream's documented resource URI concept in its guide text only; no MCP resources are served.

Docker

docker run -i -e FLASHBACK_USER_ID -e FLASHBACK_API_BASE_URL ghcr.io/cloudcorprecords/clipquery
docker run --rm ghcr.io/cloudcorprecords/clipquery setup

Development

npm install
npm run build   # tsc -> dist/
npm test        # tsx --test test/*.test.ts (fake fetch only, no network)
npm run dev     # run the CLI from source

License

MIT — Copyright (c) 2026 Rene Turcios

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.