cloudglue-mcp-server CLAUDE.md

cloudglue-mcp-server CLAUDE.md is an instructions file for coding agents from cloudglue/cloudglue-mcp-server. It costs 537 tokens per session, scanned A, original, MIT.

Repository instructions for a server that connects AI assistants to Cloudglue's video-analysis service.

In plain words
What is it for?
Use them when adding or changing tools for video collections, transcripts, metadata, entities, segments, or video search.
Why use it?
They document how to build and format the TypeScript server and how its video-analysis tools are organized.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/cloudglue/cloudglue-mcp-server/claude-md
Clone the repo
git clone --depth 1 https://github.com/cloudglue/cloudglue-mcp-server

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for cloudglue-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cloudglue/cloudglue-mcp-server/claude-md.svg)](https://agentmods.dev/instructions/cloudglue/cloudglue-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/cloudglue/cloudglue-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/cloudglue/cloudglue-mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 537 This file is loaded in full into every session.
When invoked 537 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00537 $0.00537
Opus 5 $0.00269 $0.00269
Sonnet 5 $0.00107 $0.00107
Haiku 4.5 $0.00054 $0.00054

Measured 4d ago against content hash a1012d041f2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cloudglue-mcp-server CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Cloudglue MCP Server - A Model Context Protocol server that bridges AI assistants (Claude, Cursor) with Cloudglue's video analysis platform. Enables AI to analyze videos, extract transcripts, identify entities, segment content, and search across video collections.

Common Commands

# Build the project (TypeScript compilation + MCP packaging)
npm run build

# Watch mode for development
npm run watch

# Format code with Prettier
npm run format

No dedicated test or lint commands are currently defined.

Architecture

Entry Point: src/index.ts initializes the McpServer, creates the Cloudglue client (via @cloudglue/cloudglue-js SDK), registers all tools, and connects via stdio transport.

Tool Pattern: Each tool in src/tools/ is a self-contained module that exports:

  • A Zod schema for input validation
  • A register[ToolName](server, cgClient) function that registers the tool with its handler

10 Tools Available:

  • list-collections, list-videos - Browse collections and videos
  • describe-video, get-video-metadata - Video details and transcripts
  • extract-video-entities - Structured entity extraction
  • retrieve-summaries - Bulk summary retrieval
  • search-video-moments, search-video-summaries - Semantic search
  • segment-video-camera-shots, segment-video-chapters - Video segmentation

Key Patterns

Pagination: Most tools return paginated results (25 items or 5-minute segments per page). Response includes page and total_pages fields.

Cost Optimization: Tools like describe_video check for existing results in collections and jobs before creating new ones.

URL Formats: Tools accept Cloudglue URLs (cg://), YouTube, HTTP, Dropbox, Google Drive, and Zoom URLs.

Error Handling: Consistent JSON error responses with error and details fields.

Tool Hints: Tools declare readOnlyHint, idempotentHint, and openWorldHint for MCP clients.

Read the full file on GitHub · 59 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 59 lines · 537 tokens per session scan A a1012d041f2b

Subscribe to this mod's changes

cloudglue-mcp-server CLAUDE.md is an instructions file published in the GitHub repository cloudglue/cloudglue-mcp-server (14 stars, last pushed 17d ago), licensed MIT. It adds 537 tokens to every session, about $0.0027 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.