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.
npx agentmods add instructions/cloudglue/cloudglue-mcp-server/claude-mdgit clone --depth 1 https://github.com/cloudglue/cloudglue-mcp-serverWrote 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.
[](https://agentmods.dev/instructions/cloudglue/cloudglue-mcp-server/claude-md)<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>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.
| Model | Per session | Once 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 |
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.
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
schemafor 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 videosdescribe-video,get-video-metadata- Video details and transcriptsextract-video-entities- Structured entity extractionretrieve-summaries- Bulk summary retrievalsearch-video-moments,search-video-summaries- Semantic searchsegment-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.
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.
- 4d ago First seen · 59 lines · 537 tokens per session scan A a1012d041f2b
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.
Other instructions, from other repositories
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
ai-toolkit AGENTS.md
AGENTS.md instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).
flyto-core CLAUDE.md
Claude Code instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.