Borrowing it
Nothing to install: this file belongs to vicseeai/vicsee-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vicseeai/vicsee-mcp-server/main/CLAUDE.mdgit clone --depth 1 https://github.com/vicseeai/vicsee-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/vicseeai/vicsee-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/vicseeai/vicsee-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/vicseeai/vicsee-mcp-server/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/vicseeai/vicsee-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/vicseeai/vicsee-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01103 | $0.01103 |
| Opus 5 | $0.00551 | $0.00551 |
| Sonnet 5 | $0.00221 | $0.00221 |
| Haiku 4.5 | $0.00110 | $0.00110 |
Grade A, and why
vicsee-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 9d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — VicSee MCP Server
Context file for Claude Code sessions.
What Is This?
A standalone MCP (Model Context Protocol) server that exposes the public
VicSee API (https://vicsee.com/api/v1) as agent tools, so AI
agent runtimes (Hermes, OpenClaw, Claude, Cursor) can generate, edit, and upscale AI video &
images via VicSee.
It is a thin proxy — no backend logic of its own. It wraps /api/v1 and authenticates with
the caller's VICSEE_API_KEY.
Layout
src/
├── index.ts # MCP server — registers the 6 tools, stdio transport
└── vicsee-client.ts # thin fetch client for /api/v1 (unwraps {success,data,error})
The 6 tools
vicsee_list_models, vicsee_generate, vicsee_get_task, vicsee_upscale_image,
vicsee_upscale_video, vicsee_get_credits.
Generation is async: vicsee_generate returns a task id; poll vicsee_get_task until
status === "completed" and read result.url.
API contract
See the published API docs at https://vicsee.com/docs/api for the authoritative reference.
- Base URL:
https://vicsee.com/api/v1(override viaVICSEE_BASE_URL) - Auth:
Authorization: Bearer sk-<key>(all tools exceptvicsee_list_models, which is public) - Envelope:
{ success, data, error: { code, message } }— the client unwrapsdata, throws on error generatebody:{ model, input: { prompt, image_urls, duration, aspect_ratio, resolution, ... } }tasks/{id}status:pending|processing|queued|completed|failed; result URL atresult.url- Result URLs are stable
cdn.vicsee.comlinks
Commands
pnpm build # tsc → dist/
pnpm dev # run from source (tsx)
pnpm typecheck # tsc --noEmit
VICSEE_API_KEY=sk-... node dist/index.js # run the stdio server
Releasing
Three independent channels. A change is not shipped until all three are current.
| Channel | Command | Notes |
|---|---|---|
Hosted connector (mcp.vicsee.com) |
npx wrangler deploy |
Use the stored wrangler OAuth session — env -u CLOUDFLARE_API_TOKEN -u CF_API_TOKEN if a token env var is set, it breaks the deploy. Most customers are on this one. |
npm (@vicsee/mcp-server) |
see below | Self-hosted agent builders. |
GitHub (vicseeai/vicsee-mcp-server) |
git push + tag v<version> |
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.
- 9d ago First seen · 95 lines · 1,103 tokens per session scan A 2cc84e89b898
vicsee-mcp-server CLAUDE.md is an instructions file published in the GitHub repository vicseeai/vicsee-mcp-server (0 stars, last pushed 3d ago), licensed MIT. It adds 1,103 tokens to every session, about $0.0055 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 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.