Borrowing it
Nothing to install: this file belongs to wawimundo/viber-mcp. 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/wawimundo/viber-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/wawimundo/viber-mcpWrote 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/wawimundo/viber-mcp/claude-md)<a href="https://agentmods.dev/instructions/wawimundo/viber-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/wawimundo/viber-mcp/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/wawimundo/viber-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/wawimundo/viber-mcp/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 | $0.02068 | $0.02068 |
| Opus 5.5 | $0.00827 | $0.00827 |
| Sonnet 5.5 | $0.00414 | $0.00414 |
| Haiku 4.5 | $0.00207 | $0.00207 |
Grade A, and why
viber-mcp 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 2mo 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 — 133 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.
What this is
A macOS-only MCP server that sends and reads Viber Desktop messages by automating the running,
signed-in Viber app — Viber has no API, its message DB is encrypted, and its Qt accessibility tree
is unusable, so everything is done via the viber:// URL scheme, synthetic HID input, and screen OCR.
Commands
uv sync # install deps (Python managed by uv)
# Standalone client = the way to test/run tools without Claude (spawns a fresh server each call,
# so it always uses the latest code). Subcommands map 1:1 to tools:
uv run client.py list # advertise tools
uv run client.py open|openread|search "<name-or-+E164>"
uv run client.py send "<to>" "<text>" [--dry-run]
uv run client.py reply "<text>" # into the currently-open chat
uv run client.py draft "<text>" # paste into open chat, do NOT send
uv run client.py note "<text>" # save to My Notes
uv run client.py chats | read | contacts
# Register with Claude Code (user scope):
claude mcp add --transport stdio --scope user viber -- uv --directory "$(pwd)" run server.py
There is no test suite, linter, or build step. Verify changes by driving the real app with
client.py and screenshotting the Viber window (viber_ocr.capture_window) to confirm the outcome —
the returned verified flag is best-effort and gives false negatives.
After editing server code, the registered MCP server keeps running the old code until reconnected
(/mcp → reconnect viber, or restart Claude Code); client.py always runs fresh code.
Architecture
The code is split into platform-neutral domain logic and a platform Backend (so the app is port-ready for Windows/Linux — see "Porting" below):
server.py— FastMCP stdio server; thin@mcp.tool()wrappers only. Tools:send_message,reply,open_chat,open_and_read,read_open_chat,list_chats,put_draft,search_and_open,save_to_my_notes,open_my_notes,list_contacts.viber_send.py— platform-neutral write/navigation logic: recipient resolution (contacts.jsonalias → E.164), the send pipeline, search-result scoring, panel detection, send verification. Holds a module-levelbackend = get_backend()and calls only its semantic methods. RaisesSendError.viber_ocr.py— platform-neutral read side:read_open_chat()/read_chat_list()formatbackend.observe()output (read_chat_listkeeps only left-column x<0.30). RaisesOCRError.backends/— the platform layer.base.py—BackendABC +OCRError. Semantic interface:app_running/focus/open_url,observe()→[{text,x,y}], clipboard,type_text/select_all/delete/paste, and element clicksclick_compose/send/search/result(norm_y)/panel_close. The domain never sees pixels or key codes.macos.py—MacBackend: all Quartz/Vision/AppKit code AND the macOS Viber-layout constants (element pixel/fraction offsets). This is the only file with OS APIs.__init__.py—get_backend()picks the backend bysys.platform(macOS only today).
client.py— standalone MCP stdio client for testing.contacts.json— name→E.164 map, git-ignored (real numbers); shipcontacts.example.json.
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.
- 2mo ago First seen · 133 lines · 2,068 tokens per session scan A 1fd0bfe52bbe
viber-mcp CLAUDE.md is an instructions file published in the GitHub repository wawimundo/viber-mcp (0 stars, last pushed 4mo ago), licensed MIT. It adds 2,068 tokens to every session, about $0.0083 per session on Opus 5.5. 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.
viber-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| viber-mcp CLAUDE.mdwawimundo/viber-mcp | Instructions file | 0 | 4mo ago | MIT | A | 2,068 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |