Borrowing it
Nothing to install: this file belongs to byaan-ai/byaan. 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/byaan-ai/byaan/main/.agents/skills/byaan:mcp-setup/SKILL.mdgit clone --depth 1 https://github.com/byaan-ai/byaanWrote 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/skills/byaan-ai/byaan/byaan-mcp-setup)<a href="https://agentmods.dev/skills/byaan-ai/byaan/byaan-mcp-setup"><img src="https://agentmods.dev/badge/skills/byaan-ai/byaan/byaan-mcp-setup/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/skills/byaan-ai/byaan/byaan-mcp-setup"><img src="https://agentmods.dev/badge/skills/byaan-ai/byaan/byaan-mcp-setup.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 | $0.00061 | $0.01299 |
| Opus 5.5 | $0.00024 | $0.00520 |
| Sonnet 5.5 | $0.00012 | $0.00260 |
| Haiku 4.5 | $0.00006 | $0.00130 |
Grade C, and why
byaan:mcp-setup scanned grade C with 2 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 1mo 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ~/.codex/config.toml 2>/dev/null || echo "" Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
cat ~/.cursor/mcp.json 2>/dev/null || echo "{}" How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an MCP configuration assistant. Your job is to connect Byaan's MCP server to the user's AI coding assistant so they can query databases directly from their editor or terminal.
Important: This skill is for the local community/dev version of Byaan only. If the user is running the Mac desktop app (Tauri), tell them:
The Mac desktop app configures MCP through its built-in UI. Open the Byaan app and click the MCP icon to get setup instructions.
Step 1: Detect Environment
First, confirm we are in the Byaan project directory by checking for the project marker:
test -f pyproject.toml && echo "BYAAN_PROJECT_FOUND" || echo "NOT_FOUND"
If NOT_FOUND, look for clues:
ls server/mcp/stdio_server.py 2>/dev/null && echo "FOUND" || echo "NOT_FOUND"
If still not found, ask the user for the path to their Byaan project directory.
Set PROJECT_ROOT to the absolute path of the Byaan project root (the directory containing pyproject.toml).
Step 2: Verify Prerequisites
Check that uv is installed:
command -v uv && echo "UV_OK" || echo "UV_MISSING"
If missing, tell the user:
uvis required to run the Byaan MCP server. Install it: https://docs.astral.sh/uv/
Check that the database exists (the app must have been run at least once):
test -f server/.data/app.db && echo "DB_OK" || echo "DB_MISSING"
If the database is missing, tell the user:
Please run Byaan at least once to initialize the database before configuring MCP. You can start it with:
cd <PROJECT_ROOT> && make dev
Step 3: Ask User Which Tool to Configure
Ask the user which AI assistant they want to connect Byaan to. The options are:
- Claude Code - Uses
claude mcp add-jsonCLI command - Cursor - Edits
~/.cursor/mcp.jsonconfig file - Codex CLI - Edits
~/.codex/config.tomlconfig file - All of the above - Configure all three
Step 4: Build the MCP Configuration
The stdio MCP config for Byaan uses these values:
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.
- 1mo ago First seen · 153 lines · 61 tokens per session scan C 5cd469653bcb
byaan:mcp-setup is a skill published in the GitHub repository byaan-ai/byaan (97 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 1,299 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 2 findings (reads agent configuration directories, reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
txtify-transcribe
Transcribe audio, video files, or YouTube links into text and subtitles (txt, srt, vtt, sbv, pdf) using the user's own self-hosted Txtify instance (open-source, Whisper-based, runs locally in Docker). Use when the user wants a transcript or subtitle file from media and is fine running Txtify on their machine, or…
plausible-analytics
Privacy-friendly web analytics with Plausible.
meetily
A meeting assistant that runs entirely on the local computer: it captures audio, transcribes speech with Parakeet or Whisper, and uses Ollama or another language model to create summaries. No cloud service is required.
experiment-tracking-swanlab
Provides guidance for experiment tracking with SwanLab. Use when you need open-source run tracking, local or self-hosted dashboards, and lightweight media logging for ML workflows.
debugging-executions
Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error. Also load when a live run you started for the user fails with an error from…
standardize-health-data
Turn raw health data into standardized data, and read a lab report without guessing. A lab report PDF, photo, spreadsheet or CSV becomes readings with LOINC codes and UCUM units; an Apple Health export becomes JSON lines; a symptom or diagnosis in any language becomes an ICPC-3 code; any reading becomes a FHIR…