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/keboola/mcp-server/claude-mdgit clone --depth 1 https://github.com/keboola/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/keboola/mcp-server/claude-md)<a href="https://agentmods.dev/instructions/keboola/mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/keboola/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 | $0.02459 | $0.02459 |
| Opus 5 | $0.01229 | $0.01229 |
| Sonnet 5 | $0.00492 | $0.00492 |
| Haiku 4.5 | $0.00246 | $0.00246 |
Grade C, and why
mcp-server CLAUDE.md 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 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s "https://hub.docker.com/v2/repositories/keboola/mcp-server/tags/?page_size=20&name=production" | python3 -c "import sys,json; [print(t['name'], t['last_updated']) for t in json.load(sys.stdin)['results']]" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://hub.docker.com/v2/repositories/keboola/mcp-server/tags/?page_size=20&name=production" | How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Keboola MCP Server - Project Guide
Contributing Guidelines
See CONTRIBUTING.md for the authoritative contributor guide. It covers:
- RFC requirement — when a design doc in
feature_spec/<feature-name>/RFC.mdis required before implementation (new tools, new architectural concepts, new end-to-end behavior), and the required RFC structure - Testing requirements — regression tests for bug fixes, unit + E2E tests for features, and parametrize conventions
- PR checklist — the full set of items every PR must address (branch naming, version bump,
uv.lock,tox, RFC link, etc.)
The rules in this file (git workflow, versioning, venv setup) complement CONTRIBUTING.md — when the two overlap, CONTRIBUTING.md is the source of truth for contributor-facing process. Read it before opening a PR.
Git Workflow
- Always create a branch first before committing changes
- Branch names must start with the Linear issue ID and be short (e.g.,
AI-2480-whitelist-n8n-domains)- Exception: release branches use
release/vX.Y.Z(e.g.,release/v1.55.0) — these have no Linear issue
- Exception: release branches use
- Commit messages must start with the Linear issue ID (e.g.,
AI-2480: description) - When working on a Linear task, check the current branch first (
git branch). If not already on the correct task branch, create one before making any changes:git checkout -b AI-XXXX-short-description - When creating PRs, use the template at
.github/pull_request_template.md - Every PR must include a
pyproject.tomlversion bump — bump before merging; see Versioning for the rules - Prefer rebasing onto
mainto keep a linear history. Rebasing your own feature/PR branch and force-pushing the result is allowed and expected — always usegit push --force-with-lease(never a baregit push --force) so you never clobber commits someone else pushed. Do not rebase a branch that others are actively committing to.
Mapping a Docker Image Tag to a 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.
- 4d ago First seen · 159 lines · 2,459 tokens per session scan C 9d9f0da19660
mcp-server CLAUDE.md is an instructions file published in the GitHub repository keboola/mcp-server (86 stars, last pushed yesterday), licensed MIT. It adds 2,459 tokens to every session, about $0.0123 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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).
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
mcp-dockhand copilot-review.instructions.md
Copilot instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
cyxj-groksearch CLAUDE.md
Claude Code instructions for chenyuxiaojin/cyxj-groksearch, covering claude.md, 常用命令 and 结构与坑.
minecraft-dev-mcp AGENTS.md
Instructions for MCDxAI/minecraft-dev-mcp, covering agent handbook – minecraft dev mcp, project snapshot, what agents should prioritize, architecture wayfinder (src/) and available mcp tools (for llm surfaces).
bray AGENTS.md
AGENTS.md instructions for forgesworn/bray, covering agents.md — nostr-bray, what this is, build & test, architecture and tool groups.