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.
git clone --depth 1 https://github.com/kaminari-ad/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/rules/kaminari-ad/mcp/mcp-dev-environment)<a href="https://agentmods.dev/rules/kaminari-ad/mcp/mcp-dev-environment"><img src="https://agentmods.dev/badge/rules/kaminari-ad/mcp/mcp-dev-environment/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/rules/kaminari-ad/mcp/mcp-dev-environment"><img src="https://agentmods.dev/badge/rules/kaminari-ad/mcp/mcp-dev-environment.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 | $0.00000 | $0.01019 |
| Opus 5.5 | $0.00000 | $0.00408 |
| Sonnet 5.5 | $0.00000 | $0.00204 |
| Haiku 4.5 | $0.00000 | $0.00102 |
Grade A, and why
mcp-dev-environment 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 today.
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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Environment — mcp/
Everything runs in Docker
Production runs node:20-alpine in a pinned image. To avoid host-Node version drift, all dev commands execute inside the same image via make (run from mcp/).
cd mcp/
make lint # eslint --max-warnings 0
make lint-fix # eslint --fix
make format # prettier --write
make format-check # prettier --check
make typecheck # tsc --noEmit
make test # vitest run (all suites)
make test-unit # vitest run tests/unit
make test-integration # vitest run tests/integration
make test-isolation # vitest run tests/isolation (mandatory merge gate)
make test-cov # vitest run --coverage
make check # everything; ~3 min on first run
# Architecture / quality gates (run inside `make check`)
make check-file-sizes
make check-imports
make check-shared-state
make check-tool-naming
# Security
make audit # npm audit --audit-level=moderate
make license-check # license-checker, MIT/Apache/BSD/ISC whitelist
Rules:
- NEVER run
tsc,eslint,vitest, ornodedirectly on the host. Usemake. (You may run them via your IDE for inline feedback; commit-time validation ismake check.) - NEVER install project dependencies on host Node. The Docker image owns
node_modulesvia a named volume. - Use
make buildto rebuild the image after dependency changes.
Dependency management — npm
make install # npm ci (or npm install if no lockfile)
# Manual deps still go through docker-compose run
docker compose -f docker-compose.dev.yml run --rm mcp-dev npm install <pkg>
docker compose -f docker-compose.dev.yml run --rm mcp-dev npm install --save-dev <pkg>
.npmrc enforces save-exact=true. Always commit package.json AND package-lock.json.
Secrets & .env
.envinmcp/root, gitignored..env.exampledocuments every var with safe defaults.- The TypeScript
Configschema (src/shared/config.ts, zod-based) is the ONLY waysrc/reads env vars. Directprocess.env.XoutsideConfigis a code-review blocker.
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.
- today First seen · 105 lines · 0 tokens per session scan A f6429cd16bb3
mcp-dev-environment is a cursor rule published in the GitHub repository kaminari-ad/mcp (0 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,019 tokens. 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 2026-11-05.
Other cursor rules, from other repositories
search-routing
Smart Search Routing — always use QMD semantic search when available, never bypass with grep for vault content.
python-containerization-cursorrules-prompt-file
Cursor rules for Python development with containerization integration.
python-general-coding-standards
A set of general standards for Python projects, including type hints, input checking, code style, security, web requests, background work, and tests. It also covers FastAPI-specific tasks such as CORS and authentication.
execute-test
Execute Katalon True Platform/TestOps tests when the input is an existing test case, manual test case list, test suite, suite collection, execution request, or "run with AI" instruction. Use when you need to create a manual test run, start Run with AI, poll AI session results, schedule automated suites, read…
roslyn-mcp-pitfalls
Known pitfalls and regression lessons from production use.
roslyn-mcp-version-bump
Auto-bump Version after successful MCP self-build and reload.