Borrowing it
Nothing to install: this file belongs to AliKarami/MikroMCP. 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/AliKarami/MikroMCP/main/CLAUDE.mdgit clone --depth 1 https://github.com/AliKarami/MikroMCPWrote 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/alikarami/mikromcp/claude-md)<a href="https://agentmods.dev/instructions/alikarami/mikromcp/claude-md"><img src="https://agentmods.dev/badge/instructions/alikarami/mikromcp/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 5.1 | $0.05870 | $0.05870 |
| Opus 5 | $0.02935 | $0.02935 |
| Sonnet 5 | $0.01174 | $0.01174 |
| Haiku 4.5 | $0.00587 | $0.00587 |
Grade A, and why
MikroMCP 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 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 — 427 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MikroMCP — Claude Code Guide
For the full feature roadmap (milestones v0.4–v1.0, planned tools and subsystems) see ROADMAP.md.
Commands
npm run dev # tsx watch hot-reload (development)
npm run build # tsup → dist/main.js (ESM)
npm start # run built server
npm test # vitest run once
npm run test:watch # vitest watch mode
npm run typecheck # tsc --noEmit (no output, type checking only)
npm run lint # eslint src/
npm run format # prettier --write src/ test/
Run npm test before pushing a branch (runs vitest, tsc, and eslint).
Architecture in one sentence
MCP clients speak JSON-RPC to MikroMCP over stdio or HTTP/SSE; MikroMCP routes each tool call through a per-router circuit breaker (and retry engine for read tools) before hitting the RouterOS REST API over HTTPS.
Key file map
| File | What it does |
|---|---|
src/main.ts |
Entry point — loads config, wires transport |
src/mcp/tool-registry.ts |
Registers all tools with the MCP server; injects circuit breaker, retry, correlation ID, credentials |
src/domain/tools/index.ts |
Add new tool arrays here to expose them |
src/domain/tools/tool-definition.ts |
ToolDefinition, ToolContext, ToolResult interfaces |
src/domain/errors/error-types.ts |
MikroMCPError, ErrorCategory enum, Recoverability |
src/domain/errors/error-enricher.ts |
Maps HTTP/network errors to MikroMCPError |
src/adapter/rest-client.ts |
RouterOSRestClient — get, getOne, create, update, remove, execute |
src/config/app-config.ts |
Reads MIKROMCP_* env vars |
src/config/router-registry.ts |
Loads config/routers.yaml; getRouter(id) throws if missing |
src/types.ts |
RouterConfig, RouterOSRecord, QueryOptions, Role |
Adding a tool — the pattern
Every tool lives in src/domain/tools/. Either add to an existing file or create a new one and export from index.ts.
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 Changed · +1 lines · +87 tokens per session 5870a911fada
- 8d ago First seen · 426 lines · 5,783 tokens per session scan A 5002fb0de337
MikroMCP CLAUDE.md is an instructions file published in the GitHub repository AliKarami/MikroMCP (63 stars, last pushed 2d ago), licensed MIT. It adds 5,870 tokens to every session, about $0.0294 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 2026-08-30.
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.