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 skills add AliKarami/MikroMCP --skill mikromcpgit 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/skills/alikarami/mikromcp/mikromcp)<a href="https://agentmods.dev/skills/alikarami/mikromcp/mikromcp"><img src="https://agentmods.dev/badge/skills/alikarami/mikromcp/mikromcp/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/alikarami/mikromcp/mikromcp"><img src="https://agentmods.dev/badge/skills/alikarami/mikromcp/mikromcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00050 | $0.01094 |
| Opus 5 | $0.00025 | $0.00547 |
| Sonnet 5 | $0.00010 | $0.00219 |
| Haiku 4.5 | $0.00005 | $0.00109 |
Grade A, and why
mikromcp 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 12d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Driving MikroMCP
MikroMCP exposes MikroTik RouterOS management as MCP tools (over stdio or HTTP).
This skill is about operating those tools well and safely. It does not reproduce
RouterOS documentation — when you need to know what a RouterOS field means, see
references/routeros-docs.md and fetch the linked official page.
When to use
- Configuring, inspecting, or troubleshooting a MikroTik router via MikroMCP tools.
- Rolling a change across many routers.
When not to use
- Devices that are not MikroTik/RouterOS.
- Tasks with no MikroMCP server connected.
First moves
- Establish the target router. Tools take an optional
routerId. If omitted, MikroMCP usesMIKROMCP_DEFAULT_ROUTER, or the sole configured router. If several routers exist and none is defaulted, ask which one. - Orient before changing anything:
get_system_status, thenlist_interfaces(and the relevantlist_*for the area you're touching).
Golden rules (the safety spine)
- Reads are safe; treat every write as consequential.
- Dry-run first. Call a write tool with
dryRun: true, show the diff, then apply for real. Never skip this for a non-trivial change. - Confirmation tokens. Destructive tools may require a two-step confirm: the
first call returns an approval requirement + token; repeat the call with
confirmationToken. This is a guardrail — explain it, don't try to bypass it. - Writes are idempotent.
already_existsandno_changeare SUCCESS, not errors. ACONFLICTmeans the resource exists with different config — resolve it deliberately (seereferences/safety-and-recovery.md). - Rollback exists. Write tools snapshot+journal first. To undo, use
rollback_changewith the journal ID. Know this before bulk changes. - Prefer dedicated tools over
run_command. Userun_commandonly when no dedicated tool covers the need.
Intent → tool quick index
| I want to… | Tool |
|---|---|
| See device health/uptime/version | get_system_status |
| List interfaces | list_interfaces |
| Add/serve an IP on an interface | manage_ip_address |
| Block/allow traffic | manage_firewall_rule |
| Port-forward / NAT | manage_firewall_rule (table nat) |
| Add a static route | manage_route |
| Add a DNS record | manage_dns_entry |
| See/assign DHCP leases | list_dhcp_leases, manage_dhcp_lease |
| See who's connected (WiFi) | list_wifi_clients |
| Test connectivity | ping, traceroute |
| Run a change across many routers | bulk_execute |
| Undo a change | rollback_change |
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 99 lines · 50 tokens per session scan A 8b6db2f42c49
mikromcp is a skill published in the GitHub repository AliKarami/MikroMCP (65 stars, last pushed 6d ago), licensed MIT. It adds 50 tokens to every session and 1,094 once invoked, about $0.0003 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 skills, from other repositories
spark-environment-setup
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
spark-memory-thermal-ops
Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
terraform-module-library
Build reusable Terraform modules for AWS, Azure, GCP, and OCI infrastructure following infrastructure-as-code best practices. Use when creating infrastructure modules, standardizing cloud provisioning, or implementing reusable IaC components.
jetson-video-capability
Use when Jetson codec, profile, chroma, bit-depth, dimension, engine-count, or operational support must be reconciled using live SDK APIs, authenticated NVIDIA samples, and NVIDIA documentation. Also use for Jetson questions about Netflix, Widevine, or other DRM-protected streaming-service playback to apply the…
amc-run-rtsp-calibration
Calibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP URLs or asks to calibrate live cameras; VIOS records clips, AMC ingests them, then runs calibration.