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 skills/lukacf/meerkat/mcp-server-setupnpx skills add lukacf/meerkat --skill mcp-server-setupgit clone --depth 1 https://github.com/lukacf/meerkatWrote 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/lukacf/meerkat/mcp-server-setup)<a href="https://agentmods.dev/skills/lukacf/meerkat/mcp-server-setup"><img src="https://agentmods.dev/badge/skills/lukacf/meerkat/mcp-server-setup.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 | $0.00018 | $0.00506 |
| Opus 5 | $0.00009 | $0.00253 |
| Sonnet 5 | $0.00004 | $0.00101 |
| Haiku 4.5 | $0.00002 | $0.00051 |
Grade A, and why
MCP Server Setup 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 5d 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.
What it actually says
MCP Server Setup
Use MCP when an external server should provide tools to Meerkat. MCP server configuration controls tool discovery and transport; it does not move semantic ownership away from the server or Meerkat runtime.
Operating Rules
- Use
rkat mcp addto register servers in project or user config. Project is the default scope;--scope localis an alias for project. - Use stdio for local command-backed servers, streamable HTTP for modern network servers, and SSE only for legacy servers that require it.
- Use
rkat mcp listandrkat mcp getto inspect configured servers. - Use
rkat mcp login <name>for OAuth-protected HTTP servers. Do not paste bearer tokens into prompts or command arguments. - Project configuration wins when the same server name exists in both scopes.
Specify
--scopewhen removing an ambiguous name. - Start or resume a session to load configured MCP tools into the agent.
- For live session mutation, use JSON-RPC
mcp/add,mcp/remove, andmcp/reload, or the REST/sessions/{id}/mcp/*routes. Mutations are staged and take effect at a turn boundary; editing config does not mutate an active session mid-turn. - Keep durable work state in WorkGraph and time-based wakeups in Schedule. MCP tools are actuators or external integrations.
Examples
rkat mcp add files -- npx -y @modelcontextprotocol/server-filesystem .
rkat mcp add issue-api --url https://mcp.example.com
rkat mcp login issue-api
rkat mcp list
Configuration Format
[[servers]]
name = "local-tools"
command = "path/to/server"
args = ["--flag", "value"]
env = { KEY = "value" }
[[servers]]
name = "issue-api"
url = "https://mcp.example.com"
connect_timeout_secs = 10
Project config lives at <context-root>/.rkat/mcp.toml; user config lives at
~/.rkat/mcp.toml. Prefer the CLI because it preserves unrelated TOML content
and coordinates concurrent mutations.
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.
- 5d ago First seen · 58 lines · 18 tokens per session scan A 19de03d8606a
MCP Server Setup is a skill published in the GitHub repository lukacf/meerkat (20 stars, last pushed today), licensed Apache-2.0. It adds 18 tokens to every session and 506 once invoked, about $0.0001 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
frame-macos-notification
拟真 macOS 通知 banner + app icon + 标题正文, 适合 video overlay / 产品发布预告.
prototype-web
可点击的功能性 Web 原型, 含导航、英雄区、特性区、CTA.
waitlist-page
【模板: 等候名单页 / Waitlist】 【意图】为新产品 / 早鸟内测做一张极简等候页。 【布局】.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
deck-pitch
10 页融资 deck, 白底 + 蓝紫渐变 hero, traction 柱状, $X.XM ask.
conversational-ux
Design voice and conversational interfaces — dialog flows, error recovery, and persona. Use when the interface speaks and listens rather than being tapped. For graphical input collection, use form-design.