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 ArcBlock/agent-skills --skill mcpgit clone --depth 1 https://github.com/ArcBlock/agent-skillsWrote 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/arcblock/agent-skills/mcp)<a href="https://agentmods.dev/skills/arcblock/agent-skills/mcp"><img src="https://agentmods.dev/badge/skills/arcblock/agent-skills/mcp/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/arcblock/agent-skills/mcp"><img src="https://agentmods.dev/badge/skills/arcblock/agent-skills/mcp.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 | $0.00027 | $0.00756 |
| Opus 5.5 | $0.00011 | $0.00302 |
| Sonnet 5.5 | $0.00005 | $0.00151 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade C, and why
mcp 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 1mo 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.
| `arc` CLI is **not** on `PATH` | Plugin skills still load. Do **not** treat this as a silent total failure. Install the CLI (`curl -fsSL https://arc.afsd.io/install.sh \| bash` — see `docs/guides/arc-cli-distribution.m Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `arc` CLI is **not** on `PATH` | Plugin skills still load. Do **not** treat this as a silent total failure. Install the CLI (`curl -fsSL https://arc.afsd.io/install.sh \| bash` — see `docs/guides/arc-cli-distribution.m How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ARC skill: mcp
MCP is a transport into the same AFS world, not a second ontology.
Capability negotiation (local first)
Decide which MCP path is available before assuming tools exist:
| Host situation | What to do |
|---|---|
arc CLI is on PATH |
Use local stdio: plugin .mcp.json server arc-local → arc mcp (bridge to the daemon; starts it if needed). |
arc CLI is not on PATH |
Plugin skills still load. Do not treat this as a silent total failure. Install the CLI (curl -fsSL https://arc.afsd.io/install.sh | bash — see docs/guides/arc-cli-distribution.md). Plugin bootstrap that auto-installs CLI is S5 (not shipped yet). |
| Want remote / no-shell host | Not ready in v1. arc-remote is intentionally absent from .mcp.json so "not configured" is not the same colour as "endpoint down". Tracked in #6432 (hosted endpoint + OAuth grant). |
Say the remote path is unready out loud. An agent that reads "remote unavailable" behaves differently from one that never sees remote mentioned.
Distinguish failure reasons when local MCP will not start:
arcmissing —command not found/ spawn ENOENT forarc. Fix: install CLI (above). Message shape: needsarcon PATH.arcpresent but daemon unreachable — CLI runs; bridge cannot attach / daemon will not stay up. Fix:arc service start(or check instance). Message shape: daemon unavailable — not "arc missing".
Connect
# Bridge stdio MCP client ↔ running daemon (auto-starts daemon if configured to)
arc mcp
# Standalone serve variants exist under `arc serve --transport mcp-*`
# Check: arc serve --help
After connect (L1)
Prefer live AFS tools over re-reading booklets. For multi-terminal layout pointers:
arc skill show afs # section: WM / multi-terminal
Plugin .mcp.json (v1 — local only, flat format — no mcpServers wrapper):
{
"arc-local": { "command": "arc", "args": ["mcp"] }
}
Claude Desktop user config (outside the plugin) still uses the mcpServers envelope:
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.
- 1mo ago First seen · 75 lines · 27 tokens per session scan C 1d724aeffe63
mcp is a skill published in the GitHub repository ArcBlock/agent-skills (5 stars, last pushed 9d ago), licensed MIT. It adds 27 tokens to every session and 756 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-14.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.