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 ouyadi/market-brief --skill chat-mcp-setupgit clone --depth 1 https://github.com/ouyadi/market-briefWrote 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/ouyadi/market-brief/chat-mcp-setup)<a href="https://agentmods.dev/skills/ouyadi/market-brief/chat-mcp-setup"><img src="https://agentmods.dev/badge/skills/ouyadi/market-brief/chat-mcp-setup/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/ouyadi/market-brief/chat-mcp-setup"><img src="https://agentmods.dev/badge/skills/ouyadi/market-brief/chat-mcp-setup.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 | $0.00148 | $0.05094 |
| Opus 5 | $0.00074 | $0.02547 |
| Sonnet 5 | $0.00030 | $0.01019 |
| Haiku 4.5 | $0.00015 | $0.00509 |
Grade D, and why
chat-mcp-setup scanned grade D with 3 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 10d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
./install-daemon.sh # per-user LaunchAgent, no sudo nc -z 127.0.0.1 6280 && echo "discord MCP up" 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.
curl -LsSf https://astral.sh/uv/install.sh | sh # uv Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -o /dev/null -w '%{http_code}\n' http://<gateway-host>:7777/discord/mcp How it starts
The opening of the file, as written. The whole thing — 425 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chat MCP setup
There are two supported host platforms; pick one. Clients are configured the same way in either case (see §A).
Shape 1 — macOS host with LAN gateway
Client Mac ─── http://<gateway-host>:7777/discord/mcp ──╮
Client Mac ─── http://<gateway-host>:7777/chatlog/mcp ──┤
▼
┌──── Caddy :7777 (Bearer auth) ────┐
│ /discord/* → 127.0.0.1:6280 │
│ /chatlog/* → 127.0.0.1:5030 │
└────────────────────────────────────┘
host Mac
The shared Bearer token lives at client/token (and
host/macos/mcp-gateway/token). Build/maintain in §B.macOS.
Shape 2 — Windows host, local services (no gateway)
Same Windows machine (no LAN, no Bearer, no Caddy):
claude mcp on this machine ─── http://127.0.0.1:5030/mcp (chatlog)
└── http://127.0.0.1:6280/mcp (discord-selfbot)
Both services run as scheduled tasks (At log on):
ChatlogServer - chatlog.exe minimized window (TUI needs a real console)
DiscordSelfbot - python server.py hidden window (plain Python, stdio redirected)
Build/maintain in §B.windows. The Windows host setup is the lower-overhead option (no Bearer rotation, no LAN exposure) but only serves clients on the same machine.
No live credentials are tracked in git. host/macos/mcp-gateway/token,
client/token, host/macos/discord-selfbot/dot-discord-selfbot.env, and
host/macos/chatlog/chatlog.json are all .gitignore'd (see
.gitignore). The repo carries only .example placeholders;
each host fills in real values locally and never commits them back.
Note: 2026-05 从私 repo
ouyadi/mcp-chat-skills迁入ouyadi/market-brief(本仓chat-mcp-setup/子目录)+ scrub 了所有个人 token / data_key / LAN IP。
A. Client setup
A.1 — Connecting to the macOS LAN gateway
What ships with it
20 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.
- .gitignore 299 B
- client/install-client.sh 1.9 KB runs code
- host/macos/chatlog/chatlog.example.json 1.8 KB
- host/macos/chatlog/com.chatlog.daemon.plist 1.3 KB
- host/macos/chatlog/install-daemon.sh 1.9 KB runs code
- host/macos/chatlog/uninstall-daemon.sh 701 B runs code
- host/macos/discord-selfbot/.env.example 458 B
- host/macos/discord-selfbot/com.discord-selfbot.daemon.plist 1.1 KB
- host/macos/discord-selfbot/install-daemon.sh 2.1 KB runs code
- host/macos/discord-selfbot/pyproject.toml 308 B
- host/macos/discord-selfbot/server.py 13 KB runs code
- host/macos/discord-selfbot/start.sh 608 B runs code
- host/macos/discord-selfbot/uninstall-daemon.sh 463 B runs code
- host/macos/mcp-gateway/Caddyfile 1000 B
- host/macos/mcp-gateway/com.mcp-gateway.daemon.plist 1.3 KB
- host/macos/mcp-gateway/install-daemon.sh 2.5 KB runs code
- host/windows/chatlog/README.md 2.8 KB
- host/windows/README.md 6.9 KB
- host/windows/scripts/install-mcp-services.ps1 4.1 KB runs code
- host/windows/scripts/run-hidden.vbs 1.3 KB
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.
- 10d ago First seen · 425 lines · 148 tokens per session scan D 1a9147fb1a10
chat-mcp-setup is a skill published in the GitHub repository ouyadi/market-brief (2 stars, last pushed 4d ago), licensed MIT. It adds 148 tokens to every session and 5,094 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…