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/ziwang-physics/agentchat/mcp-servernpx skills add ziwang-Physics/AgentChat --skill mcp-servergit clone --depth 1 https://github.com/ziwang-Physics/AgentChatWrote 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/ziwang-physics/agentchat/mcp-server)<a href="https://agentmods.dev/skills/ziwang-physics/agentchat/mcp-server"><img src="https://agentmods.dev/badge/skills/ziwang-physics/agentchat/mcp-server.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 | $0.00037 | $0.00662 |
| Opus 5 | $0.00018 | $0.00331 |
| Sonnet 5 | $0.00007 | $0.00132 |
| Haiku 4.5 | $0.00004 | $0.00066 |
Grade A, and why
mcp-server scanned grade A with 1 finding 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 6d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
│ child_process.spawn('node', ['AgentChat-OneWeb/index.js', ...]) What it actually says
AgentChat MCP Server
最后更新: 2026-07-06 核心原则: 将 AgentChat 的 8 个 AI Provider 暴露为 MCP 工具，任何 MCP 兼容客户端可直接调用 Provider 层:
AgentChat-OneWeb（单源真相） 安全策略: 永不关闭用户 Chrome
是什么
MCP（Model Context Protocol）Server 包装层。让 Claude Desktop、Cursor、Continue.dev 等 MCP 客户端直接发现并调用 AgentChat 的 AI Provider 降级链。
架构
Claude Desktop / Cursor / 任何 MCP 客户端
│
│ MCP Protocol (stdio JSON-RPC)
▼
AgentChat MCP Server (本 skill, ~200 行)
│
│ child_process.spawn('node', ['AgentChat-OneWeb/index.js', ...])
▼
AgentChat-OneWeb (8 个 Provider)
│
│ playwright-core → Chrome CDP port 9222
▼
Chrome → Gemini / ChatGPT / Claude / Qwen / Kimi / MiniMax / MiMo / DeepSeek
提供的工具
| 工具 | 功能 | 参数 |
|---|---|---|
gemini_think |
Pro Extended Thinking 深度推理 | prompt (必需), timeout_ms (可选) |
gemini_chat |
多轮对话（复用 tab，保留上下文） | prompt (必需) |
web_ask |
通过降级链调用任意 Provider | prompt (必需), provider (可选), timeout_ms (可选) |
web_smoke |
检查 8 个 Provider 可达性 | 无参数 |
配置方式
Claude Desktop
// claude_desktop_config.json
{
"mcpServers": {
"agentchat": {
"command": "node",
"args": ["path/to/AgentChat/skills/mcp-server/index.mjs"]
}
}
}
Cursor / Continue.dev
{
"mcpServers": {
"agentchat": {
"command": "node",
"args": ["skills/mcp-server/index.mjs"],
"cwd": "path/to/AgentChat"
}
}
}
前提条件
- Chrome CDP 必须在 9222 端口运行
- 至少一个 Provider 已在 Chrome 中登录
- Node.js >= 18
依赖
| 依赖 | 说明 |
|---|---|
@modelcontextprotocol/sdk |
MCP 协议实现 |
AgentChat-OneWeb |
Provider 实现（同一仓库内） |
What ships with it
2 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.
- 6d ago First seen · 86 lines · 37 tokens per session scan A 58faa6ffb791
mcp-server is a skill published in the GitHub repository ziwang-Physics/AgentChat (760 stars, last pushed 25d ago), licensed MIT. It adds 37 tokens to every session and 662 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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…
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…
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…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…