Agent skill

MCP Server

by ziwang-Physics in ziwang-Physics/AgentChat

AgentChat MCP Server — expose 8 AI providers as MCP tools for any MCP-compatible client (Claude Desktop, Cursor, Continue.dev).

MITAuto-check passedAgent Workflows

Install MCP Server

skills CLI

$ npx skills add ziwang-Physics/AgentChat --skill mcp-server -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install ziwang-Physics/AgentChat mcp-server --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/ziwang-Physics/AgentChat.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/mcp-server .claude/skills/mcp-server && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "mcp-server" agent skill from https://github.com/ziwang-Physics/AgentChat/tree/master/skills/mcp-server into .claude/skills/mcp-server/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcp-server", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/ziwang-Physics/AgentChat/tree/master/skills/mcp-server

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add ziwang-Physics/AgentChat --skill mcp-server -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install ziwang-Physics/AgentChat mcp-server --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ziwang-Physics/AgentChat.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/mcp-server .agents/skills/mcp-server && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "mcp-server" agent skill from https://github.com/ziwang-Physics/AgentChat/tree/master/skills/mcp-server into .agents/skills/mcp-server/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcp-server", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add ziwang-Physics/AgentChat --skill mcp-server -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install ziwang-Physics/AgentChat mcp-server --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ziwang-Physics/AgentChat.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/mcp-server .cursor/skills/mcp-server && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "mcp-server" agent skill from https://github.com/ziwang-Physics/AgentChat/tree/master/skills/mcp-server into .cursor/skills/mcp-server/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcp-server", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/ziwang-Physics/AgentChat.git --path skills/mcp-server

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add ziwang-Physics/AgentChat --skill mcp-server -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install ziwang-Physics/AgentChat mcp-server --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ziwang-Physics/AgentChat.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/mcp-server .gemini/skills/mcp-server && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "mcp-server" agent skill from https://github.com/ziwang-Physics/AgentChat/tree/master/skills/mcp-server into .gemini/skills/mcp-server/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcp-server", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install ziwang-Physics/AgentChat mcp-server

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add ziwang-Physics/AgentChat --skill mcp-server -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/ziwang-Physics/AgentChat.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/mcp-server .github/skills/mcp-server && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "mcp-server" agent skill from https://github.com/ziwang-Physics/AgentChat/tree/master/skills/mcp-server into .github/skills/mcp-server/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcp-server", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add ziwang-Physics/AgentChat --skill mcp-server -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install ziwang-Physics/AgentChat mcp-server --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ziwang-Physics/AgentChat.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/mcp-server .opencode/skills/mcp-server && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "mcp-server" agent skill from https://github.com/ziwang-Physics/AgentChat/tree/master/skills/mcp-server into .opencode/skills/mcp-server/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "mcp-server", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: mcp-server
GitHub stars: 785
Token cost: ~464 tokens
SKILL.md length: 101 words
Files: 3
Skills in repo: 1
Repo updated: Aug 11, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

AgentChat MCP Server — expose 8 AI providers as MCP tools for any MCP-compatible client (Claude Desktop, Cursor, Continue.dev).

Tasks that involve MCP servers
SKILL.md covers 是什么, 架构, 提供的工具 and 配置方式, plus 2 more sections
Runs JavaScript scripts from its folder; calls claude

What it does

MCP Server is an agent skill from ziwang-Physics/AgentChat. AgentChat MCP Server — expose 8 AI providers as MCP tools for any MCP-compatible client (Claude Desktop, Cursor, Continue.dev). Configuration/reference skill, not executable

Its SKILL.md is about 460 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `package.json`).

It sits in Agent Workflows, covering MCP servers. It works with Model Context Protocol. The licence is MIT.

When your agent uses it

Tasks that involve MCP servers

Example prompts

“/mcp-server”

Requirements

Node.js

What it can do on your machine

Read from SKILL.md and the folder at commit 56aa8f1. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships script files (JavaScript), which the agent can run.
Shell commands in SKILL.md call:
- claude
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

MCP Server loads about 464 tokens when it runs. Until then it costs about 46 tokens; SKILL.md has 101 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~46
When it runs · the whole SKILL.md, loaded when a task matches: ~464

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ziwang-Physics/AgentChat at commit 56aa8f1, republished under its MIT licence (© ziwang-Physics). 101 words, ~464 tokens.

Download SKILL.mdSave it as .claude/skills/mcp-server/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.

name: mcp-server
description: AgentChat MCP Server — expose 8 AI providers as MCP tools for any MCP-compatible client (Claude Desktop, Cursor, Continue.dev). Configuration/reference skill, not executable

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

json

// claude_desktop_config.json
{
  "mcpServers": {
    "agentchat": {
      "command": "node",
      "args": ["path/to/AgentChat/skills/mcp-server/index.mjs"]
    }
  }
}

Cursor / Continue.dev

json

{
  "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）

Files

SKILL.md and 2 other files in skills/mcp-server of ziwang-Physics/AgentChat.

SKILL.md
index.mjs
package.json

Open the folder on GitHubat commit 56aa8f1

Compare with similar skills

MCP Server next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

MCP Server compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
MCP Server this skillziwang-Physics/AgentChat	785	—	~464	Automated safety check: Pass	MIT	1 mo ago
MCP Server Builderanthropics/skills	180k	63 repos	~2.3k	Automated safety check: Pass	Apache-2.0	yesterday
MCP Server BuildershareAI-lab/learn-claude-code	78k	5 repos	~1.2k	Automated safety check: Pass	MIT	11 days ago
MCP Integration for Pluginsanthropics/claude-plugins-official	38k	11 repos	~3.1k	Automated safety check: Pass	Apache-2.0	yesterday
Crush Configurationcharmbracelet/crush	29k	—	~3.7k	Automated safety check: Pass	Custom licence	yesterday
Context Mode Output Sandboxmksglu/context-mode	26k	—	~4.1k	Automated safety check: Pass	Custom licence	yesterday

Similar skills

MCP Server Builder
anthropics/skills
Official
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
180k GitHub starsUsed in 63 repos~2.3k tokens
Agent WorkflowsAuto-check passed
MCP Server Builder
shareAI-lab/learn-claude-code
Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.
78k GitHub starsUsed in 5 repos~1.2k tokens
Agent WorkflowsAuto-check passed
MCP Integration for Plugins
anthropics/claude-plugins-official
Official
Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.
38k GitHub starsUsed in 11 repos~3.1k tokens
Agent WorkflowsAuto-check passed
Crush Configuration
charmbracelet/crush
Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.
29k GitHub stars~3.7k tokensUpdated yesterday
Agent WorkflowsAuto-check passed
Context Mode Output Sandbox
mksglu/context-mode
Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.
26k GitHub stars~4.1k tokensUpdated yesterday
Agent WorkflowsAuto-check passed
Warp GUI to Agent CLI Migration
warpdotdev/warp
Migrates the compatible subset of settings and global file-based MCP servers from the Warp desktop app into Warp Agent CLI without exposing credentials or state.
65k GitHub starsUsed in 1 repo~2.1k tokens
Agent WorkflowsAuto-check passed

Works with

Model Context Protocol

Questions about MCP Server

What does MCP Server do?

AgentChat MCP Server — expose 8 AI providers as MCP tools for any MCP-compatible client (Claude Desktop, Cursor, Continue.dev). MCP Server is an agent skill from ziwang-Physics/AgentChat.dev).

When should I use MCP Server?

MCP Server fits situations like: tasks that involve MCP servers.

How do I install MCP Server in Claude Code?

Run `npx skills add ziwang-Physics/AgentChat --skill mcp-server -a claude-code`. Or copy the skill folder (skills/mcp-server in ziwang-Physics/AgentChat) into .claude/skills/mcp-server in your project. Claude Code loads it when a task matches its description.

How do I install MCP Server in Codex?

Run `npx skills add ziwang-Physics/AgentChat --skill mcp-server -a codex`. Or copy the skill folder (skills/mcp-server in ziwang-Physics/AgentChat) into .agents/skills/mcp-server in your project. Codex loads it when a task matches its description.

Can I use MCP Server in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ziwang-Physics/AgentChat --skill mcp-server -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/mcp-server, .gemini/skills/mcp-server, .github/skills/mcp-server and .opencode/skills/mcp-server in your project.

What does MCP Server need to run?

Going by SKILL.md and its folder, MCP Server needs JavaScript for the scripts in its folder and the command-line tools its instructions call (claude). Our summary lists: Node.js.

Does MCP Server access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is MCP Server safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does MCP Server use?

MCP Server is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does MCP Server use?

About 464 tokens (SKILL.md is roughly 1.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to MCP Server?

Skills that share tags, products or a category with MCP Server: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Crush Configuration (charmbracelet/crush, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains MCP Server?

ziwang-Physics (a GitHub user) maintains it in ziwang-Physics/AgentChat, which has 785 GitHub stars. The repository was last updated on August 11, 2026.

Source: ziwang-Physics/AgentChat on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install MCP Server

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

AgentChat MCP Server

是什么

架构

提供的工具

配置方式

Claude Desktop

Cursor / Continue.dev

前提条件

依赖

Files

Compare with similar skills

Similar skills

MCP Server Builder

MCP Server Builder

MCP Integration for Plugins

Crush Configuration

Context Mode Output Sandbox

Warp GUI to Agent CLI Migration

Related

Questions about MCP Server