能力标签
MCP TypeScript调用器
🔌
MCP工具

MCP TypeScript调用器

基于 TypeScript · 让 AI 助手直接操作你的系统与工具
英文名:mcporter
⭐ 4.5k Stars 🍴 289 Forks 💻 TypeScript 📄 MIT 🏷 AI 8.2分
8.2AI 综合评分
MCP协议TypeScriptAPI封装CLI工具开源
✦ AI Skill Hub 推荐

经 AI Skill Hub 精选评估,MCP TypeScript调用器 获评「强烈推荐」。已获得 4.5k 颗 GitHub Star,这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 8.2 分,适合有一定技术背景的用户使用。

📚 深度解析

MCP TypeScript调用器 是一款基于 MCP(Model Context Protocol)标准协议的 AI 工具扩展。MCP 协议由 Anthropic 开发并开源,旨在建立 AI 模型与外部工具之间的标准化通信接口,目前已被 Claude Desktop、Claude Code、Cursor 等主流 AI 工具采纳。

通过安装 MCP TypeScript调用器,你的 AI 助手将获得额外的工具调用能力,可以用自然语言直接操控该工具的功能,无需学习复杂的命令行语法。MCP 工具的核心价值在于"一次配置,永久增强"——配置完成后,每次与 AI 对话时都可以无缝调用这些工具。

在技术实现上,MCP 工具通过标准的 JSON-RPC 协议与 AI 客户端通信,工具的功能以"工具列表"的形式暴露给 AI 模型,AI 可以按需调用。MCP TypeScript调用器 提供了结构化的工具调用接口,使 AI 模型能够精确地理解和使用每个功能点,显著降低 AI 在工具使用上的错误率。

与传统的 API 集成相比,MCP 工具的优势在于无需编写代码——用户只需在配置文件中添加几行 JSON,即可让 AI 获得全新能力。AI Skill Hub 将 MCP TypeScript调用器 评为 AI 评分 8.2 分,属于同类工具中的优质选择。

📋 工具概览

MCP TypeScript调用器 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。

GitHub Stars
⭐ 4.5k
开发语言
TypeScript
支持平台
Windows / macOS / Linux
维护状态
持续维护,定期更新
开源协议
MIT
AI 综合评分
8.2 分
工具类型
MCP工具
Forks
289

📖 中文文档

以下内容由 AI Skill Hub 根据项目信息自动整理,如需查看完整原始文档请访问底部「原始来源」。

MCP TypeScript调用器 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。

📌 核心特色
  • 通过标准 MCP 协议与 Claude、Cursor 等主流 AI 客户端深度集成
  • 提供结构化工具调用接口,显著降低 AI 集成复杂度
  • 支持 Claude Desktop 和 Claude Code 无缝接入,开箱即用
  • 可与其他 MCP 工具组合叠加,构建完整 AI 工作站
  • 轻量无侵入设计,不影响现有系统架构
🎯 主要使用场景
  • 在 Claude Desktop 对话中直接调用本地工具,实现 AI 与系统的深度联动
  • 通过自然语言驱动复杂的多步骤自动化任务,代替繁琐手动操作
  • 将多个 MCP 工具组合使用,构建个人专属 AI 工作站
以下安装命令基于项目开发语言和类型自动生成,实际以官方 README 为准。
安装命令
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/openclaw/mcporter

# 方式二:手动配置 claude_desktop_config.json
{
  "mcpServers": {
    "mcp-typescript---": {
      "command": "npx",
      "args": ["-y", "mcporter"]
    }
  }
}

# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
📋 安装步骤说明
  1. 确认已安装 Node.js(v18 或以上版本)
  2. 打开 Claude Desktop 或 Claude Code 的 MCP 配置文件
  3. 按「交给 Agent 安装 → Claude Desktop」标签中的 JSON 配置填入 mcpServers 字段
  4. 保存配置文件并重启 Claude 客户端
  5. 重启后,在对话中即可使用本工具
以下用法示例由 AI Skill Hub 整理,涵盖最常见的使用场景。
常用命令 / 代码示例
# 安装后在 Claude 对话中直接使用
# 示例:
用户: 请帮我用 MCP TypeScript调用器 执行以下任务...
Claude: [自动调用 MCP TypeScript调用器 MCP 工具处理请求]

# 查看可用工具列表
# 在 Claude 中输入:"列出所有可用的 MCP 工具"
以下配置示例基于典型使用场景生成,具体参数请参照官方文档调整。
配置示例
// claude_desktop_config.json 配置示例
{
  "mcpServers": {
    "mcp_typescript___": {
      "command": "npx",
      "args": ["-y", "mcporter"],
      "env": {
        // "API_KEY": "your-api-key-here"
      }
    }
  }
}

// 保存后重启 Claude Desktop 生效
📑 README 深度解析 真实文档 完整度 74/100 查看 GitHub 原文 →
以下内容由系统直接从 GitHub README 解析整理,保留代码块、表格与列表结构。

MCPorter 🧳 - Call MCPs from TypeScript or as CLI

<p align="center"> <img src="https://raw.githubusercontent.com/steipete/mcporter/main/mcporter.png" alt="MCPorter header banner" width="1100"> </p>

<p align="center"> <a href="https://www.npmjs.com/package/mcporter"><img src="https://img.shields.io/npm/v/mcporter?style=for-the-badge&logo=npm&logoColor=white" alt="npm version"></a> <a href="https://github.com/steipete/mcporter/actions/workflows/ci.yml"><img src="https://img.shields.io/github/actions/workflow/status/steipete/mcporter/ci.yml?branch=main&style=for-the-badge&label=tests" alt="CI Status"></a> <a href="https://github.com/steipete/mcporter"><img src="https://img.shields.io/badge/platforms-macOS%20%7C%20Linux%20%7C%20Windows-blue?style=for-the-badge" alt="Platforms"></a> <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-green?style=for-the-badge" alt="MIT License"></a> </p>

TypeScript runtime, CLI, and code-generation toolkit for the Model Context Protocol.

MCPorter helps you lean into the "code execution" workflows highlighted in Anthropic's Code Execution with MCP guidance: discover the MCP servers already configured on your system, call them directly, compose richer automations in TypeScript, and mint single-purpose CLIs when you need to share a tool. All of that works out of the box -- no boilerplate, no schema spelunking.

Key Capabilities

  • Zero-config discovery. createRuntime() merges your home config (~/.mcporter/mcporter.json[c], or $XDG_CONFIG_HOME/mcporter/mcporter.json[c] when set) first, then config/mcporter.json, plus Cursor/Claude/Codex/Windsurf/OpenCode/VS Code imports, expands ${ENV} placeholders, and pools connections so you can reuse transports across multiple calls.
  • One-command CLI generation. mcporter generate-cli turns any MCP server definition into a ready-to-run CLI, with optional bundling/compilation and metadata for easy regeneration.
  • Typed tool clients. mcporter emit-ts emits .d.ts interfaces or ready-to-run client wrappers so agents/tests can call MCP servers with strong TypeScript types without hand-writing plumbing.
  • Friendly composable API. createServerProxy() exposes tools as ergonomic camelCase methods, automatically applies JSON-schema defaults, validates required arguments, and hands back a CallResult with .text(), .markdown(), .json(), .images(), and .content() helpers.
  • Record/replay fixtures. mcporter record captures MCP JSON-RPC traffic as NDJSON, and mcporter replay serves the same responses deterministically for offline debugging and redacted repros.
  • OAuth and stdio ergonomics. Built-in OAuth caching, log tailing, and stdio wrappers let you work with HTTP, SSE, and stdio transports from the same interface.
  • Ad-hoc connections. Point the CLI at any MCP endpoint (HTTP or stdio) without touching config, then persist it later if you want. Hosted MCPs that expect a browser login (Supabase, Vercel, etc.) are auto-detected—just run mcporter auth <url> and the CLI promotes the definition to OAuth on the fly. See docs/adhoc.md.

What's New in 0.11.0

  • Bridge mode. mcporter serve exposes daemon-managed keep-alive servers as one MCP bridge with readable server__tool names.
  • Headless OAuth. --no-browser, vault seeding, cached-token refresh, and auth: "refreshable_bearer" cover non-interactive deployments.
  • HTTP compatibility. httpFetch: "node-http1" keeps providers that reject Node's built-in fetch working.
  • Safer writes. Config, OAuth vault, JSON output, and cache metadata writes are serialized/atomic so parallel agents stop stepping on each other.
  • Release confidence. 0.11.0 is published on npm and Homebrew, and live/published install smokes are green.

Linear: search documentation (requires `LINEAR_API_KEY`)

LINEAR_API_KEY=sk_linear_example npx mcporter call linear.search_documentation query="automations"

Installation

Install globally with npm

npm install -g mcporter

Quick Start

MCPorter auto-discovers the MCP servers you already configured in Cursor, Claude Code/Desktop, Codex, or local overrides. You can try it immediately with npx--no installation required. Need a full command reference (flags, modes, return types)? Check out docs/cli-reference.md.

Call syntax options

```bash

Try an MCP without editing config

```bash

Configuration Reference

Manage this file with mcporter config list|get|add|remove|import when you’d rather avoid hand-editing JSON; see docs/config.md for the full walkthrough. Config files are parsed as JSONC, so inline // and /* ... */ comments plus trailing commas are supported in both mcporter.json and mcporter.jsonc.

Manage configs with `mcporter config`

Run mcporter config … via your package manager (pnpm, npm, npx, etc.) when you want an interactive view of project MCPs:

  • config list shows only local entries by default and, on TTYs, prints a summary of every other config file (Cursor, Claude, Windsurf, VS Code, etc.) with counts and sample names. Add --source import to inspect those imported entries directly or --json for scripting.
  • config get/remove/logout reuse the fuzzy matching logic from mcporter list/call, so typos like sshadcn auto-correct to shadcn (with a dimmed notice) and ambiguous names surface “Did you mean …?” hints.
  • config import <kind> --copy pulls editor-managed entries into config/mcporter.json, letting you customize or remove them locally without touching upstream files.
  • Every subcommand honors --config <path> / --root <dir>, making it easy to juggle multiple project configs or workspace-specific overrides.

config/mcporter.json mirrors Cursor/Claude's shape:

{
  "mcpServers": {
    "context7": {
      "description": "Context7 docs MCP",
      "baseUrl": "https://mcp.context7.com/mcp",
      "headers": {
        "Authorization": "$env:CONTEXT7_API_KEY",
      },
    },
    "chrome-devtools": {
      "command": "npx",
      "args": ["-y", "chrome-devtools-mcp@latest", "--autoConnect"],
      "env": { "npm_config_loglevel": "error" },
    },
  },
  "imports": ["cursor", "claude-code", "claude-desktop", "codex", "windsurf", "opencode", "vscode"],
}

What MCPorter handles for you:

  • ${VAR}, ${VAR:-fallback}, and $env:VAR interpolation for config strings. Secret-bearing headers, env, and bearer-token placeholders stay lazy and resolve at runtime.
  • Automatic OAuth token caching in the shared vault (~/.mcporter/credentials.json, or $XDG_DATA_HOME/mcporter/credentials.json when set) unless you override tokenCacheDir.
  • Stdio commands inherit the directory of the file that defined them (imports or local config).
  • Import precedence matches the array order; omit imports to use the default ["cursor", "claude-code", "claude-desktop", "codex", "windsurf", "opencode", "vscode"].
  • chrome-devtools-mcp --autoConnect receives a small compatibility patch while upstream auto-connect can hang on busy Chrome profiles; set MCPORTER_DISABLE_CHROME_DEVTOOLS_COMPAT=1 to opt out.

OAuth-protected servers

If an HTTP MCP requires browser login (OAuth), persist it with --auth oauth (or set "auth": "oauth" in JSON), then run mcporter auth once:

npx mcporter config add notion https://mcp.notion.com/mcp --auth oauth
npx mcporter auth notion

On headless hosts, use npx mcporter auth notion --no-browser to print the authorization URL instead of launching the platform browser. Treat the printed URL as sensitive operational output. Keep the mcporter auth process alive until the browser redirects back to the printed redirectUrl; process managers that exit or clean up the command after capturing stdout can kill the loopback callback listener before OAuth completes. Run the command from a persistent terminal session, tmux, or a supervised background process such as nohup, and if you open the URL on another machine, make sure the callback port is reachable through a loopback-only tunnel or a configured oauthRedirectUrl.

Providers that do not support dynamic client registration can use a pre-registered app:

{
  "mcpServers": {
    "hubspot": {
      "baseUrl": "https://mcp.hubspot.com/mcp",
      "auth": "oauth",
      "oauthClientId": "your-client-id",
      "oauthClientSecretEnv": "HUBSPOT_CLIENT_SECRET",
      "oauthTokenEndpointAuthMethod": "client_secret_post",
      "oauthRedirectUrl": "http://127.0.0.1:3434/callback",
    },
  },
}

Keep client secrets in environment variables or private machine-local configs, and register the exact oauthRedirectUrl with the provider.

Refreshable bearer tokens (non-interactive OAuth)

For servers with pre-seeded OAuth tokens that need automatic refresh without browser prompts, use auth: "refreshable_bearer". HTTP servers receive Authorization: Bearer <token> headers; STDIO servers require refresh.accessTokenEnv to inject the token as an environment variable:

{
  "mcpServers": {
    "example": {
      "command": "uvx",
      "args": ["example-mcp-server"],
      "auth": "refreshable_bearer",
      "refresh": {
        "tokenEndpoint": "https://api.example.com/oauth/token",
        "clientIdEnv": "EXAMPLE_CLIENT_ID",
        "clientSecretEnv": "EXAMPLE_CLIENT_SECRET",
        "clientAuthMethod": "client_secret_basic",
        "refreshSkewSeconds": 300,
        "accessTokenEnv": "EXAMPLE_ACCESS_TOKEN",
      },
    },
  },
}

mcporter refreshes tokens before they expire (default 5 minutes early) using the refresh token from the vault. For keep-alive stdio servers that can't reload credentials after startup, use "lifecycle": "ephemeral" or restart the daemon before tokens expire.

Headless deployments that already have OAuth tokens can seed the vault without reproducing mcporter's internal vault key:

npx mcporter vault set hubspot --tokens-file ./tokens.json
npx mcporter vault set hubspot --stdin < tokens.json
npx mcporter vault clear hubspot

The JSON payload is { "tokens": { ... }, "clientInfo": { ... } }; tokens is required and clientInfo is optional.

Provide configPath or rootDir to CLI/runtime calls when you juggle multiple config files side by side.

Config resolution order & system-level configs

mcporter reads exactly one primary config per run. The lookup order is:

  1. The path you pass via --config (or programmatic configPath).
  2. The MCPORTER_CONFIG environment variable (set it in your shell to apply everywhere).
  3. <root>/config/mcporter.json inside the current project.
  4. $XDG_CONFIG_HOME/mcporter/mcporter.json[c] when XDG_CONFIG_HOME is set, falling back to ~/.mcporter/mcporter.json[c] when no XDG mcporter config exists and the project file is missing.

All mcporter config … mutations write back to whichever file was selected by that order. To manage a system-wide config explicitly, point the CLI at it:

mcporter config --config ~/.mcporter/mcporter.json add global-server https://api.example.com/mcp

Set MCPORTER_CONFIG=~/.mcporter/mcporter.json in your shell profile when you want that file to be the default everywhere (handy for npx mcporter … runs).

mcporter honors XDG Base Directory env vars for its own files when those vars are explicitly set: XDG_CONFIG_HOME for home configs, XDG_DATA_HOME for the OAuth vault, XDG_CACHE_HOME for schema caches, and XDG_STATE_HOME for daemon/runtime state. If the matching XDG var is unset or relative, mcporter keeps the legacy ~/.mcporter path. Config discovery is XDG-first but still probes ~/.mcporter/mcporter.json[c] when no XDG mcporter config exists, which keeps embedders from hiding the user registry when they set XDG_CONFIG_HOME for another tool. Existing explicit overrides still win.

context7.js (bundled CLI via Rolldown or Bun, depending on runtime)


> Convert the chrome-devtools MCP to a CLI via this one weird trick:
>
> `npx mcporter generate-cli --command "npx -y chrome-devtools-mcp@latest"`

Tip: you can drop `--command` when the inline command is the first positional argument (e.g., `npx mcporter generate-cli "npx -y chrome-devtools-mcp@latest"`).

- `--name` overrides the inferred CLI name.
- Add `--description "..."` if you want a custom summary in the generated help output (otherwise mcporter asks the MCP server for its own description/title during generation).
- Generated CLIs inherit the same color-aware help layout as `mcporter` itself: invoking the binary with no arguments shows the embedded tool list + quick start, and each `--help` page uses bold titles + dimmed descriptions when stdout is a TTY.
- Add `--bundle [path]` to emit a bundle alongside the template (Rolldown when targeting Node, Bun automatically when the runtime resolves to Bun; override with `--bundler rolldown|bun`).
- `--output <path>` writes the template somewhere specific.
- `--runtime bun|node` picks the runtime for generated code (Bun required for `--compile`).
- Add `--compile` to emit a Bun-compiled binary; MCPorter cleans up intermediate bundles when you omit `--bundle`.
- Use `--include-tools a,b,c` or `--exclude-tools a,b,c` to generate a CLI for a subset of tools (mutually exclusive).
- Use `--from <artifact>` (optionally `--dry-run`) to regenerate an existing CLI using its embedded metadata.
- Prefer a positional shorthand if the server already lives in your config/imports:
  `npx mcporter generate-cli linear --bundle dist/linear.js`.
- `--server`/`--command` accept HTTP URLs, optional `.tool` suffixes, and even scheme-less hosts (`shadcn.io/api/mcp.getComponents`).

Every artifact embeds regeneration metadata (generator version, resolved server definition, invocation flags). Use:
npx mcporter inspect-cli dist/context7.js # human-readable summary npx mcporter generate-cli --from dist/context7.js # replay with latest mcporter ```

Agents should usually get one small skill per MCP server or workflow instead of a generic "all of mcporter" skill. See docs/agent-skills.md for the pattern and a copyable template.

Types-only interface (Promise signatures)

npx mcporter emit-ts linear --out types/linear-tools.d.ts

🇨🇳 中文文档镜像 AI 翻译 2026-06-14
英文原文章节由系统翻译为中文摘要,便于快速理解。完整原文见上方 "📑 README 深度解析"。
📌 简介

MCPorter 是一个 TypeScript 或 CLI 的 MCP 调用工具,提供零配置发现和一键 CLI 生成功能。它支持多种 MCP 服务,包括 Cursor、Claude、Codex、Windsurf 和 OpenCode 等。

⚡ 功能介绍

MCPorter 的关键功能包括零配置发现、一个命令 CLI 生成、桥接模式、无头 OAuth、HTTP 兼容性和安全的写入功能。它还支持多种 MCP 服务和环境变量的使用。

📋 环境依赖

MCPorter 需要 LINEAR_API_KEY 来使用 Linear 搜索文档功能。需要安装 npm 和 Docker 等依赖包。

🛠 安装步骤(Docker/pip/源码)

MCPorter 可以通过 npm 全局安装,或者使用 Docker 镜像部署。还支持源码安装和 pip 安装等方式。

🚀 使用教程

MCPorter 的使用教程包括快速启动、命令参考和配置管理。用户可以使用 `npx` 命令尝试 MCPorter 的功能,或者查看文档获取更多信息。

⚙️ 配置说明(含 MCP / env)

MCPorter 的配置文件支持 JSONC 格式,用户可以使用 `mcporter config` 命令管理配置文件。配置文件包括 MCP 服务、环境变量和关键参数等。

🔌 API 说明

MCPorter 提供了一个 Types-only 接口,用户可以使用 `npx mcporter emit-ts` 命令生成类型定义文件。还支持 CLI 生成和 API 接口等功能。

❓ FAQ 摘要

MCPorter 的 FAQ 摘要包括常见问题和解决方案等信息。用户可以通过查看 FAQ 来获取更多信息。

🎯 aiskill88 AI 点评 A 级 2026-05-21

高星项目,TypeScript生态实用工具。MCP协议���装得当,API设计简洁易用。社区活跃度高,适合现代应用开发。

📚 实用指南(长尾问题)
适合谁
  • 需要让 Claude / Cursor 操作本地工具的 AI 工程师
  • 构建多智能体协作系统的 Agent 开发者
最佳实践
  • 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC,避免暴露公网
  • Agent 任务先做 dry-run 验证工具调用链,再开启自主执行
常见错误
  • API key 直接提交到 git 仓库(请用 .env 并加入 .gitignore)
  • MCP 配置路径拼错或权限不足,重启 Claude Desktop 才生效
部署方案
  • CLI:直接 npm install -g / pip install,命令行调用
  • 云端托管:可放在 Vercel / Railway / Fly.io 等 PaaS 平台
相关搜索
mcporter 中文教程mcporter 安装报错怎么办mcporter MCP 配置mcporter Agent 工作流mcporter 与同类工具对比mcporter 最佳实践mcporter 适合谁用

⚡ 核心功能

👥 适合谁
  • 需要让 Claude / Cursor 操作本地工具的 AI 工程师
  • 构建多智能体协作系统的 Agent 开发者
⭐ 最佳实践
  • 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC,避免暴露公网
  • Agent 任务先做 dry-run 验证工具调用链,再开启自主执行
⚠️ 常见错误
  • API key 直接提交到 git 仓库(请用 .env 并加入 .gitignore)
  • MCP 配置路径拼错或权限不足,重启 Claude Desktop 才生效

👥 适合人群

Claude Desktop / Claude Code 用户AI 工具开发者需要扩展 AI 能力的专业人士自动化工程师

🎯 使用场景

  • 在 Claude Desktop 对话中直接调用本地工具,实现 AI 与系统的深度联动
  • 通过自然语言驱动复杂的多步骤自动化任务,代替繁琐手动操作
  • 将多个 MCP 工具组合使用,构建个人专属 AI 工作站

⚖️ 优点与不足

✅ 优点
  • +MIT 协议,可免费商用
  • +标准化 MCP 协议,生态互联性强
  • +与 Claude 官方生态无缝对接
  • +即插即用,配置简单快捷
⚠️ 不足
  • 依赖 Claude 客户端,非 Claude 用户无法使用
  • MCP 协议仍在持续演进,接口可能变更
  • 需要一定的配置步骤
⚠️ 使用须知

AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。

建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。

📄 License 说明

✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。

🔗 相关工具推荐

📰 相关 AI 新闻
🍿 AI 圈相关吃瓜
🗺️ 相关解决方案
🧩 你可能还需要
基于当前 Skill 的能力图谱,自动补全的工具组合

❓ 常见问题 FAQ

mcporter 是一款TypeScript开发的AI辅助工具。开源MCP工具:Call MCPs via TypeScript, masquerading as simple TypeScript API. Or package them。⭐4.5k · TypeScript 主要应用场景包括:集成MCP服务到应用、快速构建AI能力应用、MCP工具打包发布。
💡 AI Skill Hub 点评

AI Skill Hub 点评:MCP TypeScript调用器 的核心功能完整,质量优秀。对于Claude Desktop / Claude Code 用户来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。

⬇️ 获取与下载
⬇ 下载源码 ZIP

✅ MIT 协议 · 可免费商用 · 直接从 aiskill88 服务器下载,无需跳转 GitHub

📚 深入学习 MCP TypeScript调用器
查看分步骤安装教程和完整使用指南,快速上手这款工具
🌐 原始信息
原始名称 mcporter
原始描述 开源MCP工具:Call MCPs via TypeScript, masquerading as simple TypeScript API. Or package them。⭐4.5k · TypeScript
Topics MCP协议TypeScriptAPI封装CLI工具开源
GitHub https://github.com/openclaw/mcporter
License MIT
语言 TypeScript
🔗 原始来源
🐙 GitHub 仓库  https://github.com/openclaw/mcporter 🌐 官方网站  https://mcporter.sh

收录时间:2026-05-20 · 更新时间:2026-05-30 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。

📺 订阅 AI Skill Hub Daily Telegram 频道
每天 8 条精选 AI Skill、MCP、Agent 与自动化工具推送
加入频道 →