CarryFeed

CarryFeed

CarryFeed lets AI agents resolve public X/Twitter profiles, posts, article-style links, and media metadata without browser login flows. It exposes source-preserving tools for public post text, author context, image/video/GIF candidates, profile timelines, and download URLs through the @carryfeed/mcp package.

Category
访问服务器

README

CarryFeed Agent Tools

skills.sh npm @carryfeed/sdk npm @carryfeed/cli npm @carryfeed/mcp

Public SDK, CLI, MCP server, OpenAPI notes, and agent skill wrappers for the hosted CarryFeed API.

This repository is intentionally a wrapper layer. It does not include CarryFeed's internal resolver implementation, Worker source, direct X/Twitter client code, tokens, cookies, or scraping internals.

CarryFeed gives agents one stable, source-preserving way to read public X/Twitter links. Instead of driving a browser, handling login prompts, or losing source context in screenshots, agents can call a hosted API and receive public profile, post, article, and media metadata with the original URL kept beside the result.

Useful links:

Packages

  • @carryfeed/sdk: JavaScript SDK for the hosted CarryFeed API.
  • @carryfeed/cli: CLI wrapper for agents and local scripts.
  • @carryfeed/mcp: stdio MCP server for MCP-capable agents.
  • skills/carryfeed-twitter-tools: Agent skill instructions for public X/Twitter link workflows.

Public Scope

CarryFeed works with public X and Twitter links only. It is designed for public profile, post, article, and media metadata workflows. It does not unlock private, protected, deleted, restricted, or login-only content.

Why Agents Use CarryFeed

  • One hosted API instead of brittle browser automation.
  • Public profile, post, article, image, video, and GIF-style media workflows in one place.
  • Source URL, author context, text, and media candidates stay together.
  • Clear public-only boundaries that help agents avoid overclaiming access.
  • CORS-friendly API, OpenAPI notes, CLI examples, and an agent skill.
  • Download helper for public pbs.twimg.com and video.twimg.com media URLs.

Quick Start

npm install @carryfeed/sdk
import { CarryFeedClient } from "@carryfeed/sdk";

const carryfeed = new CarryFeedClient();
const post = await carryfeed.resolve("https://x.com/user/status/123");
const media = await carryfeed.resolveMedia("https://x.com/user/status/123");
const profile = await carryfeed.getProfile("NASA");

CLI:

npx -y @carryfeed/cli resolve https://x.com/user/status/123 --compact
npx -y @carryfeed/cli media https://x.com/user/status/123 --compact
npx -y @carryfeed/cli profile NASA --statuses --count 5 --compact

MCP:

{
  "mcpServers": {
    "carryfeed": {
      "command": "npx",
      "args": ["-y", "@carryfeed/mcp"]
    }
  }
}

Agent Docs

See docs/agents.md for agent-facing usage, response expectations, and safety boundaries.

Agent Skill

The repository includes skills/carryfeed-twitter-tools, a wrapper-only skill that tells agents to use npx -y @carryfeed/cli for public X/Twitter source context. SDK and OpenAPI details are kept for developers, while the skill gives agents one default path.

After this repository is public, agents that support the Skills CLI can install it with:

npx skills add christian-beep383/carryfeed-agent-tools --skill carryfeed-twitter-tools

For ClawHub, publish from the skill folder after the npm packages and public repository are ready:

clawhub skill publish . --slug carryfeed-twitter-tools --name "CarryFeed Twitter Tools" --version 0.1.0 --changelog "Initial release"

Roadmap

Twitter/X search and hashtag search are planned as a later API surface. See docs/roadmap.md.

Publishing

The npm scope is @carryfeed.

Dry-run package contents:

npm run pack:sdk
npm run pack:cli
npm run pack:mcp

Publish when logged in as an npm user with write access to the carryfeed organization:

npm run publish:sdk
npm run publish:cli
npm run publish:mcp

Recommended first GitHub remote:

git remote add origin https://github.com/christian-beep383/carryfeed-agent-tools.git

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选