Connects Claude to public X/Twitter content through the hosted CarryFeed API. Exposes tools to resolve profiles, posts, and media without browser automation or login prompts. You get structured metadata for public tweets, images, videos, and GIFs with source URLs preserved alongside the content. Useful when you need to pull tweet text, author context, or media candidates into a workflow without spinning up Puppeteer or losing attribution. Wraps the same endpoints available through the CarryFeed SDK and CLI. Public content only, no access to protected or deleted posts.
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:
@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.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.
pbs.twimg.com and video.twimg.com media URLs.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"]
}
}
}
See docs/agents.md for agent-facing usage, response expectations, and safety boundaries.
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"
Twitter/X search and hashtag search are planned as a later API surface. See docs/roadmap.md.
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
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent