# FeedClaw

> Use this tool when you need to manage and approve content generated by AI agents, streamlining the publishing process. FeedClaw solves the problem of manual content review by providing an approval inbox that integrates with popular AI agents like OpenClaw, Claude, and ChatGPT. It takes in drafted content from AI agents and outputs approved, published content via email, making it easy to use in workflows where human oversight is required.

Canonical page: https://skillsregistry.net/skills/feedclaw-inbox  
JSON: https://api.skillsregistry.net/v1/skills/feedclaw-inbox

## Description

The approval inbox for AI agents. Your agent drafts, you approve, it publishes. X + email. Built for OpenClaw, Claude, ChatGPT, and other agents.

Connect via your AI agent's Device Grant flow — no API keys or tokens to copy. See feedclaw.io/ai-agents for setup instructions.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** communication
- **Updated:** 2026-05-13

## Source

- **Source listing:** [Smithery](https://smithery.ai/server/feedclaw/inbox)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "feedclaw-inbox"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/feedclaw-inbox` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/feedclaw-inbox/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt