# AT Protocol

> Use this tool when you need to access and retrieve data from the AT Protocol decentralized network, solving problems such as handle resolution, metadata retrieval, and full-text search for posts and users. It provides a read-only interface with inputs including handle, repository, and search queries, and outputs including metadata, records, and blobs. Use it in contexts where you require decentralized data access without authentication for public data.

Canonical page: https://skillsregistry.net/skills/karashiiro-atproto  
JSON: https://api.skillsregistry.net/v1/skills/karashiiro-atproto

## Description

Provides read-only access to the AT Protocol decentralized network, abstracting away Bluesky-specific APIs to work with any Personal Data Server (PDS). Supports handle resolution, repository metadata retrieval, record listing and fetching, blob retrieval with inline image content, and full-text search for posts and users. Built in Rust with the rmcp SDK and requires no authentication for public data access.

## Trust

- **Trust score (0–1):** 0.95
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/karashiiro-atproto)
- **Repository:** <https://github.com/karashiiro/atproto-mcp>

## 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": "karashiiro-atproto"
    }
  }
}
```

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