About mcp-server-bluesky
mcp-server-bluesky is an MCP server for working with Bluesky. It is suited to users managing accounts and content through an MCP client, with tools for profiles, follows, posts, timelines, likes, and reposts.
Key features
- 01Read profiles and followers
- 02Follow and unfollow accounts
- 03Search, publish, and delete posts
- 04View timelines and post threads
- 05Like, repost, and undo actions
Use cases
- 01Search Bluesky posts
- 02Publish or remove a post
- 03Check followers and follow lists
- 04Browse timelines and inspect post threads
MCP support
The server provides MCP clients with tools for Bluesky accounts, follows, posts, timelines, likes, and reposts. It requires a username and password; the PDS URL is optional and defaults to https://bsky.social.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y mcp-server-blueskyBLUESKY_USERNAMEBLUESKY_PASSWORDSecretBLUESKY_PDS_URLLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEmcp-server-bluesky
MCP server for Bluesky.
Usage with Claude Desktop
{
"mcpServers": {
"bluesky": {
"command": "npx",
"args": ["-y", "mcp-server-bluesky"],
"env": {
"BLUESKY_USERNAME": "username",
"BLUESKY_PASSWORD": "password",
"BLUESKY_PDS_URL": "https://bsky.social"
}
}
}
}
The BLUESKY_PDS_URL is optional and defaults to https://bsky.social if not specified.
Tools
bluesky_get_profilebluesky_followbluesky_delete_followbluesky_get_followsbluesky_get_followersbluesky_search_postsbluesky_postbluesky_delete_postbluesky_repostbluesky_delete_repostbluesky_get_timelinebluesky_get_post_threadbluesky_get_likesbluesky_likebluesky_delete_like
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.