Bluesky 社交数据 MCP 服务

这是一个通过 MCP 协议封装 Bluesky(AT Protocol)API 的服务,提供用户资料查询、帖子获取、关键词搜索、Feed 订阅、粉丝/关注列表和帖子线程等功能,适用于 AI 代理、聊天客户端和自动化脚本集成 Bluesky 社交数据。

  • by pipeworx-io
  • JavaScript
  • 本地部署
  • 更新于
在 GitHub 查看 pipeworx-io/mcp-bluesky

使用说明

mcp-bluesky

Bluesky MCP — wraps the AT Protocol API

Part of Pipeworx — an MCP gateway connecting AI agents to 1856+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

Tool Description
get_profile Look up a Bluesky user's profile by handle (e.g., "alice.bsky.social"). Returns display name, bio, follower/following counts, avatar, and verification status.
get_posts Fetch recent posts from a Bluesky user's timeline. Returns post text, timestamps, likes, reposts, reply counts, and threaded replies.
search_posts Search Bluesky posts by keyword or phrase. Returns matching posts with author handles, timestamps, engagement metrics, and content.Requires bsky_handle and bsky_app_password in the gateway URL query params.
get_feed Get posts from a Bluesky feed (e.g., "discover", "what's-hot"). Returns recent posts with authors, timestamps, and engagement counts.
get_followers Get a user's followers on Bluesky by handle. Returns follower profiles including handles, display names, bios, and follower counts.
get_follows Get accounts a Bluesky user follows by handle. Returns followed profiles with handles, display names, bios, and descriptions.
get_thread Fetch a post thread by URI. Returns the parent post and all replies in conversation order with timestamps, authors, and engagement data.
resolve_handle Convert a Bluesky handle to its DID (decentralized identifier). Returns the DID for programmatic account lookups.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "bluesky": {
      "url": "https://gateway.pipeworx.io/bluesky/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/bluesky/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1856+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/bluesky_get_profile \
  -H 'Content-Type: application/json' \
  -d '{"handle":"alice.bsky.social"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/bluesky_get_profile. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Run it from npm

@pipeworx/mcp-bluesky is a local stdio bridge to the Pipeworx gateway: your MCP client starts it with npx, and it forwards every call to the same https://gateway.pipeworx.io/bluesky/mcp endpoint shown above. It needs network access; there is no offline mode.

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

Without a key it calls anonymously, capped at 50 calls a day. A free account raises that to 200 a day: get a key at https://pipeworx.io/signup and add "env": { "PIPEWORX_API_KEY": "<your key>" } to the server entry. The key is sent as a Bearer token, the same way a hosted connection sends it, so calls are metered and billed exactly as they are there.

It lists only this pack's tools by default. Set PIPEWORX_META_TOOLS=1 to also list ask_pipeworx and the other gateway-wide tools.

Behind an HTTPS proxy: Node's built-in fetch does not read HTTPS_PROXY by default. Newer Node releases honour it when NODE_USE_ENV_PROXY=1 is set; check your Node version's documentation.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Bluesky data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT