Analyzes recent Bluesky posts about stocks by fetching content from Bluesky's public search API, filtering for stock-related posts, and providing sentiment analysis summaries with post details including author, engagement metrics, and timestamps
Uses Cloudflare Workers AI for sentiment analysis of social media posts, specifically leveraging the DistilBERT model to classify text sentiment and generate confidence scores for stock-related content analysis
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP Bluesky Stock Sentiment analyze recent posts about Tesla stock"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP server on Cloudflare Workers that pulls recent stock-related posts from Bluesky, scores their sentiment with Workers AI, and returns a concise summary to any MCP-compatible client.
🏅 3rd place at World Wild Web MCP Server Hack Night — built with Cloudflare and Fiberplane. (announcement)
An MCP client (e.g. Claude Desktop) calls the analyze_stock_posts tool over HTTP at /mcp.
The Worker (Hono + mcp-lite) searches Bluesky's public API for recent posts.
Posts are filtered down to stock-related content with keyword/regex heuristics.
Each post is classified by Workers AI (@cf/huggingface/distilbert-sst-2-int8).
The tool returns totals, percentages, average confidence, and per-post details.
The Mermaid source for the diagram lives in docs/architecture.md.
Related MCP server: Yahoo Finance MCP Server
Prerequisites: Node 18+, a Cloudflare account, and Wrangler auth (npx wrangler login).
npm install
npm run dev # http://localhost:8787
npm run deploy # deploy to Cloudflare Workers
npm run cf-typegen # optional: regenerate Worker binding typesWorkers AI is already bound in wrangler.jsonc (ai.binding = "AI").
Environment | MCP endpoint |
Local |
|
Production |
|
The server registers as bluesky-stock-sentiment. Example prompt:
Use the analyze_stock_posts tool to get recent stock posts from Bluesky and analyze their sentiment.
analyze_stock_postsInput | Type | Default | Description |
| number (1–10) |
| Number of recent stock posts to analyze |
Returns a text summary: positive/negative counts and percentages, average confidence, and for each post the label, confidence, author, likes, reposts, timestamp, and URI.
Method | Path | Description |
|
| Service metadata (name, version, description, tools) |
|
| MCP over HTTP ( |
What | Where | Notes |
Sentiment model |
| Swap for any Workers AI text-classification model |
Stock keywords |
| Tune what counts as a "stock post" |
Bluesky search |
| Public unauthenticated search with de-duplication |
Firehose (reference) |
| Real-time WebSocket collector; not wired into the Worker |
src/
├── index.ts # Hono app, MCP server wiring, routes
├── mcp/tools.ts # analyze_stock_posts registration + handler
└── lib/ # sentiment, stock filter, Bluesky search, firehose
docs/
├── architecture.md # Mermaid architecture diagram
└── images/ # README screenshotsBluesky's public search API may rate-limit or change; results vary over time.
Sentiment output is a toy signal, not financial advice.
Provided as-is; add a license if you plan to distribute.
This server cannot be deployed
Track brand mentions & keywords on Bluesky. Sentiment, engagement, author reach. Pay per result.
Analyze stocks with summaries, price targets, and analyst recommendations. Track SEC filings, divi…
AI stock intelligence: prices, fundamentals, technicals, news, macro regime, and sector signals.
Search posts, profiles, feeds, threads, and trending topics on Bluesky.