Bluesky Stock Sentiment

Provides an MCP endpoint that analyzes Bluesky stock posts using AI sentiment analysis.
  • typescript

0

GitHub Stars

typescript

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

You have an MCP server that analyzes recent Bluesky posts about stocks and returns a concise sentiment summary. It exposes an MCP endpoint you can connect to from any MCP-compatible client, and it provides quick health checks for easy monitoring.

How to use

You connect to the MCP endpoint to request sentiment analysis of stock-related Bluesky posts. The server runs a tool called analyze_stock_posts that fetches recent public Bluesky posts, filters for stock-related content, analyzes each post with a built-in AI model, and returns a structured summary including totals, percentages, average confidence, and per-post details (author, likes, reposts, timestamp, and URI). Use your MCP client to call the endpoint at the provided MCP path and process the returned JSON for dashboards, reports, or automated alerts.

The service exposes a health endpoint at the root path to help you verify the server is up and serving metadata about the MCP instance.

How to install

Prerequisites: Node 18+, a Cloudflare account, and Wrangler authentication.

Install dependencies and prepare local development environment.

Run the development server to test locally.

Deploy to Cloudflare Workers when ready.

Optionally, synchronize type bindings for MCP with type generation tooling.

# Prerequisites
- Node 18+
- Cloudflare account
- Wrangler installed and authenticated

# Install dependencies
npm install

# Start development server locally
npm run dev

# Deploy to Cloudflare Workers
npm run deploy

# Optional: generate type bindings for MCP
npm run cf-typegen

Configuration and key details

Server name: bluesky_stock_sentiment. The MCP endpoint is exposed at /mcp, and the local development server runs on http://localhost:8787/mcp. The production endpoint follows your Cloudflare Workers subdomain and exposes the same path.

Notes

The sentiment model defaults to @cf/huggingface/distilbert-sst-2-int8, but you can swap it with any Workers AI text-classification model if you prefer.

Stock post filtering relies on keywords you can adjust to fine‑tune what counts as a stock-related post.

The Bluesky public search API is used to gather posts; results may vary due to rate limits or API changes.

API overview

Available endpoint for MCP clients: GET /mcp. This is the primary HTTP transport to interact with the stock sentiment tool. A simple root GET provides service metadata for quick health checks.

Available tools

analyze_stock_posts

Fetches recent Bluesky posts, filters for stock-related text, analyzes each post with Workers AI sentiment model, and returns a concise summary with totals, percentages, average confidence, and per-post details (author, likes, reposts, timestamp, and URI).

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational
Bluesky Stock Sentiment MCP Server - tar-ive/mcp-bluesky-stock-sentiment | VeilStrat