MCP server for Bell Feed — crypto Twitter intelligence
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"bell-feed-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# bell-feed-mcp MCP server for [Bell Feed](https://degendar.com) — AI-curated crypto Twitter intelligence from bell notification accounts. ## What It Does Provides 4 tools to Claude Code for querying public Bell Feed data: - **`get_latest_summaries(count)`** — Latest AI-generated summaries with tokens, contracts (EVM + Solana), signals, push_priority/push_reason - **`get_trending_tokens(hours)`** — Token mention frequency rankings over the past N hours - **`get_daily_tldr()`** — Today's TL;DR summary - **`search_summaries(query)`** — Search summaries by keyword, token, or signal Data is sourced from [data.degendar.com](https://data.degendar.com/summaries.json) with 5-minute in-memory caching. ## Install ```bash claude mcp add bell-feed -- uvx bell-feed-mcp ``` Restart Claude Code after installation. ## Usage Ask Claude naturally: - "What's happening in crypto today?" - "Which tokens are trending?" - "Any news about SOL?" - "Give me today's TL;DR" ## Public Data Endpoints | Endpoint | Content | |----------|---------| | `summaries.json` | Hourly AI summaries with tokens, contracts, signals, push_priority, tweet counts | | `daily_tldr.json` | Daily TL;DR digest | | `feed.xml` | RSS 2.0 feed | ## Notes - No API keys required for the MCP server itself - If public data is temporarily unavailable, cached responses are reused when possible
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.