Skip to main content
Glama
Sign In
Web3 Content MCP Server

Web3 Content MCP Server

by greyisworking
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript

Web3 Content MCP Server

MCP server for web3 content management, blockchain data fetching, and content analysis.

Features

Content Management

  • save_content - Save web3 articles, posts, documents to Supabase

  • search_content - Search by keywords, tags, or blockchain

  • get_content - Retrieve content by ID

  • delete_content - Remove content

Blockchain Data

  • get_token_price - Get cryptocurrency prices from CoinGecko

  • get_trending_tokens - View trending cryptocurrencies

  • add_to_watchlist - Track tokens in your watchlist

  • get_watchlist - View watchlist with live prices

Content Analysis

  • analyze_content - Analyze text for web3 topics, mentioned tokens

  • get_web3_news - Fetch latest crypto news

Related MCP server: crypto-projects-mcp

Setup

  1. Install dependencies:

npm install

  1. Run Supabase migration:

    • Go to your Supabase dashboard

    • Run supabase/migrations/001_init.sql in the SQL editor

  2. Configure environment:

cp .env.example .env
# Edit .env with your Supabase credentials

  1. Build:

npm run build

  1. Test with MCP Inspector:

npm run inspect

Claude Desktop Configuration

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "web3-content": {
      "command": "node",
      "args": ["/Users/dahyekim/web3-content-mcp/dist/index.js"],
      "env": {
        "SUPABASE_URL": "your-supabase-url",
        "SUPABASE_KEY": "your-supabase-key"
      }
    }
  }
}

Available Tools

25 tools
add_rss_sourceB

Add a new RSS feed source

Inputs: url (required), name (required), language, source_group.

add_to_watchlistC

Add a token to the watchlist for tracking

Inputs: name (required), symbol (required), notes, blockchain, +2 more.

analyze_contentB

Analyze web3 content for key insights, sentiment, and topics

Inputs: text, content_id, analysis_type.

article_createA

새 Web3 아티클 생성. language로 한/영 톤 전환 가능 (ko=뉴닉 스타일, en=Milk Road 스타일)

Inputs: body (required), style (required), title (required), tags, +3 more.

article_exportB

아티클을 마크다운으로 내보냅니다

Inputs: id (required), include_meta.

article_getA

아티클을 ID로 조회합니다

Inputs: id (required).

article_listC

아티클 목록을 조회합니다

Inputs: limit, style, offset, status, +1 more.

article_searchB

아티클을 검색합니다 (제목+본문)

Inputs: query (required), limit, language.

article_statsC

아티클 통계를 조회합니다

Inputs: no named parameters.

article_templatesB

사용 가능한 아티클 템플릿과 톤앤매너 가이드를 조회합니다

Inputs: style, language.

article_updateC

아티클을 수정합니다

Inputs: id (required), body, tags, style, +4 more.

delete_contentB

Delete a content item by ID

Inputs: id (required).

fetch_rss_articlesB

Fetch new articles from RSS sources and save to database

Inputs: group, source_id.

get_articleC

Get full article details by ID

Inputs: id (required).

get_articlesC

Get saved articles from the database

Inputs: limit, search, unread_only, source_group, +1 more.

get_contentC

Get a specific content item by ID

Inputs: id (required).

get_token_priceC

Get current price and market data for a cryptocurrency

Inputs: token_id (required), currency.

get_trending_tokensA

Get trending cryptocurrencies from CoinGecko

Inputs: no named parameters.

get_watchlistA

Get all tokens in the watchlist with current prices

Inputs: no named parameters.

get_web3_newsC

Fetch latest web3 news from public sources

Inputs: limit, category.

list_rss_sourcesB

List all configured RSS sources for web3 news

Inputs: group, active_only.

mark_articleC

Mark an article as read or bookmarked

Inputs: id (required), is_read, is_bookmarked.

remove_rss_sourceB

Remove an RSS source by ID

Inputs: id (required).

save_contentC

Save web3 content (article, post, document) to the database

Inputs: title (required), content (required), tags, author, +4 more.

search_contentB

Search stored web3 content by keywords, tags, or blockchain

Inputs: tags, limit, query, blockchain.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    C2.7/5.0

    Scored across 25 tools

    Disambiguation2/5

    Multiple tools have unclear boundaries: get_article vs article_get, get_articles vs article_list, and search_content vs article_search appear to serve the same purpose. While some tools (token prices, watchlist) are distinct, the overlapping pairs create significant misselection risk.

    Naming Consistency2/5

    Naming is inconsistent, mixing verb-first (get_article) and noun-first (article_create) patterns, along with preposition-based verbs (add_to_watchlist). No uniform convention exists across the set, making it hard to predict tool names.

    Tool Count3/5

    At 25 tools, the count is at the upper end of 'heavy' and many tools duplicate functionality (e.g., get_articles vs article_list). The set could be streamlined to ~15-18 tools without losing capability, making the current count feel slightly inflated.

    Completeness4/5

    The server covers article CRUD reasonably well (article_create/get/list/update/search/export) and includes content storage, RSS management, and token prices. However, there is no update operation for stored content items and no remove_from_watchlist, leaving minor lifecycle gaps.

    Resources

    Related MCP Connectors

    Related MCP Servers