mcp-server
MCP Servershape-network/mcp-server
An MCP server that gives AI assistants direct access to Shape network onchain metrics, gasback distributions, and NFT analytics.
7 7MITUpdated 2025-08-08
62
GoodOverview
This Model Context Protocol (MCP) server integrates AI agents with the Shape blockchain ecosystem. Built on the xmcp framework, it provides structured modular tools for inspecting network health, querying NFT collections and wallet holdings, estimating and tracking gasback creator earnings, and monitoring ecosystem stack achievements.
Capabilities
- ▸Retrieve chain status and gas metrics
- ▸Fetch NFT collection analytics and holder data
- ▸Analyze creator gasback rewards and simulate earnings
- ▸Monitor user stack achievements
- ▸Optional Redis caching for performance optimization
Best for
Querying current Shape network status, RPC health, and gas prices, Analyzing NFT collection statistics and checking wallet ownership, Inspecting creator gasback earnings and simulating reward payouts, Tracking user progress and achievements within the Shape Stack ecosystem
Works with
CursorClaude Code
Evoa Score breakdown= Σ (score × weight)
62Task usefulness20%88 → +17.6
実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析
Code quality15%85 → +12.8
実装・指示の品質。 — AIによるSKILL.md/README解析
Maintenance15%25 → +3.8
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
Documentation12%27 → +3.2
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
Security15%80 → +12.0
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
Originality10%70 → +7.0
ありふれたラッパーではない独自性。 — AIによる独自性判定
Popularity8%34 → +2.7
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%50 → +2.5
対応AIエージェントの広さ。 — AIによる対応エージェント判定
Weighted total61.6 / 100
ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
Requires API keys for external services like Alchemy. Ensure keys are properly managed in environment variables and not exposed publicly.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.