MCP.so
ログイン

jellyfish-mcp: A Jellyfish MCP Server

@Jellyfish-AI

jellyfish-mcp: A Jellyfish MCP Server について

Jellyfish MCP server

基本情報

カテゴリ

その他

ライセンス

MIT

ランタイム

node

トランスポート

stdio

公開者

Jellyfish-AI

設定

標準の設定はありません

このサーバーの README には解析可能な MCP 設定ブロックが含まれていません。インストール手順はリポジトリをご確認ください。

リポジトリ

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is jellyfish-mcp?

A Model Context Protocol server for retrieving and analyzing data from Jellyfish’s API. It enables natural language queries about engineering metrics, team data, and other Jellyfish information via hosts like Claude Desktop or Cursor.

How to use jellyfish-mcp?

Install by downloading the .mcpb extension for Claude Desktop or use npx jellyfish-mcp-server@latest (or Docker) for other hosts. The server exposes numerous tools corresponding to Jellyfish API endpoints.

Key features of jellyfish-mcp

  • Retrieves Jellyfish API schema and current date
  • Queries company, person, and team metrics
  • Lists and searches teams, people, and deliverables
  • Analyzes AI adoption and impact analytics
  • Searches help center articles

Use cases of jellyfish-mcp

  • Ask “What were our company metrics in May 2026?” and get a natural language answer
  • Request a list of all teams in your organization
  • Find unlinked pull requests for the last month
  • Retrieve sprint summaries and devex insights per team
  • Generate branded engineering investment dashboards (via optional Skills)

FAQ from jellyfish-mcp

Do I need to install PromptGuard before using jellyfish-mcp?

PromptGuard is not bundled with the server. We recommend configuring it before daily use — see PROMPTGUARD.md for setup and SECURITY.md for details.

How do I install jellyfish-mcp for Claude Desktop?

Download the .mcpb extension from the latest release and double-click to install. For other hosts use npx jellyfish-mcp-server@latest or Docker.

What tools does jellyfish-mcp provide?

It provides tools for API schema, current date, AI impact, allocations, delivery, devex, metrics, people, teams, and help center – each corresponding to a specific Jellyfish API endpoint.

Are the optional Skills safe to use?

Skills may ask the LLM to author HTML from Jellyfish data. Because the HTML is generated, using a skill means trusting that both the data and the model’s output are safe. Skills are installed separately and are entirely optional.

Where can I find the full security considerations?

Refer to SECURITY.md in the repository for known risks and limitations before using this server.

コメント

「その他」の他のコンテンツ