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.
@Jellyfish-AI
基本信息
Jellyfish MCP server
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
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.
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.
PromptGuard is not bundled with the server. We recommend configuring it before daily use — see PROMPTGUARD.md for setup and SECURITY.md for details.
Download the `.mcpb` extension from the latest release and double-click to install. For other hosts use `npx jellyfish-mcp-server@latest` or Docker.
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.
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.
Refer to SECURITY.md in the repository for known risks and limitations before using this server.
Painless E2E Automation for Mobile and Web

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.
🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。
Hindsight: Agent Memory That Learns
评论