FAQ (answers come from our records)
How do I install it?
We did not find an install command for this repository (our install coverage is only about 4%). Check its README or releases page.
Who is it for?
We filed it under these tags: MCP 服务. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
first catalogued 2026-10-14;last seen 2026-10-16。There is no official certification or quality rating here — we record sources and dates only.
Jellyfish MCP Server
以下摘录自该仓库的 README(片段) · 在 GitHub 读完整 README →
> **Security Notice**: There are known risks and inherent limitations in this implementation. Refer to SECURITY.md before using.
> [!IMPORTANT]
> PromptGuard is not bundled with this server. We recommend configuring it before using jellyfish-mcp daily — see PROMPTGUARD.md for setup and SECURITY.md before using.
Overview
A Model Context Protocol server for retrieving and analyzing data from Jellyfish's API. This server allows a host (e.g. Claude Desktop or Cursor) to interact with your Jellyfish instance, enabling natural language queries about your engineering metrics, team data, and other information available through the Jellyfish API.
Once you have the Jellyfish MCP connected, you can ask questions about your Jellyfish data, such as:
- "What were our company metrics in May 2026?"
- "Can you get a list of my organization's teams?"
- "What are the unlinked pull requests for the last month?"
Install
See **INSTALL.md** for the full setup guide. Quick links:
- **Claude Desktop** — download the .mcpb extension, then double-click to install
- **Claude Code, Cursor, VSCode** — npx jellyfish-mcp-server@latest (recommended) or Docker
Develop
Want to modify the source or run from a local clone? See **DEVELOPMENT.md**.
Tools and Resources
The server provides several tools for interacting with the Jellyfish API. Each tool corresponds to a specific Jellyfish API endpoint and allows you to retrieve or search for data as described in the API.
General
- api_schema - Retrieves the complete API schema with all available API endpoints
- get_current_date - Returns today's date in the specified timezone
AI Impact
- ai_company_adoption_analytics
- ai_company_impact_analytics
- ai_person_adoption
- ai_person_adoption_analytics
- ai_team_adoption_analytics
- ai_team_impact_analytics
Allocations
- allocations_by_person
- allocations_by_team
- allocations_by_investment_category
- allocations_by_investment_category_person
- allocations_by_investment_category_team
- allocations_by_work_category
- allocations_by_work_category_person
- allocations_by_work_category_team
- allocations_filter_fields
- allocations_summary_by_investment_category
- allocations_summary_by_work_category
Delivery
- deliverable_scope_and_effort_history
- work_categories
- get_deliverable
- search_deliverables
DevEx
- devex_insights_by_team
Metrics
- company_metrics
- person_metrics
- team_metrics
- team_sprint_summary
- unlinked_pull_requests
People
- list_engineers
- search_people
Teams
- list_teams
- search_teams
Help Center
- search_articles
- get_article
Skills
In addition to the MCP tools above, the Jellyfish MCP pairs with optional Agent Skills. Skills can similarly be invoked throughout the chat conversation, but are not bundled with the MCP and need to be independently installed. To install a skill in Claude Desktop, download its .skill file from the latest release and double-click to install. For other host applications, install the skill directly from the skills/ directory.