Jellyfish MCP Server

Jellyfish MCP server

Local serverstdio

What is the Jellyfish MCP server?

Jellyfish MCP server. That is what the jellyfish mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

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.

The tools it exposes

The server publishes 8 tools. What each one is for:

  • General — The General tool exposed by this server
  • Allocations — The Allocations tool exposed by this server
  • Delivery — The Delivery tool exposed by this server
  • DevEx — The DevEx tool exposed by this server
  • Metrics — The Metrics tool exposed by this server
  • People — The People tool exposed by this server
  • Teams — The Teams tool exposed by this server
  • Dashboards — The Dashboards tool exposed by this server

Getting it running

The server ships on npm as jellyfish-mcp-server, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

How it compares

Among the team communication options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Jellyfish's toolset — General, Allocations, Delivery and 5 more — is a fair guide to whether it matches your workflow. It is maintained by Jellyfish-AI; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Jellyfish's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
GeneralThe General tool exposed by this server.
AllocationsThe Allocations tool exposed by this server.
DeliveryThe Delivery tool exposed by this server.
DevExThe DevEx tool exposed by this server.
MetricsThe Metrics tool exposed by this server.
PeopleThe People tool exposed by this server.
TeamsThe Teams tool exposed by this server.
DashboardsThe Dashboards tool exposed by this server.

How to install the Jellyfish MCP server

{
  "mcpServers": {
    "jellyfish": {
      "command": "npx",
      "args": ["-y", "jellyfish-mcp-server"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Jellyfish to General.
  • Use Jellyfish to Allocations.
  • Use Jellyfish to Delivery.

Frequently asked questions

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