[ MCP SERVER SUMMARY ]
Jellyfish MCP server summary
Jellyfish MCP connects AI assistants to engineering analytics and software delivery intelligence. Bifrost keeps API tokens centralized and limits which engineering metrics tools each team can invoke.
| Property | Details |
|---|---|
| Company | Jellyfish |
| Connection type | STDIO |
| Authentication | Jellyfish API token |
| Package or endpoint | jellyfish-mcp |
| Capabilities | Engineering analytics, Delivery metrics, Team and investment insights |
| Official documentation | Jellyfish MCP documentation |
Before you start
- A Jellyfish account and API token
- Follow the official jellyfish-mcp README for install
What you can do with Jellyfish
- Ask agents for delivery trends without exposing the Jellyfish UI to every user
- Separate exec-read vs eng-deep-dive tool access with virtual keys
- Audit metric exports requested by AI assistants
[ HOW TO CONNECT ]
Connect Jellyfish to Bifrost in three steps
Install Bifrost
Start the gateway locally or deploy in your VPC.
npx -y @maximhq/bifrost
Add Jellyfish in MCP Gateway
Open MCP Gateway in the Bifrost dashboard, click New MCP Server, and choose STDIO. Or register via the API below.
• Verify package name and env var names against the Jellyfish MCP GitHub README.
• Treat engineering metrics as sensitive — tighten tools_to_execute for most keys.
Point clients at Bifrost /mcp
Configure Claude Desktop, Cursor, or Claude Code to use your Bifrost endpoint with a virtual key instead of connecting directly to Jellyfish.
{
"mcpServers": {
"bifrost": {
"url": "http://localhost:8080/mcp",
"headers": {
"Authorization": "Bearer vk_your_virtual_key"
}
}
}
}[ EXAMPLE CONFIG ]
Register Jellyfish via API
Add this MCP client with a POST to /api/mcp/client. See Connecting to MCP Servers for full options.
curl -X POST http://localhost:8080/api/mcp/client \
-H "Content-Type: application/json" \
-d '{
"name": "jellyfish",
"connection_type": "stdio",
"stdio_config": {
"command": "uvx",
"args": [
"jellyfish-mcp"
],
"env": {
"JELLYFISH_API_TOKEN": "env.JELLYFISH_API_TOKEN"
}
},
"tools_to_execute": [
"*"
]
}'[ WHY BIFROST ]
Run Jellyfish through one governed gateway
Access control
Virtual keys, RBAC, and tool allowlists per team or agent.
Cost governance
Attribute MCP tool spend alongside LLM usage in one view.
Observability
Log every tool call with latency, server, and virtual key metadata.
Credential isolation
Upstream secrets stay in the gateway — not on every laptop.
[ FAQ ]
Common questions
What does the Jellyfish MCP server do?
Jellyfish exposes engineering analytics, delivery metrics, team and investment insights to MCP-compatible AI clients. Bifrost connects to it as an upstream MCP client and exposes approved tools through one governed /mcp endpoint.
How does Jellyfish authenticate when used with Bifrost?
Jellyfish uses Jellyfish API token. Store credentials in Bifrost's environment or credential configuration so they stay at the gateway instead of being copied into every AI client.
Can Claude Desktop, Cursor, or Claude Code use Jellyfish through Bifrost?
Yes. After registering Jellyfish in Bifrost, point any HTTP MCP-compatible client at the Bifrost /mcp endpoint and authenticate with a virtual key. The client sees only the tools allowed for that key.
[ RELATED SERVERS ]
More MCP integrations
GitHub
GitHub's official MCP Server.
GitLab
GitLab's official MCP server enabling AI tools to securely access GitLab project data, manage issues, and perform repository operations via OAuth 2.0.
Honeycomb
Give AI agents access to Honeycomb observability data for investigating production systems, traces, and telemetry.