H
Helicone MCP
42
Stack Score
Editorial pick✓ Verified workingMCP server
Helicone MCP
Helicone LLM gateway + observability ops.
Best for
Best for AI engineering teams running cost-aware LLM observability.
At a glance
- Pricing
- open-source
- Setup time
- 15 minutes
- Learning curve
- easy
- Last verified
- 5/26/2026
What we love
- ✓Helicone-maintained
- ✓Strong cost + cache surface
- ✓OSS self-host
Where it falls short
- −Helicone plan required for cloud
- −Best with Helicone gateway
- −Less feature-rich evals than LangSmith
Pricing
✓ Pricing verified Jun 14, 20261 tier
Open-source
$0
perpetual
- ✓MIT
Overview
MCP server for Helicone — request + cost + cache + prompt analytics, alert + threshold ops. OSS LLM observability gateway exposed to Claude.
Key features
- ●Request + cost analytics
- ●Cache hit rate
- ●Prompt analytics
- ●Alert ops
- ●API key auth
Best use cases
Cost monitoring
Let Claude query Helicone for LLM cost + cache trends.
Threshold alerts
Set up + manage cost/error alerts via Helicone from chat.
Integrations
Similar tools
See all analytics →One AI Stack pick every week.
The tool we’d pay for this week, why we’d pay for it, and what we’d skip. No promo spam.