Opik TypeScript and JavaScript SDK
Opik MCP server is a hosted integration for AI assistants that speak the Model Context Protocol. Opik TypeScript and JavaScript SDK.
Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.
Once Opik is connected, these are the calls the assistant has available:
Production — Ready Monitoring**: Scalable dashboards and online evaluation rulesCapability — OpikFramework-agnostic — YesIntegration — DescriptionADK — Log traces for Google Agent Development Kit (ADK)AG2 — Log traces for AG2 LLM callsAIsuite — Log traces for aisuite LLM callsAgno — Log traces for Agno agent orchestration framework callsAnthropic — Log traces for Anthropic LLM callsAutogen — Log traces for Autogen agentic workflowsBedrock — Log traces for Amazon Bedrock LLM callsBytePlus — Log traces for BytePlus LLM callsPlenty of AI and media services servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Opik's toolset — Production, Capability, Framework-agnostic and 11 more — is a fair guide to whether it matches your workflow. It is maintained by cometml; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| Production | Ready Monitoring**: Scalable dashboards and online evaluation rules. |
| Capability | Opik |
| Framework-agnostic | Yes |
| Integration | Description |
| ADK | Log traces for Google Agent Development Kit (ADK) |
| AG2 | Log traces for AG2 LLM calls |
| AIsuite | Log traces for aisuite LLM calls |
| Agno | Log traces for Agno agent orchestration framework calls |
| Anthropic | Log traces for Anthropic LLM calls |
| Autogen | Log traces for Autogen agentic workflows |
| Bedrock | Log traces for Amazon Bedrock LLM calls |
| BytePlus | Log traces for BytePlus LLM calls |
| Cohere | Log traces for Cohere LLM calls |
| CrewAI | Log traces for CrewAI calls |
{
"mcpServers": {
"opik-1": {
"command": "uvx",
"args": ["opik"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.