opik-mcp MCP — Casos de uso, Instalar & Demo ao vivo

Por que usar

Principais recursos

Official, maintained by Comet
Prompt lifecycle: list, get, version, promote
Workspace / project / trace exploration
Dataset + metric operations for evals
Cloud (comet.com) or self-hosted; HTTP bearer auth supported

Demo ao vivo

Como fica na prática

opik.replay ▶ pronto

0/0

Instalar

Escolha seu cliente

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "opik": {
      "command": "npx",
      "args": [
        "-y",
        "opik-mcp"
      ],
      "_inferred": true
    }
  }
}

Abra Claude Desktop → Settings → Developer → Edit Config. Reinicie após salvar.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "opik": {
      "command": "npx",
      "args": [
        "-y",
        "opik-mcp"
      ],
      "_inferred": true
    }
  }
}

Cursor usa o mesmo esquema mcpServers que o Claude Desktop. Config de projeto vence a global.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "opik": {
      "command": "npx",
      "args": [
        "-y",
        "opik-mcp"
      ],
      "_inferred": true
    }
  }
}

Clique no ícone MCP Servers na barra lateral do Cline, depois "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "opik": {
      "command": "npx",
      "args": [
        "-y",
        "opik-mcp"
      ],
      "_inferred": true
    }
  }
}

Mesmo formato do Claude Desktop. Reinicie o Windsurf para aplicar.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "opik",
      "command": "npx",
      "args": [
        "-y",
        "opik-mcp"
      ]
    }
  ]
}

O Continue usa um array de objetos de servidor em vez de um map.

~/.config/zed/settings.json

{
  "context_servers": {
    "opik": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "opik-mcp"
        ]
      }
    }
  }
}

Adicione em context_servers. Zed recarrega automaticamente ao salvar.

claude mcp add opik -- npx -y opik-mcp

Uma linha só. Verifique com claude mcp list. Remova com claude mcp remove.

Casos de uso

Usos do mundo real: opik-mcp

Pull a production trace into your IDE to debug a bad LLM response

👤 LLM app developers ⏱ ~15 min intermediate

Quando usar: A user reports a wrong answer; the trace is in Opik; you want to inspect it without leaving Cursor.

Pré-requisitos

Opik API key — comet.com/site > API Keys (or self-hosted admin)

Fluxo

Find the trace

Search traces in project 'prod-chatbot' where output contains 'I cannot help with that'. Last 24h.✓ Copiado

→ Matching trace IDs + timestamps
Inspect

Open trace ID abc123. Show me the full message chain, tools called, and intermediate reasoning.✓ Copiado

→ Full trace object
Form hypothesis

Why might the model have refused? Compare this trace to a successful one on the same prompt template.✓ Copiado

→ Diff + hypothesis

Resultado: Faster trace-driven debugging without app-switching.

Armadilhas

PII in traces — Configure Opik's redaction before enabling MCP access broadly

Iterate on a prompt template with version tracking

👤 Prompt engineers ⏱ ~25 min advanced

Quando usar: You're tuning a system prompt and want each version saved to Opik for rollback.

Fluxo

Pull current version

Get latest version of prompt 'support-agent-system'.✓ Copiado

→ Current prompt body
Edit and commit

Propose a change to handle escalations better. Show diff. Commit as a new version with message 'add escalation path'.✓ Copiado

→ Diff + new version ID
Eval against dataset

Run this new version against dataset 'support-eval-v1'. Compare pass rate vs previous version.✓ Copiado

→ Metric comparison

Resultado: Data-driven prompt changes, version-controlled.

Armadilhas

No guardrails — a regressive prompt becomes prod — Use Opik's experiment framework: don't promote until pass rate ≥ baseline

Generate a weekly LLM app health report

👤 Eng leads, LLM app PMs ⏱ ~30 min intermediate

Quando usar: You want a Monday-morning digest of cost, latency, error rate, and top failure categories.

Fluxo

Pull last week's metrics

For project 'prod-chatbot': total traces, total tokens, avg latency p50/p95, error count — over last 7 days.✓ Copiado

→ Metrics block
Classify failures

Sample 20 failed traces. Cluster by failure mode. Rank clusters by frequency.✓ Copiado

→ Failure taxonomy
Write the digest

Compose a Markdown digest with the metrics and top 3 failure modes, ready for Slack.✓ Copiado

→ Shareable report

Resultado: Weekly LLM ops awareness without manual dashboard time.

Armadilhas

Metric drift as your app evolves — Version the report template; compare apples to apples week over week

Combine com: notion

Combinações

Combine com outros MCPs para 10× de alavancagem

opik + github

When a prompt regresses, open a GitHub issue with the failing trace

If pass rate drops >5% on 'support-eval-v1' vs last week, create a GitHub issue with the top 3 failing trace IDs.✓ Copiado

opik + notion

Publish weekly LLM health digest to Notion

Compose a Monday digest from last week's Opik metrics and create a Notion page in 'LLM Weekly'.✓ Copiado

Ferramentas

O que este MCP expõe

Ferramenta	Entradas	Quando chamar	Custo
list_projects	workspace_id?	Navigate your workspace	1 API call
list_traces	project, filter?, start?, end?, limit?	Find traces by time range or content	1 API call
get_trace	trace_id	Deep-dive a single trace	1 API call
get_prompt	name, version?	Read a prompt for editing or use in code	1 API call
create_prompt_version	name, template, message?	Commit a new prompt iteration	1 API call
create_dataset	name, items[]	Build an eval dataset	1 API call
get_metrics	project, metric, window	Monitor cost / latency / quality	1 API call

Custo e limites

O que custa rodar

Cota de API: Opik Cloud has per-plan limits; self-hosted is unlimited
Tokens por chamada: Trace listings 1k-5k tokens; single traces 500-3000
Monetário: Opik has a generous free tier; paid plans for scale. MCP itself is free (Apache 2.0).
Dica: Use list_traces with a time window; never call without a range on a busy project.

Segurança

Permissões, segredos, alcance

Escopos mínimos: Opik API key scope the workspace you intend to expose

Armazenamento de credenciais: OPIK_API_KEY env var; HTTP transport uses Authorization: Bearer

Saída de dados: Traces may contain prompts/responses with PII — understand your Opik region and redaction setup

Nunca conceda: An admin-scope key to a shared dev machine

Trace data is often PII-heavy (user prompts). Redact upstream before Opik ingests.
For self-hosted, the MCP needs network reach to your Opik backend — include it in your VPN/firewall plan.

Solução de problemas

Erros comuns e correções

401 Unauthorized (Bearer)

Check OPIK_API_KEY. For self-hosted, also set --apiUrl http://host:5173/api.

Verificar: curl -H 'Authorization: Bearer $KEY' $URL/api/v1/workspaces

Empty trace list despite traffic

Wrong project / workspace. List projects first and confirm UUID.

Self-hosted MCP can't reach backend

Use container networking (same docker network) or map --apiUrl to an externally-reachable URL.

Alternativas

opik-mcp vs. outros

Alternativa	Quando usar	Troca
LangSmith MCP	You use LangSmith for tracing	Different platform; similar capabilities
Langfuse MCP	You use Langfuse (OSS)	Also OSS + self-hostable; different schemas
Arize / Phoenix	You want focus on evals + drift detection	Richer ML-monitoring features; steeper learning curve

Mais

Recursos

📖 Leia o README oficial no GitHub

🐙 Ver issues abertas

🔍 Ver todos os 400+ servidores MCP e Skills