Integrate with Opik's MCP server

One command connects your coding assistant to your traces — and teaches it how to create them in the first place:

$ opik mcp configure

What this unlocks

Things you can ask for and get in one turn, without leaving your editor:

Instrument this project

Your assistant adds tracing in the right places for your framework, runs the app, and confirms the traces arrived.

Why did this get worse?

It reads the failing traces and their scores directly, instead of you pasting screenshots into chat.

Build me a test suite

From traces you already have, so the cases are real ones your app hit.

Keep an eye on this

Every later change can be checked against real traces as you make it.

Quick setup with the Opik CLI

The CLI detects your AI client (Claude Code, Cursor, VS Code Copilot, Codex, opencode), picks the right server for your Opik deployment, configures it, and then checks that the configuration it just wrote actually works.

Prefer not to use the CLI? You can wire up any client by hand — skip to Manual setup.

Asking your coding agent to do this works. Setup writes into your AI client’s own configuration, so it never happens on a run that did not ask for it — but naming what you want is asking, and that works without a terminal:

$ opik configure --install-mcp --install-skills   # Opik + MCP + skill pack
$ opik mcp configure --ai-client cursor              # just the server, one client

A run that names nothing and has no terminal — a CI job, a Docker build — writes nothing, which is the behaviour you want there.

Install the Opik CLI

The CLI ships with the opik Python package. --upgrade installs the latest release, which is what you want — these commands gain clients and flags often:

$ pip install --upgrade opik

Configure the MCP server

$ opik mcp configure

This reuses your existing Opik configuration (~/.opik.config); if you haven’t configured Opik yet, the wizard offers to do it for you first.

You’ll choose your AI client from a list, then confirm the MCP server and the Opik skill pack for it.

Restart your AI client

Assistants read their configuration at startup, so start a new session before trying the prompts in Start using it.

If your client isn’t detected, see Manual setup.

Check your setup

Each AI client keeps its own copy of the MCP configuration, which isn’t updated automatically when your Opik configuration changes. To see what every detected client points at — and whether it still matches your current Opik configuration — run:

$ opik mcp status

It prints your active Opik configuration, then each AI client that has the Opik MCP server configured: the config file it lives in, the server it reports to (hosted or local), its workspace, and whether it has drifted from your Opik configuration.

Your Opik configuration
    File          ~/.opik.config
    Environment   https://www.comet.com/opik/api
    Workspace     my-workspace
Opik MCP server — configured for 1 AI client:
  Claude Code
    Config        ~/.claude.json
    Connection    Hosted (HTTP + OAuth)
    Reports to    https://www.comet.com/opik/api/v1/mcp
    Status        ✓ in sync with your Opik configuration

A client that has drifted is flagged ✗ OUT OF SYNC — re-run opik mcp configure to fix it.

A client keeps its MCP connection for the lifetime of its process. After changing your Opik configuration or re-running opik mcp configure, restart your AI client so it reconnects with the updated settings.

To view just your active Opik configuration (file path, environment, workspace):

$ opik configure status

To refresh the skill pack, re-run opik mcp configure — it rewrites the pack from the latest published version. Assistants read their skills at session start, so start a new session afterwards.

Start using it

Paste any of these into your assistant. Start with the first — it exercises the whole loop, so if it works, everything is wired up.

Instrument this project, end to end

Add Opik tracing to this project, then run it and show me the trace you created.

Confirm where this repo is logging

List my Opik projects and tell me which one this repo is logging to.

Find what's slow or failing

Look at the last 20 traces in Opik and tell me what's slowest and what's failing.

Turn real traces into a test suite

Build an Opik test suite from my recent traces, then run it and show me the scores.

From then on your assistant can check its own work against real traces every time you change something.

The tools you’ll have

Your assistant gets six tools. It picks between them on its own — this is here so you know what it can reach for:

Tool	What your assistant can do with it
`read`	Fetch one thing by id, name, or `opik://` URI — a trace, span, project, experiment, prompt, or test suite.
`list`	Page through any of those, optionally filtered by name.
`write`	Log traces and spans, score, comment, save prompt versions, manage test suites and experiments.
`schema`	Look up the exact payload shape for a write, so it constructs valid ones.
`ask_ollie`	Investigate or synthesize across entities via Opik’s in-product assistant.
`run_experiment`	Run an evaluation experiment end to end.

To see a payload shape yourself, ask “show me the schema for trace.create” — or read the full list.

Opik Cloud and self-hosted deployments

opik mcp configure works the same whether you’re on Opik Cloud, self-hosted, or a local install — it sets up the right server for your deployment automatically.

Opik Cloud (hosted server)

On Opik Cloud, the CLI registers the hosted MCP server over HTTP. Your AI client signs in with a browser-based OAuth flow on first connect, so:

No API key is stored in the client’s config — you authenticate through OAuth in the browser.
uv is not required — there is no local process to run.
Your workspace is selected during the OAuth sign-in, so a hosted server shows no workspace in opik mcp status.

Self-hosted and local (local server)

If no hosted server is available for your environment, the CLI sets up the local server, which runs on demand via uvx opik-mcp. This requires uv; if it isn’t on your PATH the CLI stops and prints the exact command to install it for your platform.

Workspaces

For the local server your workspace is written into the client’s config, so it has to be the right one. If your Opik configuration doesn’t name a workspace and your account has more than one, opik mcp configure refuses to continue rather than falling back to your account default:

Your Opik configuration does not name a workspace, but this account has 3:
acme-ai, acme-research, sandbox. The MCP server would fall back to your default
workspace and silently read from the wrong place. Run `opik configure` and choose
a workspace, then re-run `opik mcp configure`.

Guessing here is the one failure this CLI can produce that doesn’t look like a failure: your agent would read real traces from the wrong workspace and report them confidently. Run opik configure, pick a workspace, and re-run.

Manual setup

Prefer to wire it up yourself, or your client wasn’t detected? Configure any client by hand below.

For the skill pack on a client the CLI doesn’t cover, the community skills CLI knows the skill directories for 76+ agents (needs Node.js):

$ npx skills add comet-ml/opik-skills

There are two servers you can add by hand. opik mcp configure picks the right one for you, but you can also add either directly in your AI client’s MCP settings:

Hosted server (HTTP + OAuth) — available on Opik Cloud and any deployment that provides it. No API key is stored; your client signs in through the browser.
Local server (uvx opik-mcp, stdio) — runs on your machine with your credentials in the client’s env block.

Hosted server (Opik Cloud)

The hosted server connects over HTTP and signs in with a browser-based OAuth flow on first connect — no API key is stored in the client config. Point your client at your deployment’s MCP endpoint, which is your Opik API base plus /v1/mcp. On Opik Cloud that is https://www.comet.com/opik/api/v1/mcp.

Claude Code

Cursor

VS Code Copilot

Add the server with one command:

$ claude mcp add --transport http opik-mcp https://www.comet.com/opik/api/v1/mcp

Or edit ~/.claude.json directly:

1 {
2   "mcpServers": {
3     "opik-mcp": {
4       "type": "http",
5       "url": "https://www.comet.com/opik/api/v1/mcp"
6     }
7   }
8 }

Restart Claude Code and complete the browser sign-in when prompted, then ask in the chat: “list my Opik projects”.

Local server (uvx)

The local server runs on demand via uvx opik-mcp (requires uv), with your credentials passed through the client’s env block.

opik-mcp is now a Python package. If you previously ran the npx-based JavaScript server, use the uvx opik-mcp commands below in place of npx -y opik-mcp.

OPIK_WORKSPACE is optional — you can omit the OPIK_WORKSPACE line/key entirely and the server uses the default workspace (correct for local/OSS installs). The snippets below include it for completeness; set it only if you connect to a named cloud workspace.

Claude Code

Cursor

VS Code Copilot

Codex

opencode

MCP Inspector

Add the server with one command:

$ claude mcp add --transport stdio opik-mcp \
>   --env OPIK_API_KEY=<your-key> \
>   --env OPIK_WORKSPACE=<your-workspace> \
>   -- uvx opik-mcp

Or edit ~/.claude.json directly:

1 {
2   "mcpServers": {
3     "opik-mcp": {
4       "type": "stdio",
5       "command": "uvx",
6       "args": ["opik-mcp"],
7       "env": {
8         "OPIK_API_KEY": "<your-key>",
9         "OPIK_WORKSPACE": "<your-workspace>"
10       }
11     }
12   }
13 }

Restart Claude Code, verify with /mcp (opik-mcp should appear as connected), and then ask in the chat: “list my Opik projects”.

Self-hosted Opik. Add COMET_URL_OVERRIDE to the env block (and OPIK_URL if Opik lives at a non-default path). ask_ollie and run_experiment are available on Comet Cloud only — on self-hosted those calls fail at dispatch; use read / list / write directly.

Ollie & auto-approve

By default, writes that Ollie performs mid-stream (scores, comments, prompt versions, test-suite items) execute without a per-action confirmation step. Each auto-approved write is logged as a JSON audit row on the opik_mcp.audit Python logger.

To require manual confirmation instead, set OPIK_MCP_AUTO_APPROVE=disabled in the server’s env block. Ollie’s confirmation requests then surface as typed errors that you can re-issue manually.

ask_ollie and run_experiment are available on Comet Cloud only — on self-hosted those calls fail at dispatch; use read / list / write directly.

Known client limits

Cursor enforces a 60-second hard tool-call timeout that does not reset on progress notifications. Long ask_ollie turns will fail on Cursor. For long-running investigations, use Claude Code or VS Code Copilot.

Example conversation

A typical investigative loop using Claude Code:

You: Why did the experiment “gpt-4o-rerank-v3” regress on factuality?

Claude: (calls ask_ollie) Three traces failed because the reranker dropped the system message. The remaining 12 traces scored above 0.8…

You: Score the bottom 3 traces 0.2 with reason “dropped system message”.

Claude: (calls write with score.create ×3) Done — three scores recorded on traces <id-1>, <id-2>, <id-3>.