Connect Arize Phoenix to Claude Code

Read LLM traces, spans, sessions, datasets, experiments and prompts in Arize Phoenix, and annotate spans. Add Toolspoke to Claude Code once and it can use 16 Arize Phoenix actions. Your Arize Phoenix credential stays in Toolspoke, and you choose which actions Claude Code may call.

Set it up in Claude Code

Three steps, the first one once for every toolkit you will ever add.

  1. Add Toolspoke to Claude Code

    Run it in your project, then /mcp to sign in

    claude mcp add --transport http toolspoke https://toolspoke.com/mcp

    The sign-in opens in your browser, and Toolspoke asks you to approve it.

  2. Install Arize Phoenix and connect it

    Add Arize Phoenix to a project in your Toolspoke workspace.

    API key. You provide it once, when you install the connector. Toolspoke encrypts it at rest and decrypts it only for the length of a single call, and the gateway attaches it to the outbound request itself, so it is never part of the arguments an agent sends.

    Phoenix URL
    Phoenix Cloud: the space URL from your browser's address bar, https://app.phoenix.arize.com/s/<space>. Self-hosted: the address your Phoenix serves its UI on, with no path. It must be reachable from the internet; a private-network address is refused.
  3. Choose what Claude Code may do

    All 16 actions start on. Switch off any of the 2 actions that change something in Arize Phoenix, and Claude Code gets a refusal if it tries.

What you can ask Claude Code for

A few of the Arize Phoenix actions that only read, so they are safe to try first.

  • List tracing projects by id and name
  • Fetch one project by id or name
  • List a project's traces, newest first by default, with latency and error counts
  • List a project's sessions (multi-turn conversations), newest first by default

What Claude Code can do in Arize Phoenix

14 actions read, one writes and one deletes or permanently changes something.

Reads

  • List projects

    List tracing projects by id and name. Every trace, span and session call takes a project id or name from here. Also the install's health check.

  • Get project

    Fetch one project by id or name.

  • List traces

    List a project's traces, newest first by default, with latency and error counts. Narrow with filter, e.g. error_count > 0 or latency_ms >= 2000, or by session. include_spans returns every span with its inputs and outputs, which is large and holds your users' content.

  • List spans

    List a project's spans, filtered by trace, span kind (LLM, TOOL, RETRIEVER, AGENT…), status, name, parent or attribute. Pass parent_id "null" for root spans only. Spans carry inputs and outputs.

  • List sessions

    List a project's sessions (multi-turn conversations), newest first by default.

  • List span annotations

    Read the annotations (evaluation labels, scores, human feedback) on some spans.

  • List datasets

    List datasets used for experiments and evaluations.

  • Get dataset

    Fetch one dataset by id, with its example count and versions.

  • Get dataset examples

    Read a dataset's examples, inputs, expected outputs and metadata, at the latest or a named version, optionally one split.

  • List experiments

    List the experiments run against a dataset.

  • Get experiment

    Fetch one experiment, with its run counts and the project its traces went to.

  • List prompts

    List the prompts stored in Phoenix.

  • Get latest prompt

    Fetch the latest version of a prompt, template, model and invocation parameters.

  • Get prompt by tag

    Fetch the prompt version carrying a tag, e.g. production.

Writes

  • Annotate span

    Add or update one annotation on a span, a label, a score, or both, with an explanation. An annotation with the same name and identifier on the same span is replaced.

Deletes or permanently changes

  • Delete trace

    Delete one trace and all its spans and annotations permanently. There is no undo.

Arize Phoenix in Claude Code: questions

Does Claude Code see my Arize Phoenix credential?

No. The credential is stored encrypted in Toolspoke, and the gateway adds it to each call. Claude Code only ever talks to Toolspoke, and the dashboard shows the last four characters of the credential and nothing more.

Can I stop Claude Code from changing things in Arize Phoenix?

Yes. Each of the 16 actions can be switched off for a project. Turn off the 2 that change something and Claude Code can only read.

Will 16 actions crowd Claude Code's context?

No. Toolspoke shows Claude Code five bridge tools, plus a guide where a toolkit has one, and Claude Code searches for the Arize Phoenix action it needs when it needs it. Adding more toolkits does not add more tools to its list.

Can I add it once for every project?

Yes. Add --scope user to the command and Claude Code keeps Toolspoke in every project on this machine. Without it, the server is added to the project you ran the command in.

What does it cost?

Tool calls are free on every plan, and a Arize Phoenix call does not run in a sandbox, so it bills nothing.

Try Arize Phoenix in Claude Code

Free to start, and tool calls cost nothing on any plan.