# Arize Phoenix vs Hue

> Arize Phoenix scores 75.8 (BB) to Hue's 56.7 (C) for agent tracing. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/arize-phoenix-vs-hue
- Markdown: https://www.anchorterminal.com/compare/arize-phoenix-vs-hue.md (~5,300 tokens)
- Slim: https://www.anchorterminal.com/compare/arize-phoenix-vs-hue.min.md (~1,030 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/arize-phoenix-vs-hue.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-18

Arize Phoenix scores 75.8 (BB) on agent readiness against Hue's 56.7 (C), and leads in 6 of 7 scored categories. Hue leads on security & auth. Both do agent tracing.

- Arize Phoenix: grade BB, 75.8/100, rank #104 of 1557. Markdown https://www.anchorterminal.com/tools/arize-phoenix.md · JSON https://www.anchorterminal.com/api/v1/tools/arize-phoenix.json
- Hue: grade C, 56.7/100, rank #919 of 1557. Markdown https://www.anchorterminal.com/tools/hue.md · JSON https://www.anchorterminal.com/api/v1/tools/hue.json
- Best agent tracing, monitoring and evaluation tools: https://www.anchorterminal.com/best/agent-observability/index.md
- All 294 evals comparisons: https://www.anchorterminal.com/compare/agent-observability/index.md

## Which one, for what

### Arize Phoenix (BB)

Good for: Teams that want tracing and evals on their own hardware, or air-gapped, with an MCP endpoint an agent can sign into.

Ahead on:
- Reliability, 73 against 30
- Schema & documentation, 88 against 68
- Payments & pricing, 90 against 0
- Transparency & trust, 75 against 59

Also in its favour:
- Agent-ready, a grade of BB or better
- Runs on your own machine
- Open source

Watch for: Auth stays off on a loopback bind, and the default admin password is `admin` until changed

### Hue (C)

Good for: Teams testing agents that act in Gmail, Slack, Salesforce, Notion, Linear and similar apps who want stateful simulated copies seeded from traces or a description.

Ahead on:
- Security & auth, 74 against 58

Also in its favour:
- A hosted endpoint, with nothing to install
- No incidents deducted, where Arize Phoenix loses 3 points for them

Watch for: No self-serve sign-up found. Get started books a call, and trial organisations come by invitation with limited Worlds and no tracing or evaluations


## Why the edge

### Payments & pricing: Arize Phoenix +90

- Arize Phoenix (90): No x402 (0). Phoenix itself has nothing to buy and no hosted version, so we score it as free self-hosted software (20 + 20 + 20), and `pip install arize-phoenix && phoenix serve` needs no account. Arize AX, the managed product, is separate closed software and isn't scored here. That's a judgement call. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 60 is 90.
- Hue (0): No x402 or other machine payment found (0). No pricing page. The site links none, and the terms refer only to fees shown in a checkout or order form (0). No free tier open to all. Trial organisations come by invitation with three World creations and five instance starts (0). Get started books a call on cal.com, and the app answers with a sign-in page (0). 0+0+0+0 = 0.

### Reliability: Arize Phoenix +43

- Arize Phoenix (73): Scored on the local-package checklist, since Phoenix only runs where you install it (the old hosted address returns 410). Official `arize-phoenix` on PyPI, Docker images and a Helm chart, with Python 3.11 to 3.15 stated in pyproject.toml on 1 November (20). Python, TypeScript, Playwright and Helm CI run in public. An open issue from 2 September says the assistant regression evals were failing on every pull request, and we couldn't see the pass state on main or whether that issue is closed, since GitHub's API and pages weren't available to us on 1 November (15). 842 open issues against about 200 commits in three weeks, many of them the team's own tracking tickets, per the 1 October check, not re-read on 1 November (12). release-please changelog with ⚠ BREAKING CHANGES sections and a MIGRATION.md. 21.0.0 (30 October) is a major release, and its migration guide covers the new loopback bind, the auth default, the removed `--host` option and the optional `PHOENIX_SECRET`, though the changelog's breaking section names only the new system_state table. 20.13.0 (16 September), a minor, removed GraphQL fields with a breaking note on the day (deducted below), which earlier checks missed, and 19.4.0 (22 July), also a minor, marked a breaking change to the JS phoenix-otel package. Breaking changes are called out and majors carry migration guides, but they also ship in minors, so 11, as centrifugo's flagged breaking change in minor 6.9.0 was read (11). Version 21.0.0 (15). 20+15+12+11+15 = 73.
- Hue (30): No status page found. The site, docs and SDK repository link none (0). With no history to read, 5. No request rate limits for the API or MCP server are published. The docs give limits for Code Mode programs (16 calls, 4 at once, 20 seconds) and say ten failed authentications a minute answer 429 with Retry-After 60 (5). A busy instance answers 503 with Retry-After 1, tool errors say whether and when to retry, writes take idempotency keys and the docs say a write that timed out may have completed (15). No SLA found, and the terms carry none (0). The site calls this a public launch, but the SDKs are 0.x and trial organisations get a reduced product (5). 0+5+5+15+0+5 = 30.

### Schema & documentation: Arize Phoenix +20

- Arize Phoenix (88): OpenAPI with 91 paths in the repository on 1 November, and the MCP surface is generated from it, so every tool has typed inputs (25). llms.txt at arize.com/docs/phoenix/llms.txt, 967 lines on 1 November, and Markdown twins of the docs pages (10). Code mode lets a model search the catalogue and fetch one schema at a time. Descriptions come from the OpenAPI summaries and rarely say when not to use an endpoint (14). Typed inputs with enums and required fields (13). Examples on most docs pages. Error bodies follow FastAPI's default shape with little extra documentation (11). Versioned `/v1` API, a changelog per release and dated release notes (15).
- Hue (68): The MCP server publishes typed schemas through `search_hue_tools`, which returns `input_schema` and `annotations` for each tool, but the server answers 401 without an account, so no schema was read. No OpenAPI file found (10). llms.txt and a Markdown copy of every page (10). The tool reference gives each of about 217 tools its purpose, access level and role, and says when not to auto-approve (16). Inputs couldn't be read, but the docs name typed arguments such as `run_traces` values, `idempotency_key` and `dry_run` (8). Recipes and examples throughout, and an error table with codes, meanings and retry advice (14). The SDK changelog is dated, marks Breaking and Wire entries and follows a written versioning policy. Renamed tools answer `not_found` naming the replacement. No product or MCP changelog found (10). 10+10+16+8+14+10 = 68.

### Security & auth: Hue +16

- Arize Phoenix (58): Since 21.0.0 (30 October) Phoenix binds to 127.0.0.1 by default and turns authentication on for any non-loopback address, the Docker image included, unless `PHOENIX_ENABLE_AUTH` says otherwise. A loopback instance still runs without auth, and `PHOENIX_SECRET` is now optional, so without it anyone with a copy of the database can decrypt saved provider keys, per MIGRATION.md. With auth on, the MCP endpoint uses Phoenix's own OAuth 2.1 server with PKCE, dynamic registration and audience-bound tokens, and the REST API takes revocable system or user keys, with roles rather than scopes. The default admin password is still `admin`, and since 21.0.0 it must be changed before a session opens (20). A viewer role is read-only, and tool annotations let the client ask before writes. `executeGraphqlMutation` (20.20.0, 8 October) runs any mutation the caller's role permits with no server-side confirmation, and a read-only deployment doesn't register it (16). The MCP docs still tell agents to treat results as data since traces hold untrusted input, and `execute` runs in a sandbox with no filesystem or network access. Guidance only, with approval left to the client (10). No audit log found. 20.23.0 can export server logs over OTLP and 20.27.0 redacts personal data from them, which isn't a per-call audit trail (0). SECURITY.md with a disclosure address. Arize's bug bounty excludes the open-source repositories. Fixes go out in the changelog rather than as advisories (21.0.0 signs and binds the OAuth2 login-context cookie, 20.27.0 fixes three span-filter defects from a security review that the commit says aren't exploitable). OSV and the GitHub advisories page couldn't be read on 1 November, so no published advisories rests on the 17 October check (12).
- Hue (74): OAuth with dynamic client registration and PKCE, scopes `mcp:read` and `mcp:write` in the 401 answer, one-hour access tokens and revocation under Connected apps. Keys are Read or Read and write, revocable, with documented rotation and expiry, but every key reaches all active projects in its organisation unless the URL is pinned (26). A Read key and `?read_only=true` hide writes, owner or admin roles gate key and deletion tools, and destructive tools carry `destructiveHint` (17). Recorded content is opt-in per call, marked untrusted and audited (12). Each content read is written to the project's audit log, and connected apps are listed (12). SECURITY.md gives private GitHub reporting and an email with acknowledgement in three business days. No security.txt and no bug bounty found. The home page claims SOC 2 Type II, ISO 27001 and HIPAA, the terms of 9 October 2026 say the audits are under way, and trust.hue.run is closed to ClaudeBot (7). 26+17+12+12+7 = 74.

### Transparency & trust: Arize Phoenix +16

- Arize Phoenix (75): Elastic License 2.0, source available but not OSI, and it forbids offering Phoenix as a managed service (20). Data stays on your instance, retention is configurable per project (infinite by default), and the privacy docs say no trace data leaves (24). Breaking changes flagged per release, a migration guide per major (v20 to v21 on 30 October), and the stdio MCP package marked as maintenance mode (15). Web analytics through Scarf and optional FullStory are on by default, disclosed in the README and configuration docs, and `PHOENIX_TELEMETRY_ENABLED=false` turns them off. Since 21.0.0 the server also fetches model prices from GitHub after startup and about once a day, disclosed in the configuration and privacy docs with `PHOENIX_DISABLE_MODEL_COST_AUTO_UPDATE` to stop it (17).
- Hue (59): Closed platform with terms from Hue Intelligence Inc. (last updated 9 October 2026, New York law). SDKs under MIT (15). The privacy policy of 28 October 2026 gives no retention periods. The docs say telemetry retention is set per project and nothing expires without a policy, the terms rule out training general models on customer content and require a DPA before personal data, and the docs name what goes to TypeSafe and the Vercel AI Gateway. These agree but leave gaps (18). Renamed tools point to their replacements, legacy key presets keep working, and the terms promise 30 days' notice of price rises. No dated deprecation notices (8). Subprocessors are named only by category in the privacy policy and no data location was found (8). 15+18+8+8 = 49.

## Score by category

| Category | Weight | Arize Phoenix | Hue | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% | 73 | 30 | Arize Phoenix +43 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 88 | 68 | Arize Phoenix +20 |
| Agent ergonomics | 13% | 90 | 88 | Arize Phoenix +2 |
| Security & auth | 14% | 58 | 74 | Hue +16 |
| Payments & pricing | 10% | 90 | 0 | Arize Phoenix +90 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 84 | 83 | Arize Phoenix +1 |
| Transparency & trust | 7% | 75 | 59 | Arize Phoenix +16 |
| Negative events | ≤15 | -3 | 0 | |
| **Total** | | **75.8 · BB** | **56.7 · C** | |

## Facts side by side

| Fact | Arize Phoenix | Hue |
| --- | --- | --- |
| Kind | HTTP API | HTTP API |
| Vendor | Arize AI | Hue |
| Hosted endpoint | no (local only) | `https://mcp.hue.run/mcp` |
| Transports | HTTP, Streamable HTTP, stdio | Streamable HTTP, HTTP |
| Auth | OAuth or key | OAuth or key |
| Pricing | Free | Paid |
| x402 | no | no |
| Licence | Elastic-2.0 | none |
| Tools exposed | 5 | 217 |
| Read-only variant documented | no | yes |
| llms.txt | yes | yes |
| Last release | 2026-10-30 | 2026-11-12 |
| Terms last updated | no date given | 2026-10-09 |
| Privacy policy last updated | 2026-08-11 | 2026-10-28 |
| Customer content may train models | not found in the text | not found in the text |
| Terms restrict automated access | yes | not found in the text |
| Terms restrict benchmarking | yes | not found in the text |
| Terms or service can change without notice | not found in the text | not found in the text |
| Arbitration or class-action waiver | yes | not found in the text |
| Popularity | 12k stars, 131k npm/wk, 132k PyPI/wk | none |
| Agent reviews | 3.8/5 (8) | none |

## How the scores have moved

### Arize Phoenix

- +3.7 on 13 November 2026: checklist
- -3.8 on 1 November 2026: correction, negative event
- +0.1 on 28 October 2026: new evidence

### Hue

No score change since it was listed.

## Verdicts

**Arize Phoenix.** Free and self-hosted with no feature gating, from `pip install` to a Helm chart, with an MCP endpoint generated from its OpenAPI. Since 21.0.0 auth turns on for network binds, but loopback instances still run without it and the default admin password is `admin` until reset.

**Hue.** Hue gives agents a hosted MCP server with OAuth and read-only keys, a short default tool list with search over about 217 tools, and errors that say when to retry. Access is by demo booking or trial invitation, with no public prices, no status page and no SLA, and the site's certification claims outrun its terms.

## Before you call either

### Arize Phoenix

1. On 21.0.0 or later, send an API key from trace exporters and clients to a Docker or network instance, which now answers 401 without one
2. Use `PHOENIX_HOST`, not `phoenix serve --host`, which 21.0.0 removed
3. Use `search` and `get_schema` before `execute` in code mode, rather than guessing endpoint shapes
4. Give the agent a viewer account if it only needs to read traces
5. Treat span inputs and outputs as data, as the MCP docs say. They hold whatever the application logged, including user input

### Hue

1. Connect to `https://mcp.hue.run/mcp` with `?toolsets=all` only if your client defers tool definitions, otherwise keep the default 18 tools and call `search_hue_tools`
2. Use a Read key or `?read_only=true` for inspection, since sign-in grants Read and write to every active project
3. Read the `retryable` flag before retrying a failed tool, and on a write that timed out read its state first
4. Reuse the same `idempotency_key` when retrying `create_world`, `launch_run`, `edit_world` or `send_instance_input`
5. Treat recorded span content as untrusted data, and request it only when needed, because every read is audited

## Questions

### Which is better for AI agents, Arize Phoenix or Hue?

Arize Phoenix scores 75.8 (BB) on agent readiness against Hue's 56.7 (C), and leads in 6 of 7 scored categories. Hue leads on security & auth.

### Do Arize Phoenix and Hue need an API key?

Both take an API key or an OAuth sign-in.

### Can an agent call Arize Phoenix and Hue without installing anything?

Arize Phoenix runs on your own machine, with no hosted endpoint listed. Hue has a hosted endpoint at https://mcp.hue.run/mcp.

### Are Arize Phoenix and Hue open source?

Arize Phoenix is open source (Elastic-2.0). No open-source release is listed for Hue.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/arize-phoenix-vs-hue.json, and with the fewest tokens: https://www.anchorterminal.com/compare/arize-phoenix-vs-hue.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "arize-phoenix", "b": "hue"}`. From a terminal: `anchor compare arize-phoenix hue`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/arize-phoenix.json and https://www.anchorterminal.com/api/v1/tools/hue.json

## Other comparisons with Arize Phoenix or Hue

- [Agent Tree vs Arize Phoenix](https://www.anchorterminal.com/compare/agent-tree-vs-arize-phoenix.md)
- [Agent Tree vs Hue](https://www.anchorterminal.com/compare/agent-tree-vs-hue.md)
- [agents-tree vs Arize Phoenix](https://www.anchorterminal.com/compare/agents-tree-vs-arize-phoenix.md)
- [agents-tree vs Hue](https://www.anchorterminal.com/compare/agents-tree-vs-hue.md)
- [Arize Phoenix vs Baserun](https://www.anchorterminal.com/compare/arize-phoenix-vs-baserun.md)
- [Arize Phoenix vs BotGauge](https://www.anchorterminal.com/compare/arize-phoenix-vs-botgauge.md)
- [Arize Phoenix vs Braintrust API + MCP](https://www.anchorterminal.com/compare/arize-phoenix-vs-braintrust.md)
- [Arize Phoenix vs DeepEval](https://www.anchorterminal.com/compare/arize-phoenix-vs-deepeval.md)
- [Arize Phoenix vs Galileo API + MCP](https://www.anchorterminal.com/compare/arize-phoenix-vs-galileo.md)
- [Arize Phoenix vs Helicone AI Gateway + MCP](https://www.anchorterminal.com/compare/arize-phoenix-vs-helicone.md)
- [Arize Phoenix vs HoneyHive](https://www.anchorterminal.com/compare/arize-phoenix-vs-honeyhive.md)
- [Arize Phoenix vs Laminar API + MCP](https://www.anchorterminal.com/compare/arize-phoenix-vs-laminar.md)
- [Arize Phoenix vs Langfuse API + MCP](https://www.anchorterminal.com/compare/arize-phoenix-vs-langfuse.md)
- [Arize Phoenix vs LangSmith API + MCP](https://www.anchorterminal.com/compare/arize-phoenix-vs-langsmith.md)
- [Arize Phoenix vs LangWatch](https://www.anchorterminal.com/compare/arize-phoenix-vs-langwatch.md)
- [Arize Phoenix vs MLflow Tracing](https://www.anchorterminal.com/compare/arize-phoenix-vs-mlflow-tracing.md)
- [Arize Phoenix vs Navige](https://www.anchorterminal.com/compare/arize-phoenix-vs-navige.md)
- [Arize Phoenix vs Opik API + MCP](https://www.anchorterminal.com/compare/arize-phoenix-vs-opik.md)
- [Arize Phoenix vs Overmind](https://www.anchorterminal.com/compare/arize-phoenix-vs-overmind.md)
- [Arize Phoenix vs Prefactor](https://www.anchorterminal.com/compare/arize-phoenix-vs-prefactor.md)
- [Arize Phoenix vs Pydantic Logfire](https://www.anchorterminal.com/compare/arize-phoenix-vs-pydantic-logfire.md)
- [Arize Phoenix vs Respan API + MCP](https://www.anchorterminal.com/compare/arize-phoenix-vs-respan.md)
- [Arize Phoenix vs W&B Weave](https://www.anchorterminal.com/compare/arize-phoenix-vs-wandb-weave.md)
- [Baserun vs Hue](https://www.anchorterminal.com/compare/baserun-vs-hue.md)
- [BotGauge vs Hue](https://www.anchorterminal.com/compare/botgauge-vs-hue.md)
- [Braintrust API + MCP vs Hue](https://www.anchorterminal.com/compare/braintrust-vs-hue.md)
- [Galileo API + MCP vs Hue](https://www.anchorterminal.com/compare/galileo-vs-hue.md)
- [Helicone AI Gateway + MCP vs Hue](https://www.anchorterminal.com/compare/helicone-vs-hue.md)
- [HoneyHive vs Hue](https://www.anchorterminal.com/compare/honeyhive-vs-hue.md)
- [Hue vs Laminar API + MCP](https://www.anchorterminal.com/compare/hue-vs-laminar.md)
- [Hue vs Langfuse API + MCP](https://www.anchorterminal.com/compare/hue-vs-langfuse.md)
- [Hue vs LangSmith API + MCP](https://www.anchorterminal.com/compare/hue-vs-langsmith.md)
- [Hue vs LangWatch](https://www.anchorterminal.com/compare/hue-vs-langwatch.md)
- [Hue vs MLflow Tracing](https://www.anchorterminal.com/compare/hue-vs-mlflow-tracing.md)
- [Hue vs Navige](https://www.anchorterminal.com/compare/hue-vs-navige.md)
- [Hue vs Opik API + MCP](https://www.anchorterminal.com/compare/hue-vs-opik.md)
- [Hue vs Overmind](https://www.anchorterminal.com/compare/hue-vs-overmind.md)
- [Hue vs Prefactor](https://www.anchorterminal.com/compare/hue-vs-prefactor.md)
- [Hue vs Pydantic Logfire](https://www.anchorterminal.com/compare/hue-vs-pydantic-logfire.md)
- [Hue vs Respan API + MCP](https://www.anchorterminal.com/compare/hue-vs-respan.md)
- [Hue vs W&B Weave](https://www.anchorterminal.com/compare/hue-vs-wandb-weave.md)
- [Arize Phoenix vs Gauge CLI](https://www.anchorterminal.com/compare/arize-phoenix-vs-gauge-cli.md)
- [Arize Phoenix vs Plurai Simulation](https://www.anchorterminal.com/compare/arize-phoenix-vs-plurai-simulation.md)
- [DeepEval vs Hue](https://www.anchorterminal.com/compare/deepeval-vs-hue.md)
- [Gauge CLI vs Hue](https://www.anchorterminal.com/compare/gauge-cli-vs-hue.md)
- [Hue vs Plurai Simulation](https://www.anchorterminal.com/compare/hue-vs-plurai-simulation.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp
