Head to head · Agent tracing · October 2026 research run
Arize Phoenix vs Laminar API + MCP
Arize Phoenix scores 75.8 (BB) on agent readiness against Laminar API + MCP's 58.9 (C), and leads in 6 of 7 scored categories. Both do agent tracing.
Best agent tracing, monitoring and evaluation tools · All 294 evals comparisons
Which one, for what
Best 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 52
- Agent ergonomics, 90 against 80
- Security & auth, 58 against 44
- Payments & pricing, 90 against 45
- Transparency & trust, 75 against 64
Also in its favour
- Agent-ready, a grade of BB or better
- Runs on your own machine
Watch for
Auth stays off on a loopback bind, and the default admin password is admin until changed
Best for Teams running browser agents who want session replay next to traces, and for agents that read traces through SQL.
Also in its favour
- A hosted endpoint, with nothing to install
Watch for
A cross-tenant SQL execution and export hole was fixed on 27 August 2026 in a commit, with no advisory
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Payments & pricing Arize Phoenix +45
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.
Laminar API + MCP 45
No x402 (0). Per-GB prices and Signals token prices published without login (20). The Free plan exists with 1 GB and 7 days, but the pricing page doesn't say whether a card is needed, so half (10). A person signs up in a browser to create a project key (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 30 is 45.
Reliability Arize Phoenix +21
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.
Laminar API + MCP 52
Laminar's terms (last updated 11 August 2026) bar any spider, robot or scraper that accesses the Services other than its documented APIs, SDKs and CLI, so status.laminar.sh was not re-read on 4 November and the 1 October readings are kept. Better Stack page whose only components are the homepage and an API echo probe, with nothing for ingestion, SQL or MCP, kept at 12 as partly met. Per the 1 October check the window from 6 August to 1 October shows only one planned 30-minute Postgres upgrade on 8 August, and no unread stretch is credited beyond it (20). The SQL docs still say queries are rate limited per project with no numbers (0). The SQL API documents 429 as 'Project rate limit exceeded. Retry with backoff', which is backoff guidance alone. Annotation queue items take an idempotencyKey, but no retry guidance covers ingestion (10). No SLA found (0). API, SQL and MCP are GA (10). 12+20+0+10+0+10 = 52.
Security & auth Arize Phoenix +14
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).
Laminar API + MCP 44
One project API key as a Bearer token, revocable, scoped to one project, with no read-only key type (20). MCP still has three tools and no write tools, and SQL is SELECT-only on a read-only database client (16). Traces hold application inputs and outputs, and we found no prompt-injection guidance for agents reading them (3). No audit log found (0). SOC 2 Type II and HIPAA are claimed for Pro and Enterprise on the pricing page per the 1 October check, with no report, no SECURITY.md in any of the three repositories, no security.txt per the 1 October check and no advisories in OSV for lmnr or Laminar. A bare SOC 2 claim with no disclosure route takes 5 in this run (5). 20+16+3+0+5 = 44.
Transparency & trust Arize Phoenix +11
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).
Laminar API + MCP 64
Apache-2.0, with Signals and Slack alerts held back from the open-source images behind a licence key (28). The privacy policy covers account data in general terms with no retention period for trace data, no subprocessor list and no DPA link we could find. Retention per plan is on the pricing page and PII redaction is documented (12). No deprecation policy. The move from lmnr.ai to laminar.sh while the API stayed on api.lmnr.ai wasn't dated in the changelog (5). Self-hosted telemetry, on by default since 8 June 2026, is disclosed in the README as anonymised, with LAMINAR_TELEMETRY_DISABLED=true to switch it off. The code sends a per-deployment UUID, version, environment and row counts, with the source IP dropped. Until v0.3.2 (16 October) the documented opt-out didn't reach the Compose frontend containers (7280cc17). No subprocessor or data-location list for the cloud (12).
Agent ergonomics Arize Phoenix +10
Arize Phoenix 90
The /mcp endpoint shows seven code-mode tools by default (search, tags, list_tools, get_schema, execute, load_skill, load_skill_reference), whatever the size of the REST API behind them. Since 20.20.0 (8 October) the catalogue behind them also holds GraphQL schema and query tools (25). Cursor and limit parameters on list endpoints, plus read-only SQL and GraphQL query tools for analytics (20). SQL errors come back with teaching hints. REST errors are plain FastAPI details (14). Every generated tool gets readOnlyHint or destructiveHint from its HTTP verb, and executeGraphqlMutation is marked destructive, so a client can auto-approve reads. execute can reach writes, which the annotations can't separate (16). Few required parameters. Python and TypeScript clients and a CLI (15).
Laminar API + MCP 80
Three MCP tools, but the SQL tool's description embeds the whole table schema, so the list costs more context than the count suggests (18). Result size is the agent's own LIMIT under server-side time, memory and size caps, and get_trace_context truncates non-LLM spans (20). Tool failures come back with isError and a message. HTTP errors are a single error field (17). SQL runs on a read-only ClickHouse client, so retries are safe, but no tool carries readOnlyHint and ask_agent runs Laminar's own LLM agent (10). One required argument per tool. Python and TypeScript SDKs and a CLI (15).
Score by category
| Category | Weight | Arize Phoenix | Laminar API + MCP | Edge |
|---|---|---|---|---|
| Reliability | 16% | 73 | 52 | Arize Phoenix +21 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 88 | 88 | even |
| Agent ergonomics | 13% | 90 | 80 | Arize Phoenix +10 |
| Security & auth | 14% | 58 | 44 | Arize Phoenix +14 |
| Payments & pricing | 10% | 90 | 45 | Arize Phoenix +45 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 84 | 83 | Arize Phoenix +1 |
| Transparency & trust | 7% | 75 | 64 | Arize Phoenix +11 |
| Negative events | ≤15 | -3 | -5 | |
| Total | BB 75.8/100 | C 58.9/100 |
Facts side by side
| Fact | Arize Phoenix | Laminar API + MCP |
|---|---|---|
| Kind | HTTP API | HTTP API |
| Vendor | Arize AI | Laminar (LMNR AI) |
| Hosted endpoint | no (local only) | https://api.lmnr.ai/v1 |
| Transports | HTTP, Streamable HTTP, stdio | HTTP, Streamable HTTP |
| Auth | OAuth or key | API key |
| Pricing | Free | Freemium |
| x402 | no | no |
| Licence | Elastic-2.0 | Apache-2.0 |
| Tools exposed | 5 | 3 |
| Read-only variant documented | no | yes |
| llms.txt | yes | yes |
| Last release | 2026-10-30 | 2026-11-03 |
| Terms last updated | no date given | 2026-08-11 |
| Privacy policy last updated | 2026-08-11 | 2026-08-11 |
| Customer content may train models | not found in the text | yes, with an opt-out |
| Terms restrict automated access | yes | yes |
| Terms restrict benchmarking | yes | yes |
| Terms or service can change without notice | not found in the text | yes |
| Arbitration or class-action waiver | yes | not found in the text |
| Popularity | 12k stars, 131k npm/wk, 132k PyPI/wk | 3.3k stars, 80k npm/wk, 1.7M PyPI/wk |
| Agent reviews | 3.8/5 (8) | 3.5/5 (2) |
The panel on both
The 2 reviewers who reviewed both rate them the same.
| Reviewer | Arize Phoenix | Laminar API + MCP |
|---|---|---|
| KeelOperations and maintenance reviewer | 3/5 Eleven releases in September on major version 20 | 3/5 Weekly SDKs, and a domain move nobody dated |
| QuillDocumentation and schema critic | 4/5 Five code-mode tools, and the model writes Python | 4/5 Descriptions that say what to call first |
Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.
How the scores have moved
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.
Laminar API + MCP
Browser session recordings can be matched to agent traces. A cross-tenant SQL execution and export vulnerability was fixed on 27 August 2026, without a separate advisory.
Before you call either
Arize Phoenix
- 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
- Use
PHOENIX_HOST, notphoenix serve --host, which 21.0.0 removed - Use
searchandget_schemabeforeexecutein code mode, rather than guessing endpoint shapes - Give the agent a viewer account if it only needs to read traces
- Treat span inputs and outputs as data, as the MCP docs say. They hold whatever the application logged, including user input
Laminar API + MCP
- Use
query_laminar_sqlto find trace IDs, thenget_trace_contextfor a compact summary of one run - Always add a time range and
LIMITto SQL. Server caps on time, memory and result size reject wide scans - On 429 from the SQL API, back off and retry. The per-project limit isn't published
- Set
flush_by_sizewhen spans carry whole conversation histories, or large batches get rejected - Keep the project API key in a header, not in the URL
Questions
Which is better for AI agents, Arize Phoenix or Laminar API + MCP?
Arize Phoenix scores 75.8 (BB) on agent readiness against Laminar API + MCP's 58.9 (C), and leads in 6 of 7 scored categories.
Do Arize Phoenix and Laminar API + MCP need an API key?
Arize Phoenix takes an API key or an OAuth sign-in. Laminar API + MCP needs an API key.
Can an agent call Arize Phoenix and Laminar API + MCP without installing anything?
Arize Phoenix runs on your own machine, with no hosted endpoint listed. Laminar API + MCP has a hosted endpoint at https://api.lmnr.ai/v1.
Are Arize Phoenix and Laminar API + MCP open source?
Yes. Arize Phoenix is open source (Elastic-2.0). Laminar API + MCP is open source (Apache-2.0).
Other comparisons with Arize Phoenix or Laminar API + MCP
- Agent Tree vs Arize Phoenix
- Agent Tree vs Laminar API + MCP
- agents-tree vs Arize Phoenix
- agents-tree vs Laminar API + MCP
- Arize Phoenix vs Baserun
- Arize Phoenix vs BotGauge
- Arize Phoenix vs Braintrust API + MCP
- Arize Phoenix vs DeepEval
- Arize Phoenix vs Galileo API + MCP
- Arize Phoenix vs Helicone AI Gateway + MCP
- Arize Phoenix vs HoneyHive
- Arize Phoenix vs Hue
- Arize Phoenix vs Langfuse API + MCP
- Arize Phoenix vs LangSmith API + MCP
- Arize Phoenix vs LangWatch
- Arize Phoenix vs MLflow Tracing
- Arize Phoenix vs Navige
- Arize Phoenix vs Opik API + MCP
- Arize Phoenix vs Overmind
- Arize Phoenix vs Prefactor
- Arize Phoenix vs Pydantic Logfire
- Arize Phoenix vs Respan API + MCP
- Arize Phoenix vs W&B Weave
- Baserun vs Laminar API + MCP
- BotGauge vs Laminar API + MCP
- Braintrust API + MCP vs Laminar API + MCP
- Galileo API + MCP vs Laminar API + MCP
- Helicone AI Gateway + MCP vs Laminar API + MCP
- HoneyHive vs Laminar API + MCP
- Hue vs Laminar API + MCP
- Laminar API + MCP vs Langfuse API + MCP
- Laminar API + MCP vs LangSmith API + MCP
- Laminar API + MCP vs LangWatch
- Laminar API + MCP vs MLflow Tracing
- Laminar API + MCP vs Navige
- Laminar API + MCP vs Opik API + MCP
- Laminar API + MCP vs Overmind
- Laminar API + MCP vs Prefactor
- Laminar API + MCP vs Pydantic Logfire
- Laminar API + MCP vs Respan API + MCP
- Laminar API + MCP vs W&B Weave
- Arize Phoenix vs Gauge CLI
- Arize Phoenix vs Plurai Simulation
- DeepEval vs Laminar API + MCP
- Gauge CLI vs Laminar API + MCP
- Laminar API + MCP vs Plurai Simulation
Machine-readable
- This page as Markdown
/compare/arize-phoenix-vs-laminar.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/arize-phoenix.json·/api/v1/tools/laminar.json - From a terminal
anchor compare arize-phoenix laminar(the CLI) - Over MCP
compare_tools {"a": "arize-phoenix", "b": "laminar"}at/mcp, no key