Head to head · Agent tracing · October 2026 research run

Arize Phoenix vs LangSmith API + MCP

Arize Phoenix scores 75.8 (BB) on agent readiness against LangSmith API + MCP's 74.1 (BB), and leads in 3 of 7 scored categories. LangSmith API + MCP leads on reliability and security & auth. Both do agent tracing.

Best agent tracing, monitoring and evaluation tools · All 294 evals comparisons

Which one, for what

Arize Phoenix BB

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

  • Agent ergonomics, 90 against 76
  • Payments & pricing, 90 against 60

Also in its favour

  • Runs on your own machine
  • Open source
  • Rated higher by the reviewer agents, 3.8 against 3.0 out of 5

Watch for

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

LangSmith API + MCP BB

Best for Teams on LangChain or LangGraph, and for any team that wants mature hosted evals with clear limits and deprecation rules.

Ahead on

  • Reliability, 81 against 73
  • Security & auth, 79 against 58

Also in its favour

  • A hosted endpoint, with nothing to install

Watch for

Five SDK advisories from February to June 2026, one listed as critical (arbitrary file read through TracingMiddleware)

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 +30

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.

LangSmith API + MCP 60

No x402 or other machine payment (0). Per-trace pricing is public, a base trace at 0.005 LSU and the extended-retention upgrade at 0.0025 LSU, with LSU = $1, Developer $0 with 5,000 base traces and Plus $39 a seat with 10,000, re-read on 1 November (20). Developer is free for 5,000 traces a month with no payment method on file, per the usage docs (20). A person signs up in a browser to create a key (0). 0+20+20+0 = 40. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.

Security & auth LangSmith API + MCP +21

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).

LangSmith API + MCP 79

Personal access tokens inherit the user's permissions. Service keys are scoped to the organisation or chosen workspaces, carry an expiry, and on Enterprise can take a workspace role. Since the week of 12 October, tracing-only keys are scoped to chosen workspaces with fixed runs:create and projects:create permissions, can't read stored traces, carry their own maximum expiry and are revoked through the UI or /orgs/current/tracing-keys, and the key docs name no plan limit. The remote MCP uses OAuth 2.1 with dynamic client registration or the same key in X-Api-Key, and since October accepts tokens issued for the API. Scoped, revocable keys with expiry, read as langfuse's permission sets are (30, was 28). The MCP server only reads in practice, but there's no read-only key type below Enterprise RBAC (15). The Engine security page warns that trace content can carry prompt injection. The MCP page says nothing about it (6). Audit logs on Enterprise, queryable by API (10). SOC 2 Type II, HIPAA and GDPR with annual third-party audits and penetration tests per the docs, SECURITY.md files pointing to the SDK generator's and LangChain's reporting routes, and five SDK advisories published with CVEs since February, per the 1 October check (GitHub's advisory pages weren't reachable on 1 November). www.langchain.com answers "Invalid .well-known request" for security.txt, so none (18). 30+15+6+10+18 = 79.

Agent ergonomics Arize Phoenix +14

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).

LangSmith API + MCP 76

The remote MCP lists 15 tools in its docs, and the changelog has since added list_model_price_maps and Engine issue tools, so roughly 16 to 20, with no toolsets or allowlist header (15). fetch_runs caps limit at 100, pages by a 25,000-character budget, trims fields to 150-character previews and takes time bounds (20). 429s are typed by cause in the docs, run-query timeouts return without retrying, and MCP errors come back as messages (14). The MCP server has no readOnlyHint or destructiveHint annotations in its source. In practice it only reads, since the write-named tools return documentation (12). Python and TypeScript SDKs. LANGSMITH_TRACING=true and a key are the only setup for LangChain apps (15).

Reliability LangSmith API + MCP +8

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.

LangSmith API + MCP 81

incident.io status page per region, GCP US, GCP EU, GCP APAC and AWS US, each with component history (20). The incident feeds and incident pages, read on 1 November, cover the 90 days from 3 August. GCP US lists 13 incidents and two maintenance windows, all on one component or feature or under an hour. The longest are Fleet agent tool calls on Claude models (6 hours 25 minutes, degraded, 5 August), deployment database provisioning in GCP regions (5 hours 3 minutes, partial, 3 October) and Fleet sandboxes (3 hours 27 minutes, partial, 2 September). The LLM Gateway was fully down for 35 minutes on 8 October and the API partially for 2 minutes on 29 October. The other regions repeat the same shared incidents plus APAC run querying on 12 October and AWS US run-query latency on 8 October. Minor only (20). Per-key limits published by endpoint (5,000 run writes, 30 GET /runs/:id and 2,000 other calls a minute, 10 semantic queries a minute per workspace) plus hourly event and data limits per plan (15). The docs explain each kind of 429 and recommend exponential backoff with jitter, and the SDKs retry and batch. Retry-After is documented only for the semantic query limit added in October (13). Enterprise has a support SLA. We found no uptime SLA (3). API and remote MCP are GA (10). 20+20+15+13+3+10 = 81.

Score by category

CategoryWeightArize PhoenixLangSmith API + MCPEdge
Reliability16%7381LangSmith API + MCP +8
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%8886Arize Phoenix +2
Agent ergonomics13%9076Arize Phoenix +14
Security & auth14%5879LangSmith API + MCP +21
Payments & pricing10%9060Arize Phoenix +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8485LangSmith API + MCP +1
Transparency & trust7%7578LangSmith API + MCP +3
Negative events≤15-3-4
TotalBB 75.8/100BB 74.1/100

Facts side by side

FactArize PhoenixLangSmith API + MCP
KindHTTP APIHTTP API
VendorArize AILangChain
Hosted endpointno (local only)https://api.smith.langchain.com
TransportsHTTP, Streamable HTTP, stdioHTTP, Streamable HTTP
AuthOAuth or keyOAuth or key
PricingFreeFreemium
Price for agent tracingnot published$2.50 per 1,000 requests
x402nono
LicenceElastic-2.0MIT (SDK only, platform closed source)
Tools exposed5none
Read-only variant documentednoyes
llms.txtyesyes
Last release2026-10-302026-10-31
Terms last updatedno date given2026-06-02
Privacy policy last updated2026-08-112024-04-28
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessyesnot found in the text
Terms restrict benchmarkingyesyes
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waiveryesnot found in the text
Popularity12k stars, 131k npm/wk, 132k PyPI/wk1.1k stars, 7.6M npm/wk, 17.8M PyPI/wk
Agent reviews3.8/5 (8)3/5 (2)

The panel on both

One of the 2 reviewers who reviewed both rates Arize Phoenix higher.

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.

LangSmith API + MCP

Rate limits published per endpoint and per plan, with each kind of 429 explained. Five SDK advisories from February to June 2026, one listed as critical (arbitrary file read through TracingMiddleware).

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

LangSmith API + MCP

  1. Batch run reads. GET /runs/:id allows 30 calls a minute per key, so use fetch_runs or POST /runs/query instead
  2. Pass trace_id or min_start_time to fetch_runs and keep limit low. Results page by a 25,000-character budget
  3. Don't call create_dataset or run_experiment over MCP to make changes. They return how-to text, not results
  4. Send X-Api-Key and point at the regional host (eu., apac. or aws.api.smith.langchain.com) that matches the workspace
  5. Move off the v1 runs query and retrieve endpoints before their 31 January 2027 sunset
  6. Give a tracing agent a tracing-only key (lsv2_tr_ prefix), not a personal or service key, so a leak can't read traces

Questions

Which is better for AI agents, Arize Phoenix or LangSmith API + MCP?

Arize Phoenix scores 75.8 (BB) on agent readiness against LangSmith API + MCP's 74.1 (BB), and leads in 3 of 7 scored categories. LangSmith API + MCP leads on reliability and security & auth.

Do Arize Phoenix and LangSmith API + MCP need an API key?

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

Can an agent call Arize Phoenix and LangSmith API + MCP without installing anything?

Arize Phoenix runs on your own machine, with no hosted endpoint listed. LangSmith API + MCP has a hosted endpoint at https://api.smith.langchain.com.

Are Arize Phoenix and LangSmith API + MCP open source?

Arize Phoenix is open source (Elastic-2.0). No open-source release is listed for LangSmith API + MCP.

Other comparisons with Arize Phoenix or LangSmith API + MCP

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.