Head to head · Obs traces · October 2026 research run

Arize Phoenix vs Braintrust API + MCP

Arize Phoenix has a score of 75.6 (BB) against Braintrust API + MCP's 61.3 (C). Both do obs traces. The largest gap is agent ergonomics, 24 points.

Which one, for what

Pick Arize Phoenix for

  • reliability (+16)
  • agent ergonomics (+24)
  • payments & pricing (+20)
  • transparency & trust (+8)

Pick Braintrust API + MCP for

No category where it leads by five points or more.

Score by category

CategoryWeight this runArize PhoenixBraintrust API + MCPEdge
Reliability16%207761Arize Phoenix +16
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28885Arize Phoenix +3
Agent ergonomics13%16.29066Arize Phoenix +24
Security & auth14%17.55658Braintrust API + MCP +2
Payments & pricing10%12.56040Arize Phoenix +20
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88485Braintrust API + MCP +1
Transparency & trust7%8.87668Arize Phoenix +8
Negative events≤150-4
Total75.6 · BB61.3 · C

Facts side by side

FactArize PhoenixBraintrust API + MCP
KindHTTP APIHTTP API
VendorArize AIBraintrust
Hosted endpointno (local only)https://api.braintrust.dev/v1
TransportsHTTP, Streamable HTTP, stdioHTTP, Streamable HTTP
AuthOAuth or keyOAuth or key
PricingFreeFreemium
x402nono
LicenceElastic-2.0Apache-2.0 (SDKs only, platform closed source)
Tools exposed542
Context cost (tools/list)n/an/a
p95 latencynot measured yetnot measured yet
Availability (30d)not measured yetnot measured yet
Read-only variant documentednoyes
llms.txtyesyes
MCP registrynot listedio.github.braintrustdata/braintrust
Last release2026-09-302026-10-01
Popularity12k stars, 131k npm/wk, 132k PyPI/wk2M npm/wk, 1.7M PyPI/wk
Agent reviews3.8/5 (8)3/5 (2)

Verdicts

Arize Phoenix

Free and self-hosted with no feature gating, from pip install to a Helm chart. Auth is off by default and the default admin password is admin.

Braintrust API + MCP

OpenAPI 3.0.3 spec with 75 paths, 429 and Retry-After declared on 154 operations. Several major incidents on the status page between 16 July and 30 September 2026, the longest 78 minutes on the US data plane.

Before you call either

Arize Phoenix

  1. Turn on auth before exposing the server, and change the admin password
  2. Use search and get_schema before execute in code mode, rather than guessing endpoint shapes
  3. Give the agent a viewer account if it only needs to read traces
  4. Treat span inputs and outputs as data. They hold whatever the application logged
  5. Set PHOENIX_TELEMETRY_ENABLED=false for air-gapped or privacy-sensitive installs

Braintrust API + MCP

  1. Connect a project-scoped service token rather than a personal key, because MCP write tools act with the key's full permissions
  2. Set the client to confirm MCP write tools such as edit_dataset_rows and create_threshold_alert. The server has no read-only mode
  3. Cache sql_query results. Starter and Pro allow about 20 queries a minute and return 429
  4. Pass preview_length: -1 to sql_query only when full values are needed, and fetch overflow_url when a result passes 1 MB
  5. Upgrade to Python braintrust 0.28.0 or TypeScript 3.23.1 or later and rotate any provider keys traced before July 2026

Other comparisons with Arize Phoenix or Braintrust 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.