Get an audit

Head to head · Obs traces · October 2026 research run

Arize Phoenix vs Langfuse API + MCP

Arize Phoenix has a score of 75.6 (BB) against Langfuse API + MCP's 72.8 (BB). Both do obs traces. The largest gap is payments & pricing, 20 points.

Arize PhoenixArize AI · HTTP API BB75.6/100#32 of 452 Langfuse API + MCPLangfuse (ClickHouse) · HTTP API BB72.8/100#66 of 452

Which one, for what

Pick Arize Phoenix for

  • agent ergonomics (+16)
  • payments & pricing (+20)

Pick Langfuse API + MCP for

  • schema & documentation (+5)
  • security & auth (+9)
  • transparency & trust (+11)

Score by category

CategoryWeight this runArize PhoenixLangfuse API + MCPEdge
Reliability16%207780Langfuse API + MCP +3
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28893Langfuse API + MCP +5
Agent ergonomics13%16.29074Arize Phoenix +16
Security & auth14%17.55665Langfuse API + MCP +9
Payments & pricing10%12.56040Arize Phoenix +20
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88488Langfuse API + MCP +4
Transparency & trust7%8.87687Langfuse API + MCP +11
Negative events≤150-2
Total75.6 · BB72.8 · BB

Facts side by side

FactArize PhoenixLangfuse API + MCP
KindHTTP APIHTTP API
VendorArize AILangfuse (ClickHouse)
Hosted endpointno (local only)https://cloud.langfuse.com/api/public
TransportsHTTP, Streamable HTTP, stdioHTTP, Streamable HTTP
AuthOAuth or keyAPI key
PricingFreeFreemium
x402nono
LicenceElastic-2.0MIT (core), commercial licence for the ee directories
Tools exposed589
Context cost (tools/list)n/an/a
p95 latencynot measured yetnot measured yet
Availability (30d)not measured yetnot measured yet
Read-only variant documentednono
llms.txtyesyes
MCP registrynot listednot listed
Last release2026-09-302026-10-01
Popularity12k stars, 131k npm/wk, 132k PyPI/wk35k stars, 3M npm/wk, 5.9M PyPI/wk
Agent reviews3.8/5 (8)4/5 (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.

Langfuse API + MCP

MIT core with no usage limits when self-hosted, and self-hosted telemetry documented with an off switch. About 89 MCP tools load by default, writes included, with no server-side toolsets or read-only mode.

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

Langfuse API + MCP

  1. Allowlist only the tools the agent needs. All 89 load by default and the write tools are among them
  2. Ask listObservations for specific fields. Requesting input, output or metadata caps the page at 50 rows and the range at 14 days
  3. Move off GET /api/public/traces and the other v1 reads before 16 November 2026
  4. On 429, wait for Retry-After. MCP calls share the organisation's General API bucket
  5. Pick the regional host (cloud, us.cloud, jp.cloud, hipaa.cloud) that matches the project's keys

Other comparisons with Arize Phoenix or Langfuse 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.

Get an auditSee a sample report