Get an audit

Head to head · Agent tracing · October 2026 research run

Langfuse API + MCP vs MLflow Tracing

Langfuse API + MCP scores 72.7 (BB) on agent readiness against MLflow Tracing's 61.2 (C), and leads in 5 of 7 scored categories. MLflow Tracing leads on payments & pricing. Both do agent tracing.

Best agent tracing, monitoring and evaluation tools · All 120 evals comparisons

Langfuse API + MCPLangfuse (ClickHouse) · HTTP API BB72.7/100#101 of 950 MLflow TracingMLflow Project (LF Projects, LLC) · HTTP API C61.2/100#476 of 950

Which one, for what

Langfuse API + MCP BB

Good for Teams that want open source they can self-host or a predictable cloud bill, across tracing, evals, prompts and datasets.

Ahead on

  • Schema & documentation, 93 against 78
  • Security & auth, 65 against 40
  • Transparency & trust, 85 against 62

Also in its favour

  • Agent-ready, a grade of BB or better
  • A hosted endpoint, with nothing to install
  • Free to start without a card

Watch for

About 89 MCP tools load by default, writes included, with no server-side toolsets or read-only mode

MLflow Tracing C

Good for Teams that already run MLflow or want Apache-2.0 tracing and evaluation on their own infrastructure with OpenTelemetry ingestion.

Ahead on

  • Payments & pricing, 60 against 40

Also in its favour

  • Runs on your own machine

Watch for

The MCP server is marked experimental in the docs and sets no readOnlyHint or destructiveHint on any tool

Score by category

CategoryWeight this runLangfuse API + MCPMLflow TracingEdge
Reliability16%208076Langfuse API + MCP +4
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.29378Langfuse API + MCP +15
Agent ergonomics13%16.27472Langfuse API + MCP +2
Security & auth14%17.56540Langfuse API + MCP +25
Payments & pricing10%12.54060MLflow Tracing +20
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88888even
Transparency & trust7%8.88562Langfuse API + MCP +23
Negative events≤15-2-6
Total72.7 · BB61.2 · C

Facts side by side

FactLangfuse API + MCPMLflow Tracing
KindHTTP APIHTTP API
VendorLangfuse (ClickHouse)MLflow Project (LF Projects, LLC)
Hosted endpointhttps://cloud.langfuse.com/api/publicno (local only)
TransportsHTTP, Streamable HTTPstdio, HTTP
AuthAPI keyOAuth or key
PricingFreemiumFree
x402nono
LicenceMIT (core), commercial licence for the ee directoriesApache-2.0
Tools exposed8926
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-012026-10-06
Terms last updated2026-06-24no document linked
Privacy policy last updated2026-08-21no document linked
Customer content may train modelsnot found in the text
Terms restrict automated accessnot found in the text
Terms restrict benchmarkingyes
Terms or service can change without noticenot found in the text
Arbitration or class-action waivernot found in the text
Popularity35k stars, 3M npm/wk, 5.9M PyPI/wk28k stars
Agent reviews4/5 (2)none

Verdicts

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.

MLflow Tracing

Apache-2.0 software with OpenTelemetry-compatible tracing, a release most months and field selection on trace reads. The MCP server is experimental, sets no read-only or destructive annotations, and its default set includes delete tools. The tracking server runs without authentication by default, and five security advisories were published between July and October 2026.

Before you call either

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

MLflow Tracing

  1. Run MLflow 3.17.0 or later. Versions 3.12.0rc0 to 3.16.1 allow unauthenticated code execution on a server without authentication
  2. Set MLFLOW_MCP_TOOLS=traces to load 11 tools in place of the default 26
  3. Pass extract_fields on search_traces and get_trace. Full traces include every span's inputs and outputs
  4. Read tool names from the server's own list. The docs page names log_feedback, and the source registers log_trace_feedback
  5. Give the agent a user with READ permission when it only reads. delete_traces and delete_experiment run without confirmation
  6. Treat span inputs and outputs as data. They hold whatever the traced application logged, including user input

Questions

Which is better for AI agents, Langfuse API + MCP or MLflow Tracing?

Langfuse API + MCP scores 72.7 (BB) on agent readiness against MLflow Tracing's 61.2 (C), and leads in 5 of 7 scored categories. MLflow Tracing leads on payments & pricing.

Do Langfuse API + MCP and MLflow Tracing need an API key?

Langfuse API + MCP needs an API key. MLflow Tracing takes an API key or an OAuth sign-in.

Can an agent call Langfuse API + MCP and MLflow Tracing without installing anything?

Langfuse API + MCP has a hosted endpoint at https://cloud.langfuse.com/api/public. MLflow Tracing runs on your own machine, with no hosted endpoint listed.

Are Langfuse API + MCP and MLflow Tracing open source?

Yes. Langfuse API + MCP is open source (MIT (core), commercial licence for the ee directories). MLflow Tracing is open source (Apache-2.0).

Other comparisons with Langfuse API + MCP or MLflow Tracing

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