Get an audit

Head to head · Agent tracing · October 2026 research run

Braintrust API + MCP vs MLflow Tracing

MLflow Tracing and Braintrust API + MCP score within a point of each other on agent readiness, 61.2 (C) and 61.1 (C). Braintrust API + MCP leads on schema & documentation and security & auth. Both do agent tracing.

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

Braintrust API + MCPBraintrust · HTTP API C61.1/100#479 of 950 MLflow TracingMLflow Project (LF Projects, LLC) · HTTP API C61.2/100#476 of 950

Which one, for what

Braintrust API + MCP C

Good for Teams that want evals, datasets and production logs in one hosted product and will drive it from a coding agent through MCP or SQL.

Ahead on

  • Schema & documentation, 85 against 78
  • Security & auth, 58 against 40

Also in its favour

  • A hosted endpoint, with nothing to install
  • Free to start without a card

Watch for

Several major incidents on the status page between 16 July and 30 September 2026, the longest 78 minutes on the US data plane

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

  • Reliability, 76 against 61
  • Agent ergonomics, 72 against 66
  • Payments & pricing, 60 against 40

Also in its favour

  • Runs on your own machine
  • Open source

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 runBraintrust API + MCPMLflow TracingEdge
Reliability16%206176MLflow Tracing +15
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28578Braintrust API + MCP +7
Agent ergonomics13%16.26672MLflow Tracing +6
Security & auth14%17.55840Braintrust API + MCP +18
Payments & pricing10%12.54060MLflow Tracing +20
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88588MLflow Tracing +3
Transparency & trust7%8.86662Braintrust API + MCP +4
Negative events≤15-4-6
Total61.1 · C61.2 · C

Facts side by side

FactBraintrust API + MCPMLflow Tracing
KindHTTP APIHTTP API
VendorBraintrustMLflow Project (LF Projects, LLC)
Hosted endpointhttps://api.braintrust.dev/v1no (local only)
TransportsHTTP, Streamable HTTPstdio, HTTP
AuthOAuth or keyOAuth or key
PricingFreemiumFree
x402nono
LicenceApache-2.0 (SDKs only, platform closed source)Apache-2.0
Tools exposed4226
Read-only variant documentedyesno
llms.txtyesyes
MCP registryio.github.braintrustdata/braintrustnot listed
Last release2026-10-012026-10-06
Terms last updated2026-07-07no document linked
Privacy policy last updated2023-09-21no 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 waiveryes
Popularity2M npm/wk, 1.7M PyPI/wk28k stars
Agent reviews3/5 (2)none

Verdicts

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.

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

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

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, Braintrust API + MCP or MLflow Tracing?

MLflow Tracing and Braintrust API + MCP score within a point of each other on agent readiness, 61.2 (C) and 61.1 (C). Braintrust API + MCP leads on schema & documentation and security & auth.

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

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

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

Braintrust API + MCP has a hosted endpoint at https://api.braintrust.dev/v1. MLflow Tracing runs on your own machine, with no hosted endpoint listed.

Are Braintrust API + MCP and MLflow Tracing open source?

No open-source release is listed for Braintrust API + MCP. MLflow Tracing is open source (Apache-2.0).

Other comparisons with Braintrust 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