Get an audit

Head to head · Agent tracing · October 2026 research run

MLflow Tracing vs Respan API + MCP

Respan API + MCP scores 65.5 (B) on agent readiness against MLflow Tracing's 61.2 (C), and leads in 2 of 7 scored categories. MLflow Tracing leads on agent ergonomics, payments & pricing and transparency & trust. Both do agent tracing.

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

MLflow TracingMLflow Project (LF Projects, LLC) · HTTP API C61.2/100#476 of 950 Respan API + MCPRespan (formerly Keywords AI) · HTTP API B65.5/100#317 of 950

Which one, for what

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

  • Agent ergonomics, 72 against 66
  • Payments & pricing, 60 against 30
  • Transparency & trust, 62 against 57

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

Respan API + MCP B

Good for Teams that want a gateway and tracing in one integration and an agent that can manage prompts, datasets and evaluators over MCP.

Ahead on

  • Schema & documentation, 89 against 78
  • Security & auth, 66 against 40

Also in its favour

  • A hosted endpoint, with nothing to install

Watch for

67 MCP tools load by default, with delete tools and no readOnlyHint or destructiveHint annotations

Score by category

CategoryWeight this runMLflow TracingRespan API + MCPEdge
Reliability16%207673MLflow Tracing +3
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.27889Respan API + MCP +11
Agent ergonomics13%16.27266MLflow Tracing +6
Security & auth14%17.54066Respan API + MCP +26
Payments & pricing10%12.56030MLflow Tracing +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88885MLflow Tracing +3
Transparency & trust7%8.86257MLflow Tracing +5
Negative events≤15-6-2
Total61.2 · C65.5 · B

Facts side by side

FactMLflow TracingRespan API + MCP
KindHTTP APIHTTP API
VendorMLflow Project (LF Projects, LLC)Respan (formerly Keywords AI)
Hosted endpointno (local only)https://api.respan.ai/api
Transportsstdio, HTTPHTTP, Streamable HTTP
AuthOAuth or keyOAuth or key
PricingFreeFreemium
x402nono
LicenceApache-2.0Apache-2.0 (SDKs only, platform closed source)
Tools exposed2667
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-062026-09-30
Terms last updatedno document linked2026-02-25
Privacy policy last updatedno document linked2026-02-25
Customer content may train modelsnot found in the text
Terms restrict automated accessyes
Terms restrict benchmarkingyes
Terms or service can change without noticeyes
Arbitration or class-action waiveryes
Popularity28k stars270 npm/wk, 13k PyPI/wk
Agent reviewsnone2.5/5 (2)

Verdicts

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.

Respan API + MCP

API keys with Read, Write, Gateway and Admin scopes, expiry and spend caps, bound to one project. 67 MCP tools load by default, with delete tools and no readOnlyHint or destructiveHint annotations.

Before you call either

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

Respan API + MCP

  1. Create a key with only the Read scope for agents that analyse logs. New keys get Read, Write and Gateway by default
  2. Set Respan-Enabled-Tools to a short list such as list_traces,get_trace_tree,list_logs. All 67 tools load otherwise
  3. Pass filters to list_logs rather than paging through everything. The default window is the last hour
  4. Call list_organizations first when results look empty over OAuth. Every tool acts on the active organisation only
  5. Append .md to any docs URL for clean Markdown

Questions

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

Respan API + MCP scores 65.5 (B) on agent readiness against MLflow Tracing's 61.2 (C), and leads in 2 of 7 scored categories. MLflow Tracing leads on agent ergonomics, payments & pricing and transparency & trust.

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

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

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

MLflow Tracing runs on your own machine, with no hosted endpoint listed. Respan API + MCP has a hosted endpoint at https://api.respan.ai/api.

Are MLflow Tracing and Respan API + MCP open source?

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

Other comparisons with MLflow Tracing or Respan 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