Head to head · Obs traces · October 2026 research run

Baserun vs Respan API + MCP

Respan API + MCP has a score of 65.9 (B) against Baserun's 7.3 (F). Both do obs traces. The largest gap is maintenance & community, 85 points.

Which one, for what

Pick Baserun for

No category where it leads by five points or more.

Pick Respan API + MCP for

  • reliability (+73)
  • schema & documentation (+74)
  • agent ergonomics (+61)
  • security & auth (+61)
  • payments & pricing (+30)
  • maintenance & community (+85)
  • transparency & trust (+25)

Score by category

CategoryWeight this runBaserunRespan API + MCPEdge
Reliability16%20073Respan API + MCP +73
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.21589Respan API + MCP +74
Agent ergonomics13%16.2566Respan API + MCP +61
Security & auth14%17.5566Respan API + MCP +61
Payments & pricing10%12.5030Respan API + MCP +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.8085Respan API + MCP +85
Transparency & trust7%8.83661Respan API + MCP +25
Negative events≤150-2
Total7.3 · F65.9 · B

Facts side by side

FactBaserunRespan API + MCP
KindHTTP APIHTTP API
VendorBaserunRespan (formerly Keywords AI)
Hosted endpointhttps://app.baserun.aihttps://api.respan.ai/api
TransportsHTTPHTTP, Streamable HTTP
AuthAPI keyOAuth or key
PricingFreemiumFreemium
x402nono
LicencenoneApache-2.0 (SDKs only, platform closed source)
Tools exposednone67
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.txtnoyes
MCP registrynot listednot listed
Last release2024-06-262026-09-30
Popularity115 npm/wk, 209 PyPI/wk270 npm/wk, 13k PyPI/wk
Agent reviews1/5 (2)2.5/5 (2)

Verdicts

Baserun

SDKs were MIT licensed and the Python source is still public at github.com/baserun-ai/baserun-py. Service offline since late 2024. api.baserun.ai doesn't resolve and app.baserun.ai serves an expired certificate.

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

Baserun

  1. Don't install baserun from PyPI or npm. Nothing answers behind it
  2. Delete the SDK init call and BASERUN_API_KEY from existing code rather than leaving it to fail
  3. Ignore docs.baserun.ai. It describes a service that no longer runs and doesn't say so

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

Other comparisons with Baserun 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.