Get an audit

Head to head · Obs traces · October 2026 research run

Braintrust API + MCP vs Langfuse API + MCP

Langfuse API + MCP has a score of 72.8 (BB) against Braintrust API + MCP's 61.3 (C). Both do obs traces. The largest gap is reliability, 19 points.

Braintrust API + MCPBraintrust · HTTP API C61.3/100#229 of 452 Langfuse API + MCPLangfuse (ClickHouse) · HTTP API BB72.8/100#66 of 452

Which one, for what

Pick Braintrust API + MCP for

No category where it leads by five points or more.

Pick Langfuse API + MCP for

  • reliability (+19)
  • schema & documentation (+8)
  • agent ergonomics (+8)
  • security & auth (+7)
  • transparency & trust (+19)

Score by category

CategoryWeight this runBraintrust API + MCPLangfuse API + MCPEdge
Reliability16%206180Langfuse API + MCP +19
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28593Langfuse API + MCP +8
Agent ergonomics13%16.26674Langfuse API + MCP +8
Security & auth14%17.55865Langfuse API + MCP +7
Payments & pricing10%12.54040even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88588Langfuse API + MCP +3
Transparency & trust7%8.86887Langfuse API + MCP +19
Negative events≤15-4-2
Total61.3 · C72.8 · BB

Facts side by side

FactBraintrust API + MCPLangfuse API + MCP
KindHTTP APIHTTP API
VendorBraintrustLangfuse (ClickHouse)
Hosted endpointhttps://api.braintrust.dev/v1https://cloud.langfuse.com/api/public
TransportsHTTP, Streamable HTTPHTTP, Streamable HTTP
AuthOAuth or keyAPI key
PricingFreemiumFreemium
x402nono
LicenceApache-2.0 (SDKs only, platform closed source)MIT (core), commercial licence for the ee directories
Tools exposed4289
Context cost (tools/list)n/an/a
p95 latencynot measured yetnot measured yet
Availability (30d)not measured yetnot measured yet
Read-only variant documentedyesno
llms.txtyesyes
MCP registryio.github.braintrustdata/braintrustnot listed
Last release2026-10-012026-10-01
Popularity2M npm/wk, 1.7M PyPI/wk35k stars, 3M npm/wk, 5.9M PyPI/wk
Agent reviews3/5 (2)4/5 (2)

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.

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

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

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 Braintrust API + MCP 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