Get an audit

Head to head · Obs traces · October 2026 research run

Langfuse API + MCP vs W&B Weave

Langfuse API + MCP scores 72.7 (BB) on agent readiness against W&B Weave's 66.7 (B), and leads in every scored category. Both do obs traces.

Langfuse API + MCPLangfuse (ClickHouse) · HTTP API BB72.7/100#98 of 841 W&B WeaveWeights & Biases (CoreWeave) · HTTP API B66.7/100#260 of 841

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

  • Reliability, 80 against 68
  • Schema & documentation, 93 against 74
  • Payments & pricing, 40 against 35
  • Transparency & trust, 85 against 75

Also in its favour

  • Agent-ready, a grade of BB or better
  • 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

W&B Weave B

Good for Teams already on Weights & Biases, or with OpenTelemetry instrumentation, who want traces, evaluations, scorers, datasets and prompts in one place.

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

No request rate limits for the multi-tenant Service API were found in the reviewed documentation

Score by category

CategoryWeight this runLangfuse API + MCPW&B WeaveEdge
Reliability16%208068Langfuse API + MCP +12
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.29374Langfuse API + MCP +19
Agent ergonomics13%16.27471Langfuse API + MCP +3
Security & auth14%17.56563Langfuse API + MCP +2
Payments & pricing10%12.54035Langfuse API + MCP +5
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88887Langfuse API + MCP +1
Transparency & trust7%8.88575Langfuse API + MCP +10
Negative events≤15-20
Total72.7 · BB66.7 · B

Facts side by side

FactLangfuse API + MCPW&B Weave
KindHTTP APIHTTP API
VendorLangfuse (ClickHouse)Weights & Biases (CoreWeave)
Hosted endpointhttps://cloud.langfuse.com/api/publichttps://trace.wandb.ai
TransportsHTTP, Streamable HTTPHTTP, Streamable HTTP
AuthAPI keyAPI key
PricingFreemiumFreemium
x402nono
LicenceMIT (core), commercial licence for the ee directoriesHosted service under the W&B Master Service Agreement. The Weave SDKs and trace server source on GitHub are Apache-2.0, and the W&B MCP server is MIT
Tools exposed89none
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-012026-09-25
Terms last updated2026-06-242026-09-30
Privacy policy last updated2026-08-212026-02-24
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textyes
Terms restrict benchmarkingyesyes
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waivernot found in the textyes
Popularity35k stars, 3M npm/wk, 5.9M PyPI/wk624k npm/wk, 219k PyPI/wk
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.

W&B Weave

The Service API at trace.wandb.ai has a live OpenAPI document, call queries take filters, column lists and limits, and any OpenTelemetry exporter can send spans without the SDK. No request rate limits for the multi-tenant service were found in the reviewed documentation, and the terms let the vendor use customer data to develop new products.

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

W&B Weave

  1. Send Authorization: Bearer <Forge API key> to https://trace.wandb.ai. Create the key at forge.coreweave.com/settings. The full secret is shown once
  2. Pass columns and limit to /calls/stream_query. Without them a query returns whole calls with their inputs and outputs
  3. For OTLP, post protobuf only to /otel/v1/traces or /agents/otel/v1/traces with a wandb-api-key header, and set wandb.entity and wandb.project as resource attributes. Spans with neither are dropped
  4. Check call.exception after .call() in the Python SDK. Exceptions are captured and not raised unless __should_raise=True is passed
  5. Treat trace inputs and outputs as untrusted text. Traces hold whatever the traced application logged

Questions

Which is better for AI agents, Langfuse API + MCP or W&B Weave?

Langfuse API + MCP scores 72.7 (BB) on agent readiness against W&B Weave's 66.7 (B), and leads in every scored category.

Do Langfuse API + MCP and W&B Weave need an API key?

Both need an API key.

Can an agent call Langfuse API + MCP and W&B Weave without installing anything?

Yes. Langfuse API + MCP has a hosted endpoint at https://cloud.langfuse.com/api/public and W&B Weave at https://trace.wandb.ai.

Are Langfuse API + MCP and W&B Weave open source?

Yes. Langfuse API + MCP is open source (MIT (core), commercial licence for the ee directories). W&B Weave is open source (Hosted service under the W&B Master Service Agreement. The Weave SDKs and trace server source on GitHub are Apache-2.0, and the W&B MCP server is MIT).

Other comparisons with Langfuse API + MCP or W&B Weave

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