Get an audit

Head to head · Obs traces · October 2026 research run

Braintrust API + MCP vs LangWatch

LangWatch scores 65.5 (B) on agent readiness against Braintrust API + MCP's 61.1 (C), and leads in 5 of 7 scored categories. Braintrust API + MCP leads on reliability. Both do obs traces.

Braintrust API + MCPBraintrust · HTTP API C61.1/100#433 of 841 LangWatchReasoning Engine B.V. (LangWatch) · HTTP API B65.5/100#291 of 841

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

  • Reliability, 61 against 53

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

LangWatch B

Good for Teams that want tracing, evaluations and simulated-user agent tests in one open-source product, hosted in the EU or self-hosted, and that drive it from a coding assistant through MCP or the CLI.

Ahead on

  • Security & auth, 71 against 58
  • Maintenance & community, 90 against 85
  • Transparency & trust, 75 against 66

Also in its favour

  • Runs on your own machine
  • Open source

Watch for

The MCP server registers 101 tools, deletes and key creation among them, with no toolsets and no readOnlyHint or destructiveHint annotations in the source

Score by category

CategoryWeight this runBraintrust API + MCPLangWatchEdge
Reliability16%206153Braintrust API + MCP +8
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28587LangWatch +2
Agent ergonomics13%16.26667LangWatch +1
Security & auth14%17.55871LangWatch +13
Payments & pricing10%12.54040even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88590LangWatch +5
Transparency & trust7%8.86675LangWatch +9
Negative events≤15-4-2
Total61.1 · C65.5 · B

Facts side by side

FactBraintrust API + MCPLangWatch
KindHTTP APIHTTP API
VendorBraintrustReasoning Engine B.V. (LangWatch)
Hosted endpointhttps://api.braintrust.dev/v1https://app.langwatch.ai
TransportsHTTP, Streamable HTTPHTTP, Streamable HTTP, SSE (legacy), stdio
AuthOAuth or keyOAuth or key
PricingFreemiumFreemium
x402nono
LicenceApache-2.0 (SDKs only, platform closed source)Apache 2.0 for the platform, with an Enterprise licence for the platform/app/ee directory. The SDKs and the MCP server are MIT
Tools exposed42101
Read-only variant documentedyesno
llms.txtyesyes
MCP registryio.github.braintrustdata/braintrustnot listed
Last release2026-10-012026-10-02
Terms last updated2026-07-072026-09-22
Privacy policy last updated2023-09-212026-09-29
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textyes
Terms restrict benchmarkingyesnot found in the text
Terms or service can change without noticenot found in the textyes
Arbitration or class-action waiveryesnot found in the text
Popularity2M npm/wk, 1.7M PyPI/wk4.9k stars, 50k npm/wk, 87k PyPI/wk
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.

LangWatch

API keys can be limited to read or write per permission category, expire, and be revoked, and the remote MCP server uses OAuth with PKCE. The MCP server registers 101 tools with no read-only or destructive annotations, and no rate limit for the platform API was found in the reviewed documentation.

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

LangWatch

  1. Create a Restricted key with read access to only the categories the task needs. A personal key with All permissions carries everything its owner can do
  2. Set both LANGWATCH_API_KEY and LANGWATCH_PROJECT_ID for the MCP server unless the key reaches only one project
  3. Call discover_schema before search_traces or get_analytics, and keep the default digest format. json returns the full raw trace
  4. Allowlist MCP tools in the client. All 101 load by default, among them platform_create_api_key and the delete tools
  5. Follow next_cursor until it is null on list endpoints. A full page does not mean more rows exist

Questions

Which is better for AI agents, Braintrust API + MCP or LangWatch?

LangWatch scores 65.5 (B) on agent readiness against Braintrust API + MCP's 61.1 (C), and leads in 5 of 7 scored categories. Braintrust API + MCP leads on reliability.

Do Braintrust API + MCP and LangWatch need an API key?

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

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

Yes. Braintrust API + MCP has a hosted endpoint at https://api.braintrust.dev/v1 and LangWatch at https://app.langwatch.ai.

Are Braintrust API + MCP and LangWatch open source?

No open-source release is listed for Braintrust API + MCP. LangWatch is open source (Apache 2.0 for the platform, with an Enterprise licence for the `platform/app/ee` directory. The SDKs and the MCP server are MIT).

Other comparisons with Braintrust API + MCP or LangWatch

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