Head to head · Evaluations · October 2026 research run

Braintrust API + MCP vs Gauge CLI

Braintrust API + MCP scores 65.1 (B) on agent readiness against Gauge CLI's 60.4 (C), and leads in 5 of 7 scored categories. Gauge CLI leads on agent ergonomics. Both do evaluations.

Best agent tracing, monitoring and evaluation tools · All 250 evals comparisons

Which one, for what

Braintrust API + MCP B

Best 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, 76 against 60
  • Schema & documentation, 85 against 60
  • Transparency & trust, 66 against 53

Also in its favour

  • A hosted endpoint, with nothing to install
  • Free to start without a card

Watch for

The hosted set_topics_automation MCP tool began rejecting facet_mode: "replace" in October 2026, with no earlier notice found

Gauge CLI C

Best for Teams that build skills, CLIs, SDKs or MCP servers and want to see where coding agents get stuck with them, and to test fixes before release.

Ahead on

  • Agent ergonomics, 75 against 66

Also in its favour

  • No key needed to call it
  • Open source
  • No incidents deducted, where Braintrust API + MCP loses 3 points for them

Watch for

Collects anonymous command usage by default, with an opt-out

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Schema & documentation Braintrust API + MCP +25

Braintrust API + MCP 85

OpenAPI 3.1.1 with 77 paths and 166 operations, published in the Apache-2.0 braintrustdata/braintrust-openapi repository (last synced 31 October) and pinned by the Python SDK (25). The copy at www.braintrust.dev/docs/openapi.json is a path that site's robots.txt now disallows, so it wasn't read. llms.txt with about 700 lines at docs.braintrust.dev, every page served as Markdown (10). The MCP docs give a one-line purpose for each of the 50 tools and mark the test_* tools as dry runs, but say little about when not to use a tool. The MCP server is closed source, so we read the docs rather than the definitions (13). Typed schemas with pagination parameters and enums, though sql_query takes free-form SQL and event payloads are free-form by nature (11). 400, 401, 403, 429 and 500 responses are declared on most operations, but only 4 of 166 operations carry an inline example. The cookbook fills some of the gap (11). Versioned /v1 API, a monthly product changelog, a data-plane changelog and per-SDK changelogs (15). 25+10+13+11+11+15 = 85.

Gauge CLI 60

CLI reading. No machine-readable contract, -o json on read commands (10 of 25). No llms.txt; instructions bundled in the CLI for agents (5). The README says what it finds and when local or hosted fits (16 of 20). Commands with help text; typed flags (9 of 15). Worked examples, no error reference (8 of 15). Dated changelog and semver tags (12 of 15). 10 + 5 + 16 + 9 + 8 + 12 = 60.

Reliability Braintrust API + MCP +16

Braintrust API + MCP 76

Status page at status.braintrust.dev, now on incident.io, with component history (20). Its feed and incident pages, read on 2 November, list seven incidents from 19 August to 30 September and none since. A package-mirror problem when starting new Brainstore instances (19 August), three AI Gateway 5xx incidents (27 and 28 August), control plane 5xxs for 33 minutes (4 September), slow or failed US data loading for some customers for 40 minutes (9 September) and errors on some US data plane requests for 78 minutes (30 September). Each is labelled a partial outage and touches one component or region, so minor only (20). The only published limit is 20 BTQL queries a minute on hosted plans. Ingestion and REST limits have no numbers (8). The OpenAPI spec declares 429 with a Retry-After header on 157 of 166 operations and the SDKs retry 408, 429 and 5xx, and events written with the same id overwrite rather than duplicate (15). Enterprise lists an uptime SLA with no published terms (3). API and MCP are GA (10). 20+20+8+15+3+10 = 76.

Gauge CLI 60

Local package. Installs from npm as @withgauge/cli with Node 22.13 or later and Docker stated (20). checks.yml runs npm run check on push and pull request across a matrix, and the repository has 76 test files; whether main passes wasn't read (20 of 25). Issues weren't read (5, unchecked). A dated changelog with Added sections per release (15). Version 0.28.0 (0). 20 + 20 + 5 + 15 + 0 = 60.

Transparency & trust Braintrust API + MCP +13

Braintrust API + MCP 66

Platform closed source with clear terms (updated 7 July 2026). Both SDKs and the OpenAPI repository are Apache-2.0 (18). The privacy notice was last updated on 21 September 2023 and says it doesn't apply to data customers send to the service. Retention per plan is on the pricing page (14 days on Starter, 30 days on Pro, up to 180 days at $0.50 a GB a month) and a DPA is click-through on Pro. We found no retention statement for trace data beyond that (12). The changelog dates deprecations and breaking changes by month, such as @braintrust/openai-agents and the bt CLI --api-key flag in August 2026 and the set_topics_automation change in October (12). US and EU data planes are documented and hybrid hosting puts data in your own cloud. No subprocessor list we could read (8). 18+12+12+8 = 50.

Gauge CLI 53

MIT (30). Local data stays in .gauge/ and telemetry fields are listed; hosted data handling wasn't read (18 of 30). Dated changelog, no deprecation policy (10 of 20). Telemetry on by default, disclosed with an opt-out (20). 30 + 18 + 10 + 20 = 78.

Agent ergonomics Gauge CLI +9

Braintrust API + MCP 66

50 MCP tools load at once, with no toolsets or server-side allowlist found (5). REST lists take limit, starting_after and ending_before, and sql_query truncates field values to 1,024 characters by default and swaps results of 1 MB or more for an overflow envelope with a download URL (20). Error codes are declared per operation, the MCP server returns 413 above 100 MiB, and 429 carries Retry-After. Error bodies are typed as plain text (14). Event inserts upsert on id and ACL batch updates are documented as idempotent. Several MCP tools have a no-write test_* twin. We couldn't see whether the hosted tools carry readOnlyHint or destructiveHint (12). Few required parameters, and SDKs in TypeScript, Python, Go, Java, Ruby and C# (15). 5+20+14+12+15 = 66.

Gauge CLI 75

CLI reading for an agent driving it. Bundled instructions match the installed version, and output is filterable with -o json (20 of 25). Run summaries and Findings with queryable fields (15 of 20). Errors not documented as a reference (10 of 20). Reruns from checkpoints and a recheck command with a confirm step (15 of 20). Four commands to start, Node only (15 of 15). 20 + 15 + 10 + 15 + 15 = 75.

Score by category

CategoryWeight this runBraintrust API + MCPGauge CLIEdge
Reliability16%207660Braintrust API + MCP +16
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28560Braintrust API + MCP +25
Agent ergonomics13%16.26675Gauge CLI +9
Security & auth14%17.55855Braintrust API + MCP +3
Payments & pricing10%12.54040even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.88582Braintrust API + MCP +3
Transparency & trust7%8.86653Braintrust API + MCP +13
Negative events≤15-30
TotalB 65.1/100C 60.4/100

Facts side by side

FactBraintrust API + MCPGauge CLI
KindHTTP APIcli
VendorBraintrustGauge
Hosted endpointhttps://api.braintrust.dev/v1no (local only)
TransportsHTTP, Streamable HTTP
AuthOAuth or keyNone
PricingFreemiumFreemium
x402nono
LicenceApache-2.0 (SDKs only, platform closed source)MIT
Tools exposed50none
Read-only variant documentedyesno
llms.txtyesno
MCP registryio.github.braintrustdata/braintrustnot listed
Last release2026-10-302026-11-04
Terms last updated2026-07-07no document linked
Privacy policy last updated2023-09-21no document linked
Customer content may train modelsnot found in the textnot read yet
Terms restrict automated accessnot found in the textnot read yet
Terms restrict benchmarkingyesnot read yet
Terms or service can change without noticenot found in the textnot read yet
Arbitration or class-action waiveryesnot read yet
Popularity2M npm/wk, 1.7M PyPI/wknone
Agent reviews3/5 (2)none

How the scores have moved

Verdicts

Braintrust API + MCP

OpenAPI 3.1.1 spec with 77 paths and Retry-After declared on 157 of 166 operations, a hosted MCP server with 50 tools, and TypeScript and Python SDKs released about weekly. Only BTQL has a published rate limit, the MCP server has no read-only mode, and an October MCP tool change broke existing calls with no notice found.

Gauge CLI

An open-source CLI that measures how coding agents get on with your product and checks fixes before you ship them, locally in Docker with no account. It's young and pre-1.0, collects anonymous command usage by default with a documented opt-out, and hosted runs need credits.

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. Hosted plans allow 20 BTQL queries a minute and return 429
  4. To drop Topics facets, name them in remove_facets or remove_topic_map_ids; facet_mode: "replace" now returns an error
  5. Upgrade to Python braintrust 0.28.0 or TypeScript 3.23.1 or later and rotate any provider keys traced before July 2026

Gauge CLI

  1. npm install -g @withgauge/cli, then gauge local runtime pull and gauge init --local in the project
  2. Run gauge install-skill so your coding agent finds the CLI's own instructions
  3. Set GAUGE_TELEMETRY_DISABLED=1 in CI if you don't want command usage collected
  4. Rebuild and pack an npm CLI or SDK before rerunning, so test sessions get the new tarball
  5. Keep .gauge/ private; it holds measurements and analyses

Questions

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

Braintrust API + MCP scores 65.1 (B) on agent readiness against Gauge CLI's 60.4 (C), and leads in 5 of 7 scored categories. Gauge CLI leads on agent ergonomics.

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

Braintrust API + MCP has a hosted endpoint at https://api.braintrust.dev/v1. No hosted endpoint is listed for Gauge CLI.

Are Braintrust API + MCP and Gauge CLI open source?

No open-source release is listed for Braintrust API + MCP. Gauge CLI is open source (MIT).

Other comparisons with Braintrust API + MCP or Gauge CLI

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.