Head to head · Agent tracing · October 2026 research run

Braintrust API + MCP vs Hue

Braintrust API + MCP scores 67.6 (B) on agent readiness against Hue's 56.7 (C), and leads in 5 of 7 scored categories. Hue leads on agent ergonomics and security & auth. Both do agent tracing.

Best agent tracing, monitoring and evaluation tools · All 294 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 30
  • Schema & documentation, 85 against 68
  • Payments & pricing, 60 against 0
  • Transparency & trust, 66 against 59

Also in its favour

  • 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

Hue C

Best for Teams testing agents that act in Gmail, Slack, Salesforce, Notion, Linear and similar apps who want stateful simulated copies seeded from traces or a description.

Ahead on

  • Agent ergonomics, 88 against 66
  • Security & auth, 74 against 58

Also in its favour

  • No incidents deducted, where Braintrust API + MCP loses 3 points for them

Watch for

No self-serve sign-up found. Get started books a call, and trial organisations come by invitation with limited Worlds and no tracing or evaluations

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.

Payments & pricing Braintrust API + MCP +60

Braintrust API + MCP 60

No x402 or other machine payment (0). Usage prices published without login, $4 a GB and $2.50 per 1,000 scores on Starter, $3 and $1.50 on Pro (20). Starter is free with no card (20). A person signs up in a browser to create a key. The MCP OAuth flow also needs a browser sign-in (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.

Hue 0

No x402 or other machine payment found (0). No pricing page. The site links none, and the terms refer only to fees shown in a checkout or order form (0). No free tier open to all. Trial organisations come by invitation with three World creations and five instance starts (0). Get started books a call on cal.com, and the app answers with a sign-in page (0). 0+0+0+0 = 0.

Reliability Braintrust API + MCP +46

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.

Hue 30

No status page found. The site, docs and SDK repository link none (0). With no history to read, 5. No request rate limits for the API or MCP server are published. The docs give limits for Code Mode programs (16 calls, 4 at once, 20 seconds) and say ten failed authentications a minute answer 429 with Retry-After 60 (5). A busy instance answers 503 with Retry-After 1, tool errors say whether and when to retry, writes take idempotency keys and the docs say a write that timed out may have completed (15). No SLA found, and the terms carry none (0). The site calls this a public launch, but the SDKs are 0.x and trial organisations get a reduced product (5). 0+5+5+15+0+5 = 30.

Agent ergonomics Hue +22

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.

Hue 88

About 217 tools in all, but a default connection lists 18 (15 production reads and three catalogue tools), with named toolsets, a read-only switch and a four-tool Code Mode (15, plus 7 for the subsets). Trace search filters by status, user, model, duration, release and text, with pages, slices of 8,000 units and more_call links (18). Errors carry a code, message, hint, retryable and retry_after_ms (18). Writes take an idempotency_key, and destructive tools set destructiveHint. Read-only hints weren't seen, since the tool list couldn't be read (15). Official TypeScript and Python SDKs and a CLI (15). 22+18+18+15+15 = 88.

Schema & documentation Braintrust API + MCP +17

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.

Hue 68

The MCP server publishes typed schemas through search_hue_tools, which returns input_schema and annotations for each tool, but the server answers 401 without an account, so no schema was read. No OpenAPI file found (10). llms.txt and a Markdown copy of every page (10). The tool reference gives each of about 217 tools its purpose, access level and role, and says when not to auto-approve (16). Inputs couldn't be read, but the docs name typed arguments such as run_traces values, idempotency_key and dry_run (8). Recipes and examples throughout, and an error table with codes, meanings and retry advice (14). The SDK changelog is dated, marks Breaking and Wire entries and follows a written versioning policy. Renamed tools answer not_found naming the replacement. No product or MCP changelog found (10). 10+10+16+8+14+10 = 68.

Security & auth Hue +16

Braintrust API + MCP 58

User API keys and service tokens as Bearer tokens. Service tokens attach to permission groups that can be scoped to single projects on any plan, keys can be deleted through /v1/api_key and /v1/service_token, and the MCP server also takes OAuth 2.0 with dynamic client registration (25). Viewer groups exist, but the MCP server has no server-side read-only mode, and the docs tell users to set their client to confirm write tools (12). Traces hold whatever the application logged, and we found no prompt-injection guidance for agents reading them (3). The changelog mentions audit logging, and a knowledge-base page says org-wide API key auditing is in the UI only, per the 1 October check (8). SOC 2 Type II is claimed on the pricing page, re-read on 2 November. The Vanta trust centre at trust.braintrust.dev answers with its app page and wasn't read, there's no security.txt (404) and no SECURITY.md in either SDK repository. The knowledge-base pages for the two July credential-capture fixes now point to GitHub security advisories, whose pages we couldn't read (10). 25+12+3+8+10 = 58.

Hue 74

OAuth with dynamic client registration and PKCE, scopes mcp:read and mcp:write in the 401 answer, one-hour access tokens and revocation under Connected apps. Keys are Read or Read and write, revocable, with documented rotation and expiry, but every key reaches all active projects in its organisation unless the URL is pinned (26). A Read key and ?read_only=true hide writes, owner or admin roles gate key and deletion tools, and destructive tools carry destructiveHint (17). Recorded content is opt-in per call, marked untrusted and audited (12). Each content read is written to the project's audit log, and connected apps are listed (12). SECURITY.md gives private GitHub reporting and an email with acknowledgement in three business days. No security.txt and no bug bounty found. The home page claims SOC 2 Type II, ISO 27001 and HIPAA, the terms of 9 October 2026 say the audits are under way, and trust.hue.run is closed to ClaudeBot (7). 26+17+12+12+7 = 74.

Transparency & trust Braintrust API + MCP +7

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.

Hue 59

Closed platform with terms from Hue Intelligence Inc. (last updated 9 October 2026, New York law). SDKs under MIT (15). The privacy policy of 28 October 2026 gives no retention periods. The docs say telemetry retention is set per project and nothing expires without a policy, the terms rule out training general models on customer content and require a DPA before personal data, and the docs name what goes to TypeSafe and the Vercel AI Gateway. These agree but leave gaps (18). Renamed tools point to their replacements, legacy key presets keep working, and the terms promise 30 days' notice of price rises. No dated deprecation notices (8). Subprocessors are named only by category in the privacy policy and no data location was found (8). 15+18+8+8 = 49.

Score by category

CategoryWeightBraintrust API + MCPHueEdge
Reliability16%7630Braintrust API + MCP +46
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%8568Braintrust API + MCP +17
Agent ergonomics13%6688Hue +22
Security & auth14%5874Hue +16
Payments & pricing10%600Braintrust API + MCP +60
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8583Braintrust API + MCP +2
Transparency & trust7%6659Braintrust API + MCP +7
Negative events≤15-30
TotalB 67.6/100C 56.7/100

Facts side by side

FactBraintrust API + MCPHue
KindHTTP APIHTTP API
VendorBraintrustHue
Hosted endpointhttps://api.braintrust.dev/v1https://mcp.hue.run/mcp
TransportsHTTP, Streamable HTTPStreamable HTTP, HTTP
AuthOAuth or keyOAuth or key
PricingFreemiumPaid
x402nono
LicenceApache-2.0 (SDKs only, platform closed source)none
Tools exposed50217
Read-only variant documentedyesyes
llms.txtyesyes
MCP registryio.github.braintrustdata/braintrustnot listed
Last release2026-10-302026-11-12
Terms last updated2026-07-072026-10-09
Privacy policy last updated2023-09-212026-10-28
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textnot found in the text
Terms restrict benchmarkingyesnot found in the text
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waiveryesnot found in the text
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.

Hue

Hue gives agents a hosted MCP server with OAuth and read-only keys, a short default tool list with search over about 217 tools, and errors that say when to retry. Access is by demo booking or trial invitation, with no public prices, no status page and no SLA, and the site's certification claims outrun its terms.

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

Hue

  1. Connect to https://mcp.hue.run/mcp with ?toolsets=all only if your client defers tool definitions, otherwise keep the default 18 tools and call search_hue_tools
  2. Use a Read key or ?read_only=true for inspection, since sign-in grants Read and write to every active project
  3. Read the retryable flag before retrying a failed tool, and on a write that timed out read its state first
  4. Reuse the same idempotency_key when retrying create_world, launch_run, edit_world or send_instance_input
  5. Treat recorded span content as untrusted data, and request it only when needed, because every read is audited

Questions

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

Braintrust API + MCP scores 67.6 (B) on agent readiness against Hue's 56.7 (C), and leads in 5 of 7 scored categories. Hue leads on agent ergonomics and security & auth.

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

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

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

Yes. Braintrust API + MCP has a hosted endpoint at https://api.braintrust.dev/v1 and Hue at https://mcp.hue.run/mcp.

Other comparisons with Braintrust API + MCP or Hue

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.