Gauge CLI vs LangSmith API + MCP

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.

LangSmith API + MCP 86

Public OpenAPI 3.1 at api.smith.langchain.com/openapi.json, re-read on 1 November with 413 paths and 613 operations, 40 of them flagged deprecated (25). llms.txt and Markdown docs (10). MCP tool docstrings are long and practical. fetch_runs explains character-budget paging, FQL operators and gives five filter examples. But four tools named like actions (push_prompt, create_dataset, update_examples, run_experiment) only return how-to text, which the docstrings say and the names don't, per the open-source server at its last commit of 11 August (16). Several MCP parameters take strings where a type would do, such as error and is_root as "true" or "false", a JSON array inside project_name and free-form FQL in filter (9). Examples throughout the docs and docstrings. Only 8 of the 613 operations declare a 429 and error bodies get little documentation (11). Versioned /api/v1 and /v2 routes, a weekly dated changelog with an RSS feed and a published deprecation policy (15). 25+10+16+9+11+15 = 86.

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.

LangSmith API + MCP 78

Closed platform. The SDKs and the open-source MCP server are MIT (18). Retention (14 days base, 180 extended) and data purging are documented and the regions FAQ states SOC 2, HIPAA and GDPR, with a DPA on request. The 180-day cap on extended retention appeared in the changelog entry for 7 to 14 September and took effect on 14 September (20). Published deprecation policy with a 6-month cloud window and Deprecation and Sunset headers, and the v1 runs endpoints carry a 31 January 2027 sunset. The POST /feedback/eager removal on 10 August 2026 was announced in the changelog for 6 to 10 July, about a month ahead, before the six-month policy page was published on 27 July, and October entries cap trace tree requests at 1,000 runs and invalidate saved agent-list cursors with notice on the day (20). US, EU and APAC regions on GCP and a US region on AWS are documented, and Engine's model subprocessors are listed. We couldn't read a full subprocessor list (12). 18+20+20+12 = 70.

Gauge CLI 55

Local tool. Agent credentials stay on your machine in local mode; hosted login with a device flow (20 of 30). Test agents run in fresh Docker sessions with injected inputs, and the gateway brokers credentials in hosted mode (12 of 20). Agents under test read your product's docs and outputs, with no prompt-injection guidance (5 of 15). Local transcripts and SQLite evidence per run (10 of 15). No security policy found (8 of 20). 20 + 12 + 5 + 10 + 8 = 55.

LangSmith API + MCP 79

Personal access tokens inherit the user's permissions. Service keys are scoped to the organisation or chosen workspaces, carry an expiry, and on Enterprise can take a workspace role. Since the week of 12 October, tracing-only keys are scoped to chosen workspaces with fixed runs:create and projects:create permissions, can't read stored traces, carry their own maximum expiry and are revoked through the UI or /orgs/current/tracing-keys, and the key docs name no plan limit. The remote MCP uses OAuth 2.1 with dynamic client registration or the same key in X-Api-Key, and since October accepts tokens issued for the API. Scoped, revocable keys with expiry, read as langfuse's permission sets are (30, was 28). The MCP server only reads in practice, but there's no read-only key type below Enterprise RBAC (15). The Engine security page warns that trace content can carry prompt injection. The MCP page says nothing about it (6). Audit logs on Enterprise, queryable by API (10). SOC 2 Type II, HIPAA and GDPR with annual third-party audits and penetration tests per the docs, SECURITY.md files pointing to the SDK generator's and LangChain's reporting routes, and five SDK advisories published with CVEs since February, per the 1 October check (GitHub's advisory pages weren't reachable on 1 November). www.langchain.com answers "Invalid .well-known request" for security.txt, so none (18). 30+15+6+10+18 = 79.

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.

LangSmith API + MCP 81

incident.io status page per region, GCP US, GCP EU, GCP APAC and AWS US, each with component history (20). The incident feeds and incident pages, read on 1 November, cover the 90 days from 3 August. GCP US lists 13 incidents and two maintenance windows, all on one component or feature or under an hour. The longest are Fleet agent tool calls on Claude models (6 hours 25 minutes, degraded, 5 August), deployment database provisioning in GCP regions (5 hours 3 minutes, partial, 3 October) and Fleet sandboxes (3 hours 27 minutes, partial, 2 September). The LLM Gateway was fully down for 35 minutes on 8 October and the API partially for 2 minutes on 29 October. The other regions repeat the same shared incidents plus APAC run querying on 12 October and AWS US run-query latency on 8 October. Minor only (20). Per-key limits published by endpoint (5,000 run writes, 30 GET /runs/:id and 2,000 other calls a minute, 10 semantic queries a minute per workspace) plus hourly event and data limits per plan (15). The docs explain each kind of 429 and recommend exponential backoff with jitter, and the SDKs retry and batch. Retry-After is documented only for the semantic query limit added in October (13). Enterprise has a support SLA. We found no uptime SLA (3). API and remote MCP are GA (10). 20+20+15+13+3+10 = 81.