Arcmira vs Kagi Search API

Arcmira

Four code-mode tools over a documented v1 API, OAuth 2.1 with four scopes, a read-only sign-up key from two API calls and no card, and a 1,000-credit free month. No status page, SLA or security.txt, breaking v1 changes shipped in October with same-day notice, the server is at 0.10.7, and the index covers the shows Arcmira transcribes.

Kagi Search API

A public OpenAPI file, typed filters and API keys that can be limited by product and IP address make the API simple to call, at $12 per 1,000 searches. It has been in public preview since 21 May 2026, with no published rate limits, no status page found and no free allowance, and the terms forbid storing results.

Arcmira

1. Call arcmira_describe once per session and write one program per question for arcmira_execute_read; return only the fields the answer needs, since output is cut at 12,000 characters and 3,000 per string.
2. Resolve names with arcmira.resolve (free) before any about, by, entity_ids or channel filter; a name in a filter fails with id_required. Plain keyword search needs no resolver call.
3. Check arcmira.status() or GET /v1/me for the plan, scopes and usage.credits.available before metered reads; on Free, media newer than 30 days and pages past the first fail with freshness_requires_paid and pagination_gated.
4. A Premium read of an untranscribed video starts a transcription that uses credits (300 per started 15 minutes) and may return pending; read the same video again later, which is never charged twice, and send retry: true only when the user asks.
5. Over HTTP send Authorization: Bearer arc_sk_..., an Idempotency-Key on every POST and PATCH, honour Retry-After on 429, and switch on error.code, following unlock.url on 402 and 403 rather than re-authenticating.
6. Use arcmira_execute_write only after listing the user's monitors; it creates, follows and pauses but never deletes, and a connection made before server 0.9.0 answers insufficient_scope until reconnected.

Kagi Search API

1. Send POST https://kagi.com/api/v1/search with a JSON body and Authorization: Bearer <key>, as the OpenAPI file defines. Only query is required
2. Set limit to cap results returned. In the mixed search workflow the MCP tool applies the cap to each result category separately
3. Use extract.count (1 to 10) only when page text is needed. Extraction is billed at the Extract rate on top of the search
4. Do not store results. The API terms allow only the transient caching an application needs, and require deletion on termination
5. On 429 back off before retrying. The response covers both rate limiting and an exhausted usage limit, and no Retry-After header is documented