Monid vs Smithery

Monid

An agent can search a catalogue of paid data and media endpoints by need, read each one's schema and price, and pay per run from one prepaid balance with person-set budgets, or by x402. Rate limits have no numbers, paid runs take no idempotency key, no security contact was found, and the skill sends a known email to setup telemetry.

Smithery

Service tokens can be limited by namespace, resource, operation and connection metadata, with a lifetime of at most 24 hours. No terms of service, rate limits or SLA were found, the pricing page could not be read, and the newest client release is from 20 July 2026.

Monid

1. Call inspect before every run and pass body, queryParams and pathParams in the shape it returns; run inputs aren't typed at the API level.
2. Treat a COMPLETED run as success only when providerResponse.httpStatus is 2xx; provider errors complete with a non-2xx status and aren't charged.
3. Don't resend a paid run after a timeout without checking GET /v1/runs; there's no idempotency key and a repeat bills again.
4. Start with small maxItems on per-result endpoints; limits often apply per query, not per call.
5. Pass --client alone to monid setup, or skip it; the email flag only feeds Monid's setup telemetry.

Smithery

1. Keep the API key on the backend and hand an agent a service token limited to connections with read and execute and a metadata match
2. Create connections with PUT /connect/{namespace}/{connectionId}, which is an upsert, and check status.state before calling a tool
3. On auth_required or input_required, send the person to setupUrl, then retry with the same connectionId
4. Tool names on the namespace MCP endpoint are prefixed with the connection ID, such as user-123-github.search_repositories
5. Do not rely on smithery skill commands. Version 1.1.1 of the CLI removed them