Pricing, limits, and integration
Temso's API is part of the SaaS subscription, not a standalone product. REST API access appears from the $199/month Growth plan and on Professional ($499); only the $29 Basic plan lacks it. The MCP server is on every plan, so MCP-based agent access starts at $29.
The API is documented with a live OpenAPI 3.1.1 spec (base https://api.temso.ai/v1) covering projects, AI responses, brands, mentions, sources and analytics (visibility, share of voice, brand rankings), plus POST /traffic/ingest/worker/{sourceId} for event ingestion. Auth is API-key based in practice; the spec does not declare a formal security scheme. No rate limits are published.
Operational limits are lightly documented: no published rate-limit threshold (a 429 error exists, so build in backoff), Bearer tms_ keys that are project-scoped, and required 90-day date filters on data endpoints. There are no SDKs or webhooks. Beyond the REST API, Temso runs a live OAuth MCP server (app.temso.ai/api/v1/mcp, read-only) for Claude, Cursor and ChatGPT, so agents have a no-key path as well as the programmatic one.
How much does the Temso AI API actually cost?
Temso AI publishes an API, but per-tier gating wasn't extracted automatically.
- Most likely scenario: API access is either included in all paid plans, or it's gated to higher tiers and we need to verify on the live docs page.
- Until verified, treat the question "which plan unlocks the API" as open. Don't budget on the assumption it's free with the cheapest paid plan.
API at a glance
Which AI clients can read Temso AI data?
Not every AI assistant supports MCP natively. Here's the per-client picture for Temso AI specifically.
| Client | Support | Notes |
|---|---|---|
| Claude Code | Native MCP | Add the Temso MCP connector (OAuth sign-in, no key). Read-only tools. |
| ChatGPT | Native MCP | Connect the Temso MCP server (OAuth). Read-only. |
| Cursor | Native MCP | Add the MCP connector (OAuth). Read-only tools. |
| Claude (Desktop/Web) | Native MCP | Add as a custom connector via the MCP URL (OAuth). |
Temso AI also has an MCP server
If you're wiring Temso AI into Claude / Cursor / Codex, the MCP server is usually less code than the REST API.
See Temso AI MCP pageWhat you can build with the Temso AI API
Three personas, three different shapes of build. Pick the row that matches how you actually ship.
Glue Temso AI into your daily workflow
- Pull a digest of ranking changes into your morning Slack
- Trigger a one-off backfill when something looks off
- Pipe data into your own SQLite for ad-hoc queries
Sell Temso AI reporting at scale
- White-label Temso AI data into client-branded dashboards
- Run scheduled multi-account reports without logging into the Temso AI UI
- Cross-reference with the rest of the client's stack (CRM, analytics, ad spend)
Production pipelines for Temso AI
- Real-time sync into your warehouse on a cron
- Custom alerts the dashboard's built-in alerting can't express
- Backfill + idempotency handling for Temso AI data older than the dashboard exposes
Limits and gotchas
- No OpenAPI spec — you write typed clients by hand or use a third-party generator on the docs HTML.
- No official SDK detected. Plan on hitting the API directly with your HTTP client of choice.
- Rate limits: always read the docs page before scaling — the published limit is usually lower than the practical one and overages can be expensive.
Agent-readiness verdict
A real, OpenAPI-documented REST API with the right endpoints for agent workflows, including a traffic-ingestion path. Held back mainly by the lack of SDKs, now that REST API access starts on the $199 Growth tier. Solid 7 out of 10 for API agent-readiness.
Temso AI API FAQ
Should I use the API or the MCP server for Claude / Cursor / Codex?+
Does Temso AI have a public API?+
Sources
- Temso AI official site: https://www.temso.ai
10+ years in digital marketing. I review marketing software for AI-stack fit: real pricing, MCP and API support, and how cleanly each tool drops into an AI agent workflow, cross-checked against verified data and real user feedback.

