What Moz Pro exposes
Moz operates five distinct product surfaces under the Moz Data umbrella: Moz Pro (the SEO suite), Moz Local (local SEO listings and reviews), STAT (enterprise SERP analytics, demo-only from $360/mo for 3,000 keywords), Moz API (first-party row-billed access to 17 endpoints), and Moz Data (custom bespoke pipelines for AI model training). The underlying index spans 45.5 trillion links, 8.7 trillion URLs, 1 billion domains, 800M+ keyword suggestions, and 1.25 billion monthly keyword volumes. Domain Authority is the proprietary metric most teams know Moz for, but the deeper bet for AI-stack use cases is the Moz API: a free tier of 50 rows/month is enough to wire up exploratory agents before committing to a paid plan.
Access, auth, and limits
No first-party MCP means no first-party auth flow. Going through Composio requires three things: a Composio account, a paid Moz API plan ($20/mo Starter and up, the free tier may work for light testing but the rate limit of 1 request per 10 seconds will throttle agent workflows fast), and your Moz API key pasted into Composio's credential vault. From there, Composio brokers the requests, applies your row quota, and surfaces the responses to the connected LLM. No OAuth, no token rotation, no MCP-spec transport details published by Moz. If your security model rules out third-party brokers, the alternative is writing your own MCP wrapper around the Moz API, which is achievable in a few hundred lines but unsupported by Moz.
Where it works and what to build
Via Composio, the supported clients are whatever Composio's MCP integration layer connects to, currently Claude Desktop, Claude Code, Cursor, n8n, and a handful of others through their MCP gateway. Realistic workflows worth running: ask an agent to pull Domain Authority and link metrics for a competitor list (Fetch Site Metrics + Get Top Pages), check link status on a recovery list after a redesign (Check Link Status), or pull current quota usage before a heavy batch job (Lookup Quota Info). What you give up vs a first-party MCP: no agent-optimized response shaping, no Moz-specific tool descriptions tuned for LLM reasoning, no roadmap signal that Moz is investing in agent surfaces. Composio's wrapper is functional but it's a bridge, not a destination.
Which AI clients can use Moz Pro MCP?
Not every AI assistant supports MCP natively. Per-client picture for Moz Pro:
| Client | Support | Notes |
|---|---|---|
| Claude (Desktop/Web) | Third-party bridge | Via Composio broker. Requires Composio account plus the tool's API key. |
| Claude Code | Third-party bridge | Same Composio bridge as Claude Desktop. |
| ChatGPT | Third-party bridge | Via Composio MCP gateway. |
| Cursor | Third-party bridge | Via Composio bridge. |
| Codex | Not supported | No documented path through the third-party broker. |
| Windsurf | Not supported | — |
| Cline | Not supported | — |
| Gemini | API-only (custom code) | No MCP path; call the API directly from custom code. |
| n8n | API-only (custom code) | No first-party node; HTTP Request only. |
Does Moz Pro MCP cost extra?
Moz Pro has no verified MCP server.
- No published MCP integration was detected at the last check.
- For now, agent workflows depend on the REST API or third-party automation.
Moz Pro subscription pricing
| Plan | Monthly | Annual / mo |
|---|---|---|
| Standard | $99 | $79 |
| Medium | $179 | $143 |
| Large | $299 | $239 |
| Enterprise | Contact sales | — |
Source: moz.com/products/pro/pricing. Verified 2026-05-24.
Moz Pro also publishes a REST API
Moz Pro publishes an API, but per-tier gating wasn't extracted automatically.
See Moz Pro API pageWhat you can do with Moz Pro from an AI agent
Three shapes of agent workflow. Pick the row that matches how you actually use Claude / Cursor / Codex day to day.
Skip the dashboard, ask Claude
- "What keywords moved this week?" answered in seconds
- Quick one-off questions without leaving the editor
- Pipe Moz Pro data into your personal notes / docs without writing a script
Run client analysis at agent speed
- Hand the MCP server to your team — every consultant can ask Claude about any client's Moz Pro account
- Multi-account workflows without context-switching the Moz Pro UI
- Reports you'd normally spend hours on, done before standup
Production agent workflows
- Embed in your internal Codex / Cursor agents that triage Moz Pro data daily
- Combine with other MCP servers in a multi-step agent chain
- Constrain agents to read-only roles to keep production Moz Pro safe
Limits and gotchas
- ⚠ Server unreachable on last check. May be down, moved, or auth-gated.
- Fallback: the REST API works for any flow the MCP server doesn't cover.
- Rate limits: MCP calls count against your underlying Moz Pro API quota. Burst usage from a curious agent can drain a daily allowance fast.
- No MCP available — until Moz Pro ships one, use the REST API directly.
Agent-readiness verdict
Score: 4/10 on MCP-readiness. Moz has the data and the API to support agent workflows, but they haven't built the agent-facing layer themselves. Tools that ship official MCP servers (Ahrefs, Semrush, SE Ranking) are pulling ahead on the AI-stack-fit dimension. If your team is committed to Moz for Domain Authority or Moz Local, the Composio bridge works. If you're choosing a new SEO tool primarily for AI-stack fit, look at the tools with first-party MCP first.
Skip for agent workflows. Moz Pro has documented public API access, but lacks MCP support, OpenAPI specs, and any SDK implementations that would let Claude or Cursor interact with it meaningfully. The missing webhook and structured-output support means you'd need extensive custom integration work to pipe SEO data into agentic systems.
Scored 2026-05-24 by Joonas (TMB).
Moz Pro MCP & API FAQ
Does Moz Pro have a public API?+
Does Moz Pro plan to add an MCP server?+
Sources
- Moz Pro official site: https://moz.com/
- API docs: https://moz.com/products/api
- Pricing source: https://moz.com/products/pro/pricing (verified 2026-05-24)
Data verified by Joonas on the dates shown. MCP server status auto-rechecked weekly.
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.