MCP rate limits and tier gating
Each plan gets a different MCP request-per-minute budget and tool allow-list. Free/LTD-1 read-only and 1 site; Agency gets everything.
Quick answer#
Rate limits and tool access scale with plan. Free is read-only against 1 site; Pro unlocks all read+write tools; Agency/Enterprise unlocks admin tools.
Per-tier gating#
list_sites, get_site, list_incidents, get_incident; list_sites capped to 1 resultadd_maintenance_windowRate limits#
Retry-After headerapi_request_logs with endpoint = mcp:<surface>:<name>Where to find it in Lemwatch#
Settings → MCP tokens shows your current plan limits.
FAQ#
What if I hit the limit?#
Space out calls, batch queries, or upgrade.
Do prompts count against limits?#
Only tool calls count. Loading prompts and resources are cheap and untracked.
Related#
Previous
MCP tool catalog: everything Claude and ChatGPT can call
Next
MCP security model and role scopes
Related Articles
What is the Lemwatch MCP server?
Lemwatch runs a hosted Model Context Protocol server so AI assistants like Claude and ChatGPT can read your sites and act on incidents.
MCP tool catalog: everything Claude and ChatGPT can call
The 11 MCP tools, 4 resources, and 5 prompts Lemwatch exposes to AI assistants — with what each one does and who can call it.
AI usage and quotas
How AI features count against your monthly quota, per-tier limits, and what happens when you hit the cap.
Google Search Console & GA4 Integration
Connect Google Search Console and GA4 to see search performance and traffic data inside LemWatch.